Introduction to
Analysis of
Spatial &
Temporal Data
For B3 Students
Code: TBD
by Dr. Nguyen-Xuan Thanh
(
[email protected])
Lecture 01
Introduction &
Preparation
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
2
Introduction
Personal Information
v Full name:
NGUYEN XUAN THANH
v PhD in:
Environmental Science,
Policy and Management
The Hong Kong University
of Science and
Techonology (HKUST)
v Email:
nguyen-
[email protected]
[email protected]
v Mobile:
+84 (0) 375 713 523 http://remosat.usth.edu.vn/~thanhnx/
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
3
References
Book(s) & Website(s)
Main Contents
v Most of the contents are modified based on:
1) R. S. Bivand et al. Applied Spatial Data Analysis with R.
[https://link.springer.com/book/10.1007/978-1-4614-7618-4] 2nd edition. Springer 2013.Book
2, Elsevier 2000
2) S. Banerjee, B. P. Carlin, and A. E. Gelfand. Hierarchical Modeling and Analysis for
Spatial Data.
[https://www.taylorfrancis.com/books/mono/10.1201/9780203487808/hierarchical-modeling-
analysis-spatial-data-sudipto-banerjee-bradley-carlin-alan-gelfand-sudipto-banerjee]
For R Programming
v Although most of the required contents related to R will be covered during the
lectures, students can further enhance their understanding of R through
numerous free-online resources.
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
4
Objectives
v Understand the fundamental concepts of spatial and temporal data
v To address the questions: How can information, distribution and trends
of objects be extracted from spatial-temporal data?
v To address the questions:
ü What are the popular models used in spatial and temporal analysis?
ü What are the applications of these models for monitoring the
environment and earth sciences?
ü and How can the models be manipulated in R?
v To answer questions: How to evaluate the spatio-temporal statistical
models using reference data?
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
5
Outcomes
Course Intended Learning Outcomes
v CLO 1: demonstrate a solid understanding of basic statistical methods
concepts.
v CLO 2: gain integrated insights from specific case studies and synthesize
important advances in spatio-temporal analysis.
v CLO 3: describe the key concepts and definitions relating to different
types of spatio-temporal data.
v CLO 4: understand the approaches for estimating probability distribution
of different spatio-temporal data.
v CLO 5: perform basic analysis using R programming and interpret the
results.
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
6
Rules & Policies
Time Commitment
v 12 classes in total
o 2 classes per week for 6 weeks (19/12/2023 – 26/02/2024)
v Personal computers are more welcome
Component Attendance
Lecture 20 hours
Tutorial/Exercises -
Practical/Labwork 16 hours
Total 36 hours
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
7
Rules & Policies
Assessment Scheme (Tentative)
Component Attendance Exercise Practical Reports Mid-term Final Exam
Percentage
10 (10) - 10 (20) - 30 (20) 50
(%)
v Final Exam can be replaced by presentation & report of a topic.
v Respect yourself and the others
v Honesty
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
8
Contents (tentative)
Chapter 1 & 2
Chapter & Lecture Practice
Contents
Contents hours hours
Chapter 1 - Types of data, geographic data 2 1
Introduction - Structure of geo-referenced vector data and
raster data
- Collection of temporal and spatial data
- Preparation of data
- Practice: Introduction to R
Chapter 2 - Robustness & Resistance of data analysis 3 2
Empirical - Numerical Summary Measures
Distribution - Graphical Summary Devices: Stem-and-Leaf
& Display, Histograms, Boxplots, Kernel Density
Exploratory Smoothing, Cumulative Frequency
Data Distributions, Transformations
Analysis - Practice: Exploratory Techniques in R
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
9
Contents (tentative)
Chapter 3
Chapter & Lecture Practice
Contents
Contents hours hours
Chapter 3 - Classification, components, concept of 5 5
Probability stationarity, decomposition of time series
Distribution - Parametric approach
& Trend - Linear Regression
detection - Non-Parametric approach – Turning Point test,
and slope Man-Kendall Test, Pre-Whitened Mann Kendall
estimation test, Theil and Senʼs Median Slope
of - Bivariate Joint Probability Distribution
Timeseries - Practice: Probability Distributions in R
- Practice: Bivariate Joint Probability
Distribution in R
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
10
Contents (tentative)
Chapter 4
Chapter & Lecture Practice
Contents
Contents hours hours
Chapter 4 - Poisson processes 3 2
Point - Second-order interactions
processes - Spectral & wavelet analysis
frequency - Time-frequency analysis
analysis - Non-negative matrix factorization
- Spatio-temporal point processes
- Practice: Spectral & Wavelet analysis with R
- Practice: Spatio-temporal point processes
with R
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
11
Contents (tentative)
Chapter 5
Chapter & Lecture Practice
Contents
Contents hours hours
Chapter 5 - Extracting spatial distribution of objects in 3 3
Analysis of multi-spectral data
geo- - Un-supervised classification (Isodata, K-
reference means)
multi- - Supervised classification (Parallelepiped,
spectral data Minimum distance, Maximum likelihood,
Spectral angle mapper)
- Practice (tentative): extract information from
panchromatic satellite images
- Practice (tentative): extract information from
multi-hyper spectral satellite images
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
12
Contents (tentative)
Chapter 6
Chapter & Lecture Practice
Contents
Contents hours hours
Chapter 6 - Kriging for spatio-temporal data 4 3
Spatio- - Dynamic Autoregressive Spatio-Temporal
temporal Models
models and - Non-probabilistic forecasts for discrete
its predictands, ROC
applications - Hierarchical models for spatio-temporal data
to predict future distribution of natural
phenomena
- Frequentist Statistical Inference & Statistical
Testing
- Practice: predicting the future changes of land
cover from multi temporal satellite images
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
13
Warm Up!
Introduction & Installation of R
v Letʼs visit following website and try your self first
1) https://posit.co/download/rstudio-desktop/
2) https://www.w3schools.com/r/default.asp
3) https://www.r-project.org
Nguyen-Xuan Thanh Analysis of Spatial & Temporal Data Lecture 01 (12/2023)
