An explainable semi-supervised deep learning framework for mineral prospectivity mapping: DEEP-SEAM v1.0
Preprint
- 15 September 2025
- preprint
- Published by Copernicus GmbH in EGUsphere
- Vol. 2025, 1-43
Abstract
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.Keywords
All Related Versions
- Published version: Geoscientific Model Development, 19 (7), 2593.
Funding Information
- China Scholarship Council (202206410105)
- Australian Research Council (LP210100173)
This publication has 53 references indexed in Scilit:
- Graph Deep Learning Model for Mapping Mineral ProspectivityMathematical Geosciences, 2022
- Uncertainties in GIS-Based Mineral Prospectivity Mapping: Key Types, Potential Impacts and Possible SolutionsNatural Resources Research, 2021
- Random-Drop Data Augmentation of Deep Convolutional Neural Network for Mineral Prospectivity MappingNatural Resources Research, 2020
- Geodata Science-Based Mineral Prospectivity Mapping: A ReviewNatural Resources Research, 2020
- Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a surveyArtificial Intelligence Review, 2019
- The Rare Earth Elements: Demand, Global Resources, and Challenges for Resourcing Future GenerationsNatural Resources Research, 2017
- The Principal Rare Earth Elements Deposits of the United States: A Summary of Domestic Deposits and a Global Perspective2012
- Principal component analysis for compositional data with outliersEnvironmetrics, 2009
- Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, JapanMathematical Geology, 1996
- Basic concepts in three-part quantitative assessments of undiscovered mineral resourcesNatural Resources Research, 1993