Explainable Machine Learning in Mineral Prospectivity Mapping: A Critical Review of Methods, Geological Knowledge Embedding, Validation, and Future Directions
Open Access
Abstract
Mineral prospectivity mapping (MPM) increasingly integrates geological, geochemical, geophysical, remote-sensing, and structural evidence through machine-learning workflows. Predictive accuracy alone, however, does not establish that a prospectivity map is geologically credible or useful for exploration decisions. This critical narrative review examines explainable artificial intelligence (XAI) for MPM through the connections among model behavior, mineral-system knowledge, sampling, spatial validation, uncertainty, and field evidence. We distinguish methods demonstrated in representative MPM studies from general explanation tools and proposed applications. Study-level comparisons show that SHAP and permutation-based attribution can support evidence-layer auditing and target interpretation, while their meaning depends on correlated predictors, label construction, and evaluation design. Spatially separated evaluation tests a different generalization problem from random splitting; neither replaces newly acquired field evidence. Geological plausibility, model faithfulness, explanation stability, and decision utility therefore require separate assessment. We synthesize practical pathways for geological knowledge embedding and three-dimensional modeling, identify limits in current graph explanations and uncertainty reporting, and propose a minimum reporting checklist. Future priorities include geospatial foundation models, source-traceable language tools, three-dimensional prospectivity and four-dimensional extensions incorporating geological time, knowledge-guided hypothesis generation, integrated exploration systems, and field-based evaluation of explanations.Keywords
Funding Information
- Department of Human Resources and Social Security of Guangxi Zhuang Autonomous Region (RZ2500002043)
- Department of Science and Technologies of Guangxi (2025GXNSFBA069413)
- Department of Science and Technologies of Guangxi (2026GXNSFAA00640908)
- Guangxi Academy of Artificial Intelligence (GXAAIPY02012)
- Guangxi University for Nationalities (2023KJQD34)
This publication has 80 references indexed in Scilit:
- Mineral prospectivity mapping under extreme imbalance using contrastive embeddings balanced learning and integrated uncertainty analysisDiscover Computing, 2026
- Dual Random Fields and Their Application to Mineral Potential MappingMathematical Geosciences, 2025
- Geologically Constrained Convolutional Neural Network for Mineral Prospectivity MappingMathematical Geosciences, 2024
- Workflow-Induced Uncertainty in Data-Driven Mineral Prospectivity MappingNatural Resources Research, 2024
- A Framework for Data-Driven Mineral Prospectivity Mapping with Interpretable Machine Learning and Modulated Predictive ModelingNatural Resources Research, 2023
- An Interpretable Graph Attention Network for Mineral Prospectivity MappingMathematical Geosciences, 2023
- A Geologically Constrained Variational Autoencoder for Mineral Prospectivity MappingNatural Resources Research, 2022
- Uncertainties in GIS-Based Mineral Prospectivity Mapping: Key Types, Potential Impacts and Possible SolutionsNatural Resources Research, 2021
- Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, JapanMathematical Geology, 1996
- Support-vector networksMachine Learning, 1995