GFM4MPM: Towards Geospatial Foundation Models for Mineral Prospectivity Mapping

TL;DR

This paper introduces a self-supervised geospatial foundation model for mineral prospectivity mapping, leveraging unlabeled data to improve prediction robustness and interpretability in mineral exploration.

Contribution

It proposes a masked image modeling framework for pretraining on unlabeled geospatial data, enhancing mineral prospectivity prediction accuracy and interpretability.

Findings

Self-supervised pretraining improves prediction robustness.

The model effectively interprets geological features.

Enhanced prospectivity mapping in North America and Australia.

Abstract

Machine Learning (ML) for Mineral Prospectivity Mapping (MPM) remains a challenging problem as it requires the analysis of associations between large-scale multi-modal geospatial data and few historical mineral commodity observations (positive labels). Recent MPM works have explored Deep Learning (DL) as a modeling tool with more representation capacity. However, these overparameterized methods may be more prone to overfitting due to their reliance on scarce labeled data. While a large quantity of unlabeled geospatial data exists, no prior MPM works have considered using such information in a self-supervised manner. Our MPM approach uses a masked image modeling framework to pretrain a backbone neural network in a self-supervised manner using unlabeled geospatial data alone. After pretraining, the backbone network provides feature extraction for downstream MPM tasks. We evaluated our approach alongside existing methods to assess mineral prospectivity of Mississippi Valley Type (MVT) and Clastic-Dominated (CD) Lead-Zinc deposits in North America and Australia. Our results demonstrate that self-supervision promotes robustness in learned features, improving prospectivity predictions. Additionally, we leverage explainable artificial intelligence techniques to demonstrate that individual predictions can be interpreted from a geological perspective.