Satellite imagery is employed for large-scale prospectivity mapping due to the high cost and typically limited availability of on-site mineral exploration data. In this work, we present a proof-of-concept framework that leverages generative representations learned from multispectral Sentinel-2 imagery to identify gold-bearing regions from space. An autoencoder foundation model, called Isometric, which is pretrained on the large-scale FalconSpace-S2 v1.0 dataset, produces information-dense spectral-spatial representations that serve as inputs to a lightweight XGBoost classifier. We compare this representation-based approach with a raw spectral input baseline using a dataset of 63 Sentinel-2 images from known gold and non-gold locations. The proposed method improves patch-level accuracy from 0.51 to 0.68 and image-level accuracy from 0.55 to 0.73, demonstrating that generative embeddings capture transferable mineralogical patterns even with limited labeled data. These results highlight the potential of foundation-model representations to make mineral exploration more efficient, scalable, and globally applicable.
@article{arxiv.2602.06748,
title = {Gold Exploration using Representations from a Multispectral Autoencoder},
author = {Argyro Tsandalidou and Konstantinos Dogeas and Eleftheria Tetoula Tsonga and Elisavet Parselia and Georgios Tsimiklis and George Arvanitakis},
journal= {arXiv preprint arXiv:2602.06748},
year = {2026}
}
Comments
Presented in Eurips2025, 1st Workshop: Advances in Representation Learning for Earth Observation