Parami University

Citizen Science (Spring 2024)

Topic

Data Science and Statistics

Course Objectives

 Learn basic Data Science concepts

 Learn the Role of Data Science in Climate change

2
 Today’s Overview
 SECTION I
 Basic about Data & Information
 SECTION II
 Data Science
• Data Background & History
• Need of Data Science
• Tools of Data Science
• Data Science Components
• Applications of Data Science
 SECTION III
 Data Science in Climate Change
• Role of Data Science in Climate Change
• Data Science Tools and Techniques use in Climate Change
• Data Science Key areas/solutions in Climate Change
• Data Science Solutions in Climate Change (Real World Examples)
Basic Questions:

Do you know about the data and Information?

What is the difference between data and Information?
Do you know about the Data Science?
 Section I

Data & Information

5
 What is Data
Data
 The data is information such as facts and numbers used
to analyze something or make decisions.

 Numbers, characters, symbols, images etc. Which can be

processed by a computer.

 Data must be intrepeted by a human or computer to

derive meaning
 So data is meaningless
 What is Data
Data Examples
 Names of students, marks obtains in exams, address,
etc.

 Yes, No, Yes, No, Yes, No, No

 42, 50, 120, 450, 35, A, B, C

 None of above data sets have any meaning until they

are given a CONTEXT and PROCESSED into a
 What is Data
Mainly Data is divided into two types
1. Numberic Data (Represnted in the form of Numbers)
2. Character Data
Fall into the following two groups
o String Data
 Alphabetic Data (Represented by capital and small
letters)
 Alphanumeric Data (Combination of Letters and
Numbers)
 Text Data (Sentences & Paragraphs used in written
 What is Information
Information
 The collection of data which conveys some meaningful
idea is called information.
OR
 Data that has been processed within a context to give it
meaning is called information.
OR
 Information is interpreted data

 Information is meaningful.
 Data Processing
Data Processing
Any operation or set of operations performed upon data to convert into
meaningful form/information is called data processing.

For Example: What does the number 29061996 mean?

 Is it:
o A birthday (26th June 1996)
o A bank account number
o A telephone number

 Without processing or more information this data is meaningless.

 Data Processing
Example

Raw Data 51, 77, 88, 82, 64, 70

Context Test score achieved by

students

Processing
Average test score is calculated
Information 67%. This shows a student’s
score in a assessment
 Data Processing
Data Processing Cycle
Once data is collected, it is processed to convert it into useful
information. The data is processed again and again until the accurate
resut is achieved. This is called data processing cycle.
Usually, Data processing activity involves four basic steps.

 Input
 Processing
 Output
 Storage
 Data Processing
Data Processing Cycle
Process can be:
Manipulation of data. e.g.,
arithmetic operations,
Data is comparing, sorting, Information is
meaningless searching, etc. meaningful

Data Output
Input Data
Processing Information

Information is produced on
Data is put through input
output device such as
devices, such as keyboard
screen
Type of Digital Data

14
 Type of Digital Data
Digital data is classified into the following Three categories

 Structured Data
 Semi-Structured Data
 Unstructured Data
 Type of Digital Data
Structured Data
 This data has a well defined structure

 This is the data which is in an organized form (e.g., in

rows and columns) and can be easily used by a
computer program.

 Relationships exist between entities of data, such as

classes and their objects.
 Type of Digital Data
Example of Structured Data
Data stored in databases is an example of structured data.
 Type of Digital Data

Sources of Structured Data

 Databases: Oracle, IBM-DB2, Microsoft SQL Server, SQL, MySQL,
PostgreSQL

 Spreadsheets : MS Excel, Google sheets

 Type of Digital Data
Unstructured Data
 This data does not has a well defined structure

 This data can not be easily access by a computer

program.

 About 80—90% data of an organization is in this format

 Type of Digital Data
Examples
chat rooms, PowerPoint presentations, images, videos,
letters, papers, body of an email, etc.
 Type of Digital Data
Sources of Unstructured Data

Web Pages, Images, Free-Form Text, Audios, Videos, Body

of Email, Text, Messages, Chats, Social Media data, Word
Document.
 Type of Digital Data
Semi- Structured Data
 This is the data which does not conform to a data model
but has some structure
 However, However, it is not in a form which can be used
easily by a computer program
Examples
emails, XML, markup languages like HTML, etc.

Metadata for this data is available but is not

sufficient
 Type of Digital Data
Example
 Type of Digital Data
Sources of Semi - Structured Data
 XML: eXtensible Markup Language (XML) (store data in XML format)

 JSON: Java Script Object Notation (JSON) (store data in JSON format)

 MongoDB (store data natively in JSON format).

Type of Digital Data
Qualitative Data & Quantitative Data

26
 Qualitative & Quantitative Data
Quantitative Data
Quantitative data is anything that can be counted or
measured; it refers to numerical data.

Qualitative Data
Qualitative data is descriptive, referring to things that can
be observed but not measured. For example, colors or
emotions, responses to a survey, note from observation,
transcripts from interviews, etc.
Qualitative Data vs Quantitative Data
Qualitative Data Quantitative Data
•Deals with descriptions. •Deals with numbers.

•Data can be observed but not •Data which can be measured.

measured.
•Length, height, area, volume, weight,
•Colors, textures, smells, tastes, speed, time, temperature, humidity, sound
appearance, beauty, etc. levels, cost, members, ages, etc.

•Qualitative → Quality •Quantitative → Quantity

 Qualitative Analysis & Quantitative Analysis
Qualitative Analysis Quantitative Analysis
Subjective analysis due to absence of Objective analysis due to presence of
statistical data statistical data
Classification of data on the bases of Classification of data based on measureable
attributes and properties such as, color, gender, etc. quantities like volume, weight, length, density, etc.
Small data collection Large data collection

Result are particular to the objects being Obtained results can be applicable on
examined the general population
Indefinite questions, observations and Measurements, surveys, observation and
interviews are conducted by researches experiments are made by researchers
Methodology of qualitative analysis is Methodology of quantitative analysis is conclusion
investigative
Data Analysis and Data Analytics

30
 Data Analysis and Data Analytics
Data Analysis
Data Analysis is the process of systematically applying
statistical and/or logical techniques, such as cleaning,
transforming and modeling data to achieve the results or
get useful information.
For example,
In healthcare industry. Through data analysis, healthcare
providers can predict disease outbreaks, improve patient
care, and make informed decisions about treatment
strategies.
 Data Analysis and Data Analytics
Data Analytics
 Data analytics is the science of analyzing raw data to
make conclusions about information.

 Data analytics converts raw data into actionable forms.

 It includes a range of tools, technologies, and processes

used to solve problems by using data.
 Data Analysis and Data Analytics
Example
The Parami university record the students , faculty and course details such as students,
biographic information, courses details, marks, enrolment, etc. Analyze this data to give
the students in deep detail, such, the find out the number of students gender wise (how
many boys and how many girls, etc.)., analyze the students regions wise, course wise,
predict the number of students in the coming year, etc.
 Data Analysis and Data Analytics
Data Analysis Data Analytics

Data definition, cleaning, investigation

and transformation into meaningful Data collection & its investigation
results
Used in businesses to analyze data and Used in businesses to make verdicts
extract useful insights from the data from data which are data-driven
Used to performpredictive analysis, Used to find market trends, customer
descriptive analysis, exploratory preferences, masked patterns,
analysis, inferential analysis anonymous correlations
Data Mining

35
 Data Mining
What is Data Mining
Data mining is the process of searching and analyzing a big dataset of raw data in order
to identify patterns and extract useful information. It looks for anomalies, patterns or
correlations among millions of records to predict results.

Example
In Marketing: Data mining is used to explore increasingly large databases and to
improve market segmentation. By analyzing the relationships between parameters such
as customer age, gender, tastes, etc. It also predicts which users are likely to unsubscribe
from a service, etc.
Big Data

37
 What is BIG DATA?
● A Collection of large and complex datasets which are difficult to store
and process using the traditional database and data processing tools is
considered as big data. Big data is collected from traditional and digital
sources which, when refined properly can be used for research and
analysis.

● Everything around us generates big data continuously. Social media websites

 Where does BIG DATA come from?
The bulk of big data generated comes from three primary sources: social data,
machine data and transactional data.

Transactional data
Social data is generated from all the daily
comes from the Likes, transactions that take place
Tweets & Retweets, both online and offline.
Invoices, payment orders,
Comments, Video Uploads, storage records, delivery
and general media that are receipts – all are characterized
uploaded and shared via
Machine data as transactional data
the world’s favorite social
information which is generated
media platforms. by industrial equipment,
sensors that are installed in
machinery, and even web logs
which track user behavior.
Where does BIG DATA come from?

4 petabytes of data are

500 million tweets are created on Facebook
sent everyday

4 terabytes of data are

294 billion emails are created from each 65 billion messages are
sent connected car sent on WhatsApp

5 billion searches are

made
 Section II

Data Science

42
43
Introduction to Data Science

44
 Introduction to Data Science
 The simplest definition of data science is the extraction of actionable insights.

 Famous journalist Jim Gray imagined data science as a "fourth paradigm" of science
(empirical, theoretical, computational and now data-driven) and asserted that
"everything about science is changing because of the impact of information
technology" and the big data.
 Introduction to Data Science
 Data science is a deep study of the massive amount of data, which involves
extracting meaningful insights from raw, structured, and unstructured data that is
processed using the scientific method, different technologies, and algorithms.

 It is a multidisciplinary field that uses tools and techniques to manipulate the

data so that you can find something new and meaningful.

 Data science uses the most powerful hardware, programming systems, and most
efficient algorithms to solve the data related problems. It is the future of artificial
intelligence.
 Introduction to Data Science
 Data science is an inter-disciplinary field that uses scientific methods, processes,
algorithms and systems to extract knowledge and insights from many structural and
unstructured data.

 It is a "concept to unify statistics, data analysis, machine learning,

domain knowledge and their related methods" in order to "understand and analyze
actual phenomena" with data.
Data Science Concepts

48
49
 Introduction to Data Science
 Data Science as a field focused on extracting knowledge and insights from data by
using scientific methods.
 Introduction to Data Science
 It uses techniques and theories drawn from many fields within the context of
mathematics, statistics, computer science, domain knowledge and information
science.

 An area that manages, manipulates, extracts, and interprets knowledge from

tremendous amount of data.

 Data science (DS) is a multidisciplinary field of study with goal to address the
challenges in big data

 Data science principles apply to all data i.e. big and small.
Data Science History

52
 Data Science History
 The term “data science” has been traced back to 1974, when Peter Naur proposed it as
an alternative name for computer science.

 In 1996, the International Federation of Classification Societies became the first

conference to specifically feature data science as a topic.

 In 1997, C.F. Jeff Wu suggested that statistics should be renamed data science.

 In 2002, the Committee on Data for Science and Technology launched Data Science
Journal.
 Data Science History

 In 2003, Columbia University launched The Journal of Data Science.

 In 2014, the American Statistical Association's Section on Statistical Learning and

Data Mining changed its name to the Section on Statistical Learning and Data
Science, which shows the popularity of data science.
Uses of Data Science

55
 Uses of Data Science
We can say that data science is all about:
 Asking the correct questions and analyzing the raw data.

 Modeling the data using various complex and efficient algorithms.

 Visualizing the data to get a better perspective.

 Understanding the data to make better decisions and finding the final result.
 Uses of Data Science
Example:
Let suppose we want to travel from station A to station B by car. Now, we need to take
some decisions such as which route will be the best route to reach faster at the location,
in which route there will be no traffic jam, and which will be cost-effective.

All these decision factors will act as input data, and we will get an appropriate answer
from these decisions, so this analysis of data is called the data analysis, which is a
part of data science.
Need for Data Science

58
59
 Need for Data Science
 Some years ago, data was less and mostly available in a structured form, which could
be easily stored in excel sheets, and processed using BI (business intelligence) tools.

 But in today's world, data is becoming so vast, i.e., approximately 328.77 million
terabytes of data is generating on every day.

 It is predicts the world data will grow to 175 zettabytes in 2025.

(where 1 zettabytes = One trillion GB)

Note: (One trillion = 1,000 billions)

Note: (One terabytes = 1,000 GB)
 Need for Data Science
 It is estimated as per researches, that 1.7 MB of data will be created at every single
second, by a single person on earth. Every Company requires data to work, grow,
and improve their businesses.

 Now, handling of such huge amount of data is a challenging task for every
organization. So to handle, process, and analysis of this, we required some complex,
powerful, and efficient algorithms and technology, and that technology came into
existence as data Science.
 Need for Data Science
Following are some main reasons for using data science technology

 With the help of data science technology, we can convert the massive amount of raw
and unstructured data into meaningful insights.

 Data science technology is choice by various companies, whether it is a big brand or

a startup. Google, Microsoft, Facebook, Visa, Twitters, Amazon, Netflix, etc., which
handle the huge amount of data, are using data science algorithms for better customer
experience.
 Need for Data Science
Following are some main reasons for using data science technology

 Data science is working for automating transportation such as creating a self-driving

car, which is the future of transportation.

 Data science can help in different predictions such as various survey, elections, flight
ticket confirmation, weather forecast, etc.
Data Science Components

64
65
 Data Science Components
The main components of Data Science are given below

 Statistics: Statistics is one of the most important components of data science.

Statistics is a way to collect and analyze the numerical data in a large amount and
finding meaningful insights from it.

 Domain Expertise: In data science, domain expertise binds data science together.
Domain expertise means specialized knowledge or skills of a particular area. In data
science, there are various areas for which we need domain experts.
 Data Science Components
The main components of Data Science are given below

 Data Engineering: Data engineering is a part of data science, which involves

acquiring, storing, retrieving, and transforming the data. Data engineering also
includes metadata (data about data) to the data.

 Visualization: Data visualization is meant by representing data in a visual context so

that people can easily understand the significance of data. Data visualization makes it
easy to access the huge amount of data in visuals.
 Data Science Components
The main components of Data Science are given below

 Advanced Computing: Another main component of data science is advanced

computing. Advanced computing involves designing, writing, debugging, and
maintaining the source code of computer programs.

 Mathematics: Mathematics is the critical part of data science. Mathematics involves

the study of quantity, structure, space, and changes. For a data scientist, knowledge of
good mathematics is essential.
 Data Science Components
The main components of Data Science are given below

 Machine Learning: Machine learning is backbone of data science. Machine learning

is all about to provide training to a machine so that it can act as a human brain. In data
science, we use various machine learning algorithms to solve the problems.
Data Science Process

70
 Data Science Process

1 Business Problem
1 Understand

Business Questions Define Objectives

Common data science problems:

• Classification/Recognition
• Prediction/Regression
• Association
• Pattern detection/clustering
• Scoring and ranking
• Optimization
 Data Science Process
2 Data Acquisition
2

Data Sources
• Questionnaires
• Web servers
• Web services (API)
• Database
• Logs
• Online repositories
 Data Science Process
3 Data Preparation

Data Cleaning Data Transformation

• Inconsistent •Converting data from
data types one format/structure
• Missing data into another format or
• Duplicate data structure.
• etc. •Help to understand data
structure
•Understand what we
actually can do with the
data
 Data Science Process
4 Exploratory Data Analysis

name id align eye hair gender alive appearances first_appear publisher

Spider-Man (Peter Secret Good Hazel Eyes Brown Hair Male Living 4043 Aug-62 marvel

Parker) Characters

Captain America Public Good Blue Eyes White Hair Male Living 3360 Mar-41 marvel

(Steven Rogers) Characters

… … … … … … … … … …

Natalia Romanova Public Good Green Eyes Red Hair Female Living 1050 Apr-64 marvel

(Earth-616) Characters

Selection of feature variable that will be

?

used in the model development

 Data Science Process
Recognition
• Decision tree
5 Data Modeling Association • kNN
• SVM
• Itemset mining Regression
• Summarizing • Linear regression
Itemsets Clustering
• Polynomial regression
• K-mean
Mathematical/Statistical
• Hierarchical clustering
Modeling • DBSCAN

Training Set
Model

Model Evaluation Recognition/prediction Accuracy

Test
Set
 Data Science Process

6 Visualization & Communication

6

• Create powerful reports and

dashboards
• Communicate business finding to
convince the stakeholders
 Data Science Process
7 Deploy & Maintenance

Model
Test in pre-production Deploy in production
environment environment

Running Model

Monitoring

Real-time Analytics
 Data Science Process
Not enough data for analyzing
Exploratory Data
Analysis

Business Problem Data Preparation

Data Acquisition
Low accuracy

Cannot answer the business problem

Visualization &
Communication Data Modeling

Deploy &
Maintenance
Tools for Data Science

79
 Tools for Data Science
Following are some tools required for data science
 Data Analysis tools: R, Python, Statistics, SAS, Jupyter, R Studio, MATLAB, Excel,
RapidMiner

 Data Warehousing: ETL, SQL, Hadoop, Informatica / Talend, AWS Redshift

 Data Visualization tools: R, Jupyter, Tableau, Cognos.

 Machine learning tools: Spark, Mahout, Azure ML studio.

Applications of Data Science

81
82
 Application of Data Science
Following are some common applications areas of data science

 Fraud and Risk Detection

 Healthcare
 Internet Search
 Targeted Advertising
 Website Recommendations
 Advanced Image Recognition
 Speech Recognition
 Airline Route Planning
 Gaming
 Application of Data Science
Following are some common applications areas of data science

 Anomaly detection (fraud, disease, crime, etc.).

 Automation and decision-making (background checks, credit worthiness, etc.).

 Classifications (in an email server, this could mean classifying emails as “important”
or “junk”).

 Forecasting (sales, revenue and customer retention)

 Application of Data Science

 Pattern detection (weather patterns, financial market patterns, etc.)

 Recognition (facial, Voice , text , etc.).

 Recommendations (based on learned preferences, recommendation engines can refer

you to movies, restaurants and books you may like) and many more.
 Application of Data Science
 Image recognition and speech recognition: Data science is currently using for
Image and speech recognition. When you upload an image on Facebook and start
getting the suggestion to tag to your friends. This automatic tagging suggestion uses
image recognition algorithm, which is part of data science. When you say something
to you computer/mobile, for example, “My name is Sara ", etc., and these
devices respond as per voice control, so this is possible with speech recognition
algorithm.
 Application of Data Science
 Gaming World: In the gaming world, the use of Machine learning algorithms is
increasing day by day. EA Sports, Sony, Nintendo, are widely using data science for
enhancing user experience.

 Internet Search: When we want to search for something on the internet, then we use
different types of search engines such as Google, Yahoo, etc. All these search engines
use the data science technology to make the search experience better, and you can get
a search result with a fraction of seconds.
 Application of Data Science
 Transport: Transport industries also using data science technology to create self-
driving cars. With self-driving cars, it will be easy to reduce the number of road
accidents.

 Healthcare: In the healthcare sector, data science is providing lots of benefits. Data
science is being used for tumor detection, drug discovery, medical image analysis,
virtual medical bots, etc.
 Application of Data Science
 Recommendation systems: Most of the companies, such as Amazon, Netflix, Google
Play, etc., are using data science technology for making a better user experience with
personalized recommendations. Such as, when you search for something on Amazon,
and you started getting suggestions for similar products, so this is because of data
science technology.

 Risk detection: Finance industries always had an issue of fraud and risk of losses,
but with the help of data science, this can be rescued. Most of the finance companies
are looking for the data scientist to avoid risk and any type of losses with an increase
in customer satisfaction.
Machine Learning

90
 Machine Learning
Machine learning (ML) is a branch of Artificial Intelligence (AI) that uses
algorithms trained on data sets to create models that enable machines to perform
tasks like a humans, such as categorizing images, analyzing data, or predicting price
fluctuations.

ML is one of the Key component of Data Science.

Traditional Programming

Data
Computer Output

Program
Machine Learning

Data
Computer Progra
m
Output 4
 When Do We Use Machine Learning?
ML is used when:
• Human expertise does not exist (navigating on Mars)
• Humans can’t explain their expertise (speech recognition)
• Models must be customized (personalized medicine)
• Models are based on huge amounts of data (genomics)

Learning isn’t always useful:

• There is no need to “learn” to calculate payroll
5
Some more examples of tasks that are best solved by using
a
Machine learning algorithm
• Recognizing patterns:
– Facial identities or facial expressions
– Handwritten or spoken words
– Medical images
• Generating patterns:
– Generating images or motion sequences
• Recognizing anomalies:
– Unusual credit card transactions
– Unusual patterns of sensor readings in a nuclear power plant
• Prediction:
– Future stock prices or currency exchange rates
 Sample Applications
• Web search
• Computational biology
• Finance
• E-commerce
• Space exploration
• Robotics
• Information extraction
• Social networks
• Debugging software
• Solve Climate change problems
 Types of Learning

• Supervised Learning
– Given: training data + desired outputs (labels)
• Unsupervised Learning
– Given: training data (without desired outputs)
• Semi-supervised Learning
– Given: training data + a few desired outputs
• Reinforcement Learning
– Rewards from sequence of actions
 Machine Learning Example

Classification Example

● Example: Credit scoring

● Differentiating between low-
risk and high-risk customers
from their income and
savings
 Section III

Data Science in Climate Change

98
Climate Change

99
 Climate Change
What is Climate Change?
Climate change refers to long-term shifts in temperatures and weather patterns.
Natural events and human activities as contributing to average global temperatures by
increase in “Greenhouse” gases such as Carbon Dioxide (CO2).
Artificial Intelligence

101
 Artificial Intelligence
What is Artificial Intelligence (AI)
Artificial Intelligence (AI) is the science and engineering of making intelligent
machines, especially intelligent computer programs. It is related to the similar task
of using computers to understand human intelligence

AI BRANCHES
1. Machine Learning 4. Neural Networks
2. Fuzzy Logic 5. Computer Vision
3. Expert Systems 6. Natural Language Processing(Speech
4. Robotics Recognition, Image Recognition, Pattern
Recognition, etc.)
Role of AI in Climate Change

103
 Role of AI in Climate Change
AI for Climate Action
Technology Mechanism supports transformational climate solutions. Some AI-powered
solutions for climate action are already undergo, including

 Innovative adaptation technologies such as AI-powered models can provide early

warning systems to alert communities about coming disasters. The Biosphere
Reserves as Observatories for Climate Change Adaptation in Southern Africa, for
example, uses AI to predict flooding patterns in Mozambique.
 Role of AI in Climate Change
 Agri-food systems and crop management can be optimized with AI predicting the
best planting times, assessing soil health and monitoring pest and disease outbreaks.
AI-driven precision agriculture can also reduce water usage, promote sustainable
farming practices and boost food production. For example, in East Africa, the AI use
to enhance impact-based forecasting by the Climate Prediction, which is key for food
security, livelihoods, and economic development.
 Role of AI in Climate Change
 Renewable energy systems’ efficiency and reliability can be improved by AI
algorithms that predict energy demand, optimize grid operations and integrate
renewable energy sources seamlessly, reducing greenhouse gas emissions and
promoting a shift toward low-emission energy solutions. One example is the
Global Renewables Watch, a live atlas intended to map and measure utility-scale solar
and wind installations using AI and satellite images, allowing users to evaluate clean
energy transition progress and to track trends over time.
How Machine Learning Combat
Climate Change

107
 How Machine Learning Combat Climate Change
Machine learning can produce sustainability insights and help plan effective climate
action. It can use such as,

 Information gathering, such as analyzing satellite and aerial images to track

deforestation.
 Forecasting and simulation, such as using historical data and imagery to predict
extreme weather events.
 Automated decision-making, such as optimizing buildings' heating and cooling
systems based on weather conditions and usage patterns.
 How Machine Learning Combat Climate Change

 Predictive maintenance, such as detecting and patching methane leaks in natural gas
infrastructure.

 Novel scientific research, such as accelerating discovery of electrofuels, a more

sustainable type of fuel created using electricity, water and carbon dioxide.
Role of Data Science in Climate Change

110
 Data Science Role
Data science Contribute by

 Providing insights into climate change impacts

 Helping develop adaptation strategies, and offering predictive models for mitigation
efforts

 Help in understanding and addressing the challenges posed by climate change

through data-driven approaches
 Role of Data Science
 It contributes to climate change research by processing and analysing large datasets

 Identifying trends, and providing predictive models

 Help researchers in gaining a comprehensive understanding of climate patterns,

impacts, and potential solutions

 Data science supports attempts to reduce climate change

 Energy effectiveness: Machine learning (Data Science) models reduce the amount of
energy used in industrial, transportation, and building processes.
How Data Science is used to Combat
Climate Changes

113
 How Data Science is used to Combat Climate Changes

1. Data Science For Climate Understanding

 Data Collection
A robust system for monitoring and data collection captures data from various sources
• Satellites,
• Weather stations,
• Ocean buoys, and
• Sensors
This data provide a huge information about temperature, precipitation,
greenhouse gas concentrations, etc.
 How Data Science is used to Combat Climate Changes

1. Data Science For Climate Understanding (Continue…..)

 Data Processing
The raw data is preprocessed to clean and structure it for analysis. It involves
handling missing data, quality control, and converting data into standardized formats.

 Data Analysis
Data scientists utilize statistical and machine learning techniques to uncover patterns
and relationships within the data. This analysis helps identify trends, anomalies, and
potential correlations between climate variables.
 How Data Science is used to Combat Climate Changes

1. Data Science For Climate Understanding (Continue…..)

 Climate Models
Advanced climate models are developed and refined using data science techniques to
simulate future climate scenarios and simulate the earth climate system. These
models help scientists predict future climate scenarios and understand the potential
impacts of climate change
 How Data Science is used to Combat Climate Changes

2. Climate Prediction and Adaptation

Data science enables the development of climate prediction models that support informed
decision-making for climate adaptation. The system’s functions in this regard include:

 Forecasting
Climate models, driven by data science, provide short-term and long-term climate
forecasts. It enables real-time monitoring of climate variables, such as temperature,
sea levels, and weather patterns. These predictions help governments, industries, and
communities prepare for extreme weather events and plan for climate adaptation
strategies.
 How Data Science is used to Combat Climate Changes

2. Climate Prediction and Adaptation (Continue…..)

 Risk Assessment
Data science is employed to assess the risks associated with climate change,
including rising sea levels, extreme weather events, and shifts in agricultural
productivity.

 Early Warning Systems

Data science is used to develop early warning systems that provide timely alerts for
weather-related disasters, helping communities prepare and evacuate if necessary.
 How Data Science is used to Combat Climate Changes
3. Renewable Energy and Sustainability
The transition to renewable energy sources is a vital component of combating climate
change. Data science aids in the optimization of renewable energy systems, with the
following functions:

 Energy Production Forecasting

Data science models predict renewable energy production, accounting for factors
like weather conditions and energy demand. These forecasts help grid operators
manage the integration of renewables into the energy system effectively.
 How Data Science is used to Combat Climate Changes

3. Renewable Energy and Sustainability (Continue…..)

 Energy Efficiency
Data analytics and machine learning are used to optimize energy consumption and
reduce waste. Smart grids, for example, employ data science techniques to manage
energy distribution efficiently.

 Carbon Footprint Reduction

Data science contributes to reducing the carbon footprint by optimizing supply
chains, transportation, and energy consumption in industrial processes. The analysis
identifies areas where emissions can be minimized.
 How Data Science is used to Combat Climate Changes

4. Climate Policy and Decision-Making

Data science provides critical insights for policymakers and stakeholders to develop
effective climate policies and make informed decisions. The functions include:

 Policy Analysis
Data science models assess the potential impact of climate policies on emissions,
energy consumption, and other relevant metrics. This analysis informs the
development of policy strategies.
 How Data Science is used to Combat Climate Changes

4. Climate Policy and Decision-Making (Continue…..)

 Scenario Modeling
Data science enables the modeling of different climate scenarios, allowing
policymakers to evaluate the consequences of different courses of action and make
data-driven decisions.

 Emissions Monitoring
Data science is used to monitor and verify greenhouse gas emissions, ensuring
compliance with emissions reduction targets.
 How Data Science is used to Combat Climate Changes

5. Climate Communication and Education

Effective communication and education are vital for raising awareness and mobilizing
action to combat climate change. Data science functions in this context include:

 Data Visualization
Data scientists use visualization techniques to present climate data in a
comprehensible and engaging manner, making the information accessible to a
broader audience.
 How Data Science is used to Combat Climate Changes

5. Climate Communication and Education (Continue…..)

 Public Awareness Campaigns

Data-driven insights inform the content and strategy of climate change awareness
campaigns, tailoring messages to different demographics.

 Climate Education
Data science supports the development of educational tools and platforms that teach
students and the public about climate science and sustainable practices.
 How Data Science is used to Combat Climate Changes

6. Monitoring and Enforcement

A robust system for monitoring and enforcing climate agreements and regulations relies
on data science for several key functions:

 Satellite Technology
Data from remote sensing satellites is analyzed using data science to monitor
deforestation, land use changes, and carbon emissions. This information is crucial
for tracking compliance with international climate agreements.
 How Data Science is used to Combat Climate Changes
7. Citizen Engagement and Crowdsourced Data
Engaging citizens in data collection and climate monitoring can enhance the data science
system. Functions in this area include:

 Crowdsourcing
Citizens can contribute data on weather conditions, air quality, and other
environmental parameters through mobile apps and online platforms. Data science is
employed to process and integrate this crowdsourced data into climate models.

 Community Resilience
Communities use data science and crowdsourced information to build resilience
against climate change impacts, such as local flooding and heatwaves.
 How Data Science is used to Combat Climate Changes
8. Climate Finance and Investment
Data science is integral to climate finance by supporting the allocation of resources to
projects that reduce emissions and promote sustainability. Functions in this realm
include:

 Investment Analysis
Data science helps assess the financial viability and environmental impact of
climate-related projects, facilitating investment decisions by governments,
organizations, and individuals.
 How Data Science is used to Combat Climate Changes

8. Climate Finance and Investment (Continue…..)

 Carbon Markets
Data science is used to develop and optimize carbon markets, ensuring accurate
measurement and verification of emissions reductions.

 Impact Measurement
Data-driven impact assessment determines the effectiveness of climate finance
initiatives, enabling adjustments and improvements in resource allocation.
Data Science Tools and Techniques use in
Climate Change

129
Data Science Tools and Techniques Use in Climate Change
To address the challenges of climate change, data scientists use a wide range of tools and
techniques

1. Machine Learning: Machine learning algorithms can identify complex patterns in

climate data, allowing for more accurate predictions and better climate models.
For example, neural networks are used to predict future temperature changes and analyze
the impact of greenhouse gas concentrations.

2. Big Data Analytics: Climate data is massive and ever-growing. Big data analytics
tools help manage and process this data efficiently, making it easier to extract insights
and respond to climate events in real-time.
 Data Science Tools and Techniques Use in Climate Change

3. Remote Sensing: Satellites equipped with remote sensing technology provide a

continuous stream of data about the Earth's surface. This data helps in monitoring
deforestation, glacier melt, and changes in land use patterns.

4. Geospatial Analysis: Geospatial data and geographic information systems (GIS) are
used to understand the spatial distribution of climate-related phenomena, such as
temperature changes, sea-level rise, and the impact on local ecosystems.
Data Science Key Areas / Solutions in
Climate Change

132
 Data Science Solutions in Climate Change
Some key areas where Data Science/Data-Driven solutions are making
a difference

1. Renewable Energy Optimization: Data science helps optimize the use of renewable
energy sources like wind and solar power. By analyzing historical weather data and
energy production, we can better predict when and where to deploy these resources for
maximum efficiency.

2. Precision Agriculture: Data science is used in precision agriculture to enhance crop

yields while minimizing resource use. By analyzing soil data, weather patterns, and crop
health, farmers can make informed decisions on irrigation, fertilization, and pest control.
 Data Science Solutions in Climate Change
3. Climate Resilience: Vulnerable communities benefit from data-driven strategies that
enhance climate resilience. These solutions include flood prediction models, early
warning systems, and disaster response plans based on historical weather data and
geographic factors.

4. Green Transportation: Data science is revolutionizing transportation by optimizing

routes, reducing emissions, and promoting the use of electric vehicles. Traffic data and
smart city initiatives are helping reduce the carbon footprint of urban areas.
Data Science Solutions in Climate Change
(Real World examples)

135
 Electricity Systems
Enabling Low-Carbon Electricity

136
 Enabling Low-Carbon Electricity Example
Enabling Low-Carbon Electricity

 Many electricity system have data

 The power industry try to use AI & ML to introduce the smart grid

 The electricity system is responsible for about a quarter of human-

caused GHG (Greenhouse Gasses) emissions each year [1].

1. IPCC. 2014. Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. O.
Edenhofer, et all Minx (Eds.). Intergovernmental Panel on Climate Change
 Enabling Low-Carbon Electricity Example
Enabling low carbon electricity
Low-carbon electricity sources are essential to tackling climate change.

These sources are: Solar panels, wind turbines, and other electricity generators (they
need natural gas plants, storage, or other controllable sources ready to buffer changes in
their output. These sources are provided by coal and natural gas plants which provide
huge amount of CO2).
Enabling Low-Carbon Electricity

139
 Enabling Low-Carbon Electricity Example
Role of ML in enabling low carbon electricity
 ML can contribute in research, deployment, and operation of electricity system
technologies, including

• Accelerating the development of clean energy technologies

• Improving forecasts of demand and clean energy
• Improving electricity system optimization
• Enhancing system monitoring

These contributions require a variety of ML paradigms and techniques

 Enabling Low-Carbon Electricity Example
Role of ML in enabling low carbon electricity

 ML can both reduce emissions from today’s standby generators and enable the
transition to carbon-free systems by helping improve necessary technologies
(namely forecasting, scheduling, and control) and by helping create advanced
electricity markets that accommodate both variable electricity and flexible demand.
Example
 Forecasting supply and demand
ML methods can be used to forecast electricity supply and demand (used historical data,
physical model outputs, images, video data).
 Enabling Low-Carbon Electricity Example
 Improving scheduling and flexible demand
ML can help improve the existing (centralized) process of scheduling and dispatch by
speeding up power system optimization problems and improving the quality of
optimization solutions.

 Advance variable power generation

ML can be used to optimized and better use of power generation systems.
For example, use low-carbon variable generators produce energy as efficiently and
profitable as possible
 Enabling Low-Carbon Electricity Example
 Optimized use of solar panels
ML can be use to connect the solar panels into the electric grid.

 Managing existing technologies

New technologies (geothermal, nuclear fission, dam-based hydropower) can be
use
to reduced the emission of carbon while generating the electricity.
• ML can provide valuable input in planning where these technologies should be
deployed
• ML can also help maintain already-operating power plants
Transportation

144
Transportation

145
 Transportation Example
Role of ML in enabling low carbon in Transportation

 Reducing Transport Activity

• ML can be use to reduced the number of vehicles on the road.
• ML can be use to classify roads with similar traffic patterns
• ML can provide information about mobility patterns.
• ML can use to help to provide alternative to transport
• etc.
 Improving Vehicle Efficiency
• ML can help design more efficient vehicles and the impacts that autonomous
driving may have on GHG emissions.
• ML can help to propose better design for vehicles that emit low CO 2
 Transportation Example
 Alternative Fuels and Electrification
 Electric vehicles
• ML is used to improve charge scheduling, congestion management, and
vehicle-to-grid algorithms
• ML methods have also been applied to battery energy management

 Alternative Fuels
Much of the transportation sector dependent on (liquid fossil fuels, Electro fuels,
Solar fuels, Hydrogen & natural gas.
• ML techniques can be used to provide best option of fuels that emit less emit
low CO2
 Transportation Example
 Transport Modal Selection

• ML techniques can help transportation policymakers about passengers travel

mode choice.
• ML help policymakers to select best transport options (e.g., Bus, Rail, etc.) to
save energy and reduced the emission of CO2 .
• ML techniques can use provide the bike or car sharing option to reduce the
traffic on the road and reduced the emission of CO2 .
Buildings and Cities

149
Optimizing Buildings

150
 Optimizing Buildings and Cities Example
Designing new buildings and improving existing ones, there are numerous
technologies that can reduce GHG emissions

ML can used to
 Modeling data on energy consumption and
 Optimizing energy use (in smart buildings).
 Optimizing Buildings and Cities Example
 Modeling data on energy consumption
• ML can used to forecast the energy demand of specific buildings.
• Energy demand depend on building physical design and physical structure of the
building
• ML can used to evaluate and forecast the predication ignoring the building
physical design and physical structure
• ML can be use how to transfer the knowledge gain in the deign of one building
to another building design
 Optimizing Buildings and Cities Example
 Smart Buildings
In smart buildings intelligent control systems can be used to decrease the carbon
emission.
• ML can be use to reduce energy usage
• ML can be use forecasting which temperature are need through the systems
• ML can be use for automatics building diagnostics and maintenance through
fault detection.
• ML can be used to derive high level patterns, while designing strategies such as
district heating and cooling, integrating new technology within buildings, etc.
• ML can be used to Modeling energy use across buildings.
• ML can be use for gathering infrastructure data.
 Optimizing Buildings and Cities Example
 Future of Cities
For the smart cities development, the city govt. try to regulate transportation, buildings,
and economic activity. For this they handle, diverse issues, including energy, water,
waste, crime, health, etc.

• ML and data use for improving efficiency in these areas

• In smart cities applications, ML use to preprocess large amount data in large
sensor network and identify what data is transmitted form all this raw data.
• ML can help the policy makers in data management while design strategies for
smart cities.
Industry

155
Selected opportunities to reduce GHG emissions in industry using ML

156
Farms & Forests

157
Selected opportunities to reduce GHG emissions from land use using ML

158
Best Climate Datasets for
Machine Learning

159
Best Climate Datasets for Machine Learning
1. World Bank Climate Change Data
2. Climate Change: Earth Surface Temperature Data
3. International Greenhouse Gas Emissions
4. Daily Sea Ice Extent Data
5. Temperature Change Dataset
6. Air Quality Annual Summary
7. VEMAP 2: Annual Ecosystem Model Responses to U.S. Climate Change,
1994 - 2100
8. Climate Change Tweets Ids
9. EU emission trading system
Data Science (Machine Learning) Research
in Climate Change

161
The Data Science Research in Climate Change

The growth in the publications on applications of machine learning (ML) and deep learning (DL) in climate
162
change mitigation and adaptation (left) and the dominant subject areas (right).
The most frequent
machine learning and
deep learning
methods applied for
climate change
adaptation and
mitigation.

163
 Thanks You
Questions/ Answers

164