This repository documents my complete learning journey through the Coursera course Remote Sensing Image Acquisition, Analysis, and Applications. It is part of my broader PhD preparation plan in AI-powered environmental monitoring and blue carbon sink estimation.
Course Provider: from John Richards, Emeritus Professor at The University of New South Wales, delivered via Coursera
Modules: 15 total, covering theory, data acquisition methods, preprocessing, analysis, and application of remote sensing in environmental and resource management.
Almost all diagrams in this repository are self-made and copyright-owned by me. Screenshots from the course are used sparingly, only when necessary, and are properly attributed under each figure. These materials are strictly for educational and non-commercial purposes.
remote-sensing-course/
│
├── README.md # Course overview and navigation
├── week 1/ # Week 1 learning notes and assets
│ ├── RS week 1.md # Week 1 comprehensive notes
│ └── RS week 1.assets/ # Week 1 diagrams and images
├── week 2/ # Week 2 learning notes and assets
│ ├── RS week 2.md # Week 2 comprehensive notes
│ └── RS week 2.assets/ # Week 2 diagrams and images
├── week 3/ # Week 3 learning notes and assets
│ ├── RS week 3.md # Week 3 comprehensive notes
│ └── RS week 3.assets/ # Week 3 diagrams and images
├── week 4/ # Week 4 learning notes and assets
│ ├── RS week 4.md # Week 4 comprehensive notes
│ └── Week 4.assets/ # Week 4 diagrams and images
├── week 5/ # Week 5 learning notes and assets
│ ├── RS week 5.md # Week 5 comprehensive notes
│ └── Week 5.assets/ # Week 5 diagrams and images
├── week 6/ # Week 6 learning notes and assets
│ ├── RS week 6.md # Week 6 comprehensive notes
│ └── Week 6.assets/ # Week 6 diagrams and images
├── week 7/ # Week 7 learning notes and assets
│ ├── RS week 7.md # Week 7 comprehensive notes
│ └── Week 7.assets/ # Week 7 diagrams and images
├── week 8/ # Week 8 learning notes and assets
│ ├── RS week 8.md # Week 8 comprehensive notes
│ └── Week 8.assets/ # Week 8 diagrams and images
├── week 9/ # Week 9 learning notes and assets
│ ├── RS week 9.md # Week 9 comprehensive notes
│ └── RS week 9.assets/ # Week 9 diagrams and images
├── week 10/ # Week 10 learning notes and assets
│ ├── RS week 10.md # Week 10 comprehensive notes
│ └── RS week 10.assets/ # Week 10 diagrams and images
├── week 11/ # Week 11 learning notes and assets
│ ├── RS week 11.md # Week 11 comprehensive notes
│ └── RS week 11.assets/ # Week 11 diagrams and images
├── week 12/ # Week 12 learning notes and assets
│ ├── RS week 12.md # Week 12 comprehensive notes
│ └── RS week 12.assets/ # Week 12 diagrams and images
├── python_code/ # Python scripts for generating diagrams
│ ├── Integrated script to reproduce the target image.py
│ ├── Cubic Convolution Kernel Shape.py
│ ├── Effect Of Normalization On Solar Spectrum.py
│ ├── High-Order Vs Low-Order Polynomial Fitting.py
│ ├── Match the means and standard deviations.py
│ ├── Oversampling.py
│ ├── Biased vs Unbiased Variance Estimation.py
│ ├── Mean Vector and Covariance Ellipse in Spectral Space.py
│ ├── PCA_Coordinate_Transformation_Visualization.py
│ ├── Low variance (PC5-PC6) Quantization dominates (noise).py
│ ├── 3D heat-colored discriminant surface for two Gaussian mixtures.py
│ ├── True Distribution vs Gaussian Approximations.py
│ ├── Spectral class vs information class.py
│ ├── Common Activation Functions.py
│ └── Understanding oscillations in neural network training.py
└── README.assets/ # README diagrams and images
| Week | Topic | Notes | Key Concepts | Status |
|---|---|---|---|---|
| Week 1 | Image Acquisition & Error Correction | 📖 RS week 1.md | - Remote sensing fundamentals - Atmospheric effects - Imaging platforms - Scanner types |
✅ Completed 2025-08-06 |
| Week 2 | Image Distortions & Corrections | 📖 RS week 2.md | - Radiometric distortions - Geometric distortions - Correction techniques - Mathematical modeling |
✅ Completed 2025-08-10 |
| Week 3 | Geometric Correction & Resampling | 📖 RS week 3.md | - Control points - Mapping functions - Resampling methods - Image registration |
✅ Completed 2025-08-12 |
| Week 4 | Classification & Thematic Mapping | 📖 RS week 4.md | - Classification fundamentals - Supervised learning - Correlation & covariance - Principal Component Analysis |
✅ Completed 2025-08-16 |
| Week 5 | Principal Components Transform | 📖 RS week 5.md | - PCA worked examples - Data compression - Feature reduction - Change detection applications |
✅ Completed 2025-08-17 |
| Week 6 | Machine Learning in Remote Sensing | 📖 RS week 6.md | - Image analysis fundamentals - Maximum likelihood classifier - Minimum distance classifier - Bayes theorem applications |
✅ Completed 2025-08-20 |
| Week 7 | Linear Classifiers Training | 📖 RS week 7.md | - Supervised learning - Linear classification - Training algorithms - Performance evaluation |
✅ Completed 2025-08-24 |
| Week 8 | Neural Network Structure & Training | 📖 RS week 8.md | - Neural network fundamentals - Activation functions - Multilayer perceptron - Backpropagation training |
✅ Completed 2025-08-28 |
| Week 9 | Deep Learning & CNN in Remote Sensing | 📖 RS week 9.md | - Convolutional neural networks - Spatial context classification - CNN architecture & topology - Hyperspectral data analysis |
✅ Completed 2025-09-01 |
| Week 10 | Unsupervised Classification & Clustering | 📖 RS week 10.md | - K-means clustering algorithm - ISODATA clustering - SSE evaluation - Non-convex optimization |
✅ Completed 2025-10-29 |
| Week 11 | Feature Reduction & Selection | 📖 RS week 11.md | - Feature selection methods - Wrapper/Filter/Embedded approaches - ReliefF algorithm - Nonparametric discriminant analysis |
✅ Completed 2025-10-30 |
| Week 12 | Classifier Performance & Map Accuracy | 📖 RS week 12.md | - Error matrix & accuracy assessment - Cross-validation methods - Producer's & User's accuracy - True vs estimated accuracy |
✅ Completed 2025-11-02 |
| Week | Topic | Status | Expected Focus |
|---|---|---|---|
| Week 13 | Imaging radar nature | ⏳ | - SAR principles - Radar characteristics |
| Week 14 | Radar energy scattering | ⏳ | - Scattering mechanisms - Surface interactions |
| Week 15 | Radar geometric corrections | ⏳ | - Distortion types - Correction techniques |
- Python 3.8+
- Git
git clone https://github.com/henrypan1993/remote-sensing-learning-notes.git
cd remote-sensing-learning-notes
pip install -r requirements.txtcd python_code
python "PCA_Coordinate_Transformation_Visualization.py"
By the end of this course, I aim to:
- Understand the fundamentals of remote sensing theory and data acquisition.
- Master preprocessing techniques for various sensor data (multispectral, SAR, LiDAR).
- Apply image analysis and classification methods to environmental monitoring.
- Gain hands-on experience with remote sensing software and cloud platforms (e.g., Google Earth Engine).
- Build a knowledge base to support AI-powered carbon sink estimation research.
Below are sample diagrams from my notes:
As shown in the picture above, I will redraw images using Python or Excalidraw based on my own understanding of the learning content, aiming for efficient and elegant visual expression. These images have been created with a great deal of effort, thus becoming the essence of my study notes.
The python_code/ directory contains 15 scripts that generate various diagrams and visualizations:
- Integrated script to reproduce the target image.py - FOV projection visualization
- Cubic Convolution Kernel Shape.py - Convolution kernel visualization
- Effect Of Normalization On Solar Spectrum.py - Spectral normalization effects
- High-Order Vs Low-Order Polynomial Fitting.py - Polynomial fitting comparison
- Match the means and standard deviations.py - Statistical matching
- Oversampling.py - Oversampling technique demonstration
- Biased vs Unbiased Variance Estimation.py - Variance estimation comparison
- Mean Vector and Covariance Ellipse in Spectral Space.py - Statistical visualization
- PCA_Coordinate_Transformation_Visualization.py - PCA transformation demonstration
- Low variance (PC5-PC6) Quantization dominates (noise).py - Low variance component analysis
- 3D heat-colored discriminant surface for two Gaussian mixtures.py - 3D discriminant surface visualization
- True Distribution vs Gaussian Approximations.py - Distribution comparison analysis
- Spectral class vs information class.py - Class mapping visualization
- Common Activation Functions.py - Neural network activation functions visualization
- Understanding oscillations in neural network training.py - Neural network training oscillation analysis
This is a personal learning repository, but suggestions and corrections are welcome through Issues and Pull Requests. See CONTRIBUTING.md for details.
- GitHub: @henrypan1993
- Research Focus: AI-powered environmental monitoring, blue carbon sink estimation
- Course Instructor: John Richards, Emeritus Professor at The University of New South Wales
- Platform: Coursera
- Course: Remote Sensing Image Acquisition, Analysis, and Applications
All original diagrams and notes are licensed under CC BY-NC 4.0 (Attribution-Noncommercial). All original diagrams © Henry Pan. Course slides are used under fair use for educational purposes. Not for commercial use.