Masked Mineral Modeling: Continent-Scale Mineral Prospecting via Geospatial Infilling

2025-11-12

AI Summary

To address the challenge of low-cost, high-accuracy detection of concealed mineral resources under decarbonization imperatives, this paper proposes Masked Mineral Modeling (MMM): a generative framework that integrates heterogeneous geospatial data—including remote sensing, geophysical surveys, and nationwide soil surveys—and performs mineral occurrence inference at continental scale under sparse mineral deposit annotations via masked reconstruction. MMM overcomes the reliance of conventional supervised learning on dense ground-truth labels, substantially improving predictive capability in data-scarce or unexplored regions. Applied to the conterminous United States at 1×1 square mile resolution, the best-performing model achieves a Dice coefficient of 0.31±0.01 and recall of 0.22±0.02. This work establishes a scalable, data-efficient geospatial AI paradigm for large-scale strategic mineral exploration.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Minerals play a critical role in the advanced energy technologies necessary for decarbonization, but characterizing mineral deposits hidden underground remains costly and challenging. Inspired by recent progress in generative modeling, we develop a learning method which infers the locations of minerals by masking and infilling geospatial maps of resource availability. We demonstrate this technique using mineral data for the conterminous United States, and train performant models, with the best achieving Dice coefficients of $0.31 pm 0.01$ and recalls of $0.22 pm 0.02$ on test data at 1$ imes$1 mi$^2$ spatial resolution. One major advantage of our approach is that it can easily incorporate auxiliary data sources for prediction which may be more abundant than mineral data. We highlight the capabilities of our model by adding input layers derived from geophysical sources, along with a nation-wide ground survey of soils originally intended for agronomic purposes. We find that employing such auxiliary features can improve inference performance, while also enabling model evaluation in regions with no recorded minerals.

Problem

• Predicting hidden mineral deposits using geospatial data
• Improving mineral prospecting accuracy with machine learning
• Incorporating auxiliary data sources for enhanced mineral inference

Innovation

• Masked geospatial infilling for mineral prediction
• Incorporating auxiliary data sources for enhanced performance
• Achieving high spatial resolution with generative modeling