SOM-Exp: Self-Organising Maps For Hyperspectral Remote Sensing-Based Mineral Exploration

A comparative study of topology-preserving (Self-Organizing Maps) versus non-topology-preserving methods (k-means with dimensionality reduction) for hyperspectral geological mapping in the Tibooburra region, NSW, Australia.

Project Overview

This repository contains the implementation code for a thesis comparing four machine learning approaches for processing EnMAP hyperspectral satellite data:

1. Self-Organizing Maps (SOM) - Topology-preserving clustering
2. k-means + PCA - Principal Component Analysis for dimensionality reduction
3. k-means + Canonical Autoencoder - Neural network-based dimensionality reduction
4. k-means + Stacked Autoencoder - Deep learning approach with multiple encoder layers

Research Focus: Identifying Kanimblan metamorphic unit boundaries for gold exploration in the Tibooburra region.

Repository Structure

.
├── SimpleTut/                    # Tutorial folder with basic SOM examples
├── Datasets/                     # Multispectral Sentinel-2 data
├── SOM_Spectral.ipynb           # SOM clustering implementation
├── k-MeansPCA_Spectral.ipynb    # PCA + k-means implementation
├── k-MeansCA_Spectral.ipynb     # Canonical Autoencoder + k-means
├── k-MeansSA_Spectral.ipynb     # Stacked Autoencoder + k-means
├── QGIS.ipynb                   # Ground truth preparation
├── PCA & SOM.ipynb              # Initial comparison on multispectral data
├── Evluation.ipynb              # Comprehensive evaluation and metrics
└── README.md                    # This file

Requirements

# Core libraries
numpy
matplotlib
rioxarray
scikit-learn
scipy
minisom

# Deep learning (for autoencoder methods)
torch
torchvision

# Geospatial
GDAL
rasterio

# Visualization
seaborn

Install dependencies:

pip install numpy matplotlib rioxarray scikit-learn scipy minisom torch GDAL rasterio seaborn

Data

Included in Repository:

• Datasets/: Sentinel-2 L2A multispectral imagery (12 bands, 10-20m resolution)

Download Separately (Due to Size):

• EnMAP Hyperspectral Image (363.6 MB):
  • File: ENMAP01-____L2A-DT0000160657_20251016T011429Z_002_V010502_20251017T031330Z-SPECTRAL_IMAGE.TIF
  • Download from: https://unsw-my.sharepoint.com/:u:/g/personal/z5042599_ad_unsw_edu_au1/Eb53i2FdyeVPhapjG6vh494BSfKrV1ZVBIOBl6jQ44zu-Q?e=pARiRh
  • Specifications: 219 valid spectral bands, 30m resolution, 1,044,103 valid pixels
  • Place in: ./Datasets/ directory

Ground Truth Data:

• MinView simplified geological maps (shapefile format)
• Processed using QGIS.ipynb to generate rasterized ground truth
• Important: When running QGIS notebook, input shapefiles from bottom to top (youngest to oldest geological units)

Usage

1. SimpleTut - Getting Started

Start here to understand basic SOM implementation using MiniSom:

jupyter notebook SimpleTut/

2. Initial Comparison (Multispectral)

Compare PCA+k-means vs SOM on Sentinel-2 data:

jupyter notebook "PCA & SOM.ipynb"

3. Prepare Ground Truth

Convert geological shapefile to raster format:

jupyter notebook QGIS.ipynb

Note: Input shapefiles in order from bottom (oldest) to top (youngest) geological layers.

4. Run Main Methods (Hyperspectral)

Each notebook processes the EnMAP hyperspectral image and saves results for evaluation:

SOM Method:

jupyter notebook SOM_Spectral.ipynb

• Outputs: som_encoded_data.npy, som_labels_spatial.npy

PCA + k-means:

jupyter notebook k-MeansPCA_Spectral.ipynb

• Outputs: pca_encoded_data.npy, pca_labels_spatial.npy

Canonical Autoencoder + k-means:

jupyter notebook k-MeansCA_Spectral.ipynb

• Outputs: ca_encoded_data.npy, ca_labels_spatial.npy

Stacked Autoencoder + k-means:

jupyter notebook k-MeansSA_Spectral.ipynb

• Outputs: sa_encoded_data.npy, sa_labels_spatial.npy

5. Comprehensive Evaluation

Run evaluation notebook after generating all method outputs:

jupyter notebook Evluation.ipynb

Inputs: All saved .npy files from above methods + ground truth .tif

Outputs:

• Confusion matrices
• Validation metrics (ARI, NMI, Purity, Cohen's Kappa, Calinski-Harabasz, Davies-Bouldin, Silhouette)
• Comparative visualisations
• Performance analysis plots

Contributors

• Author: Cheng Wang (UNSW)
• Supervisor: Dr. Rohitash Chandra (UNSW)
• Co-supervisor: Dr. Ehsan Farahbakhsh (USYD)
• Industry Collaborator: Sam Johnson (Datarock)

Contact

For questions or collaboration opportunities:

• Email: [victorwang1995@hotmail.com]
• GitHub: [@Vi90195]

Acknowledgments

• UNSW Faculty of Computer Science and Engineering
• EnMAP satellite mission for hyperspectral data
• NSW Seamless Geology dataset
• MiniSom library developers

---

Note: This is thesis research code. For production mineral exploration applications, additional validation and domain expert review is recommended.