A Comparative Analysis of Siamese Networks and Spectral Angle Mapper for Mineral Detection using Hyperspectral Imagery

This study conducts a comparative analysis of Siamese Networks and Spectral Angle Mapper (SAM) for mineral detection in hyperspectral images. Siamese Networks, a neural network architecture, and SAM, a spectral matching technique, are evaluated based on metrics f1-score, recall, precision, and accuracy with varying thresholds. In our research, we use an open-source dataset for over 50 different locations obtained from fieldwork in Chile to train Siamese models. Our results provide insights into the strengths and limitations of Siamese Networks and SAM, aiding researchers in selecting the most suitable approach for mineral detection. This research contributes to advancing hyperspectral imaging techniques for improved mineral exploration and resource mapping.