A Multimodal Learning Framework for Comprehensive 3D Mineral Prospectivity Modeling with Jointly Learned Structure-Fluid Relationships

TL;DR

This paper introduces a deep learning framework that combines structural and fluid data for 3D mineral prospectivity mapping, improving accuracy in identifying ore deposits through multimodal data fusion and feature alignment.

Contribution

The study develops a novel multimodal fusion model using CNN, MLP, and CCA for 3D mineral prospectivity, demonstrating superior performance over existing methods.

Findings

Outperforms existing models in ore-bearing prediction accuracy

Shows the effectiveness of joint feature utilization and CCA in data fusion

Enhances mineral exploration decision-making through improved data integration

Abstract

This study presents a novel multimodal fusion model for three-dimensional mineral prospectivity mapping (3D MPM), effectively integrating structural and fluid information through a deep network architecture. Leveraging Convolutional Neural Networks (CNN) and Multilayer Perceptrons (MLP), the model employs canonical correlation analysis (CCA) to align and fuse multimodal features. Rigorous evaluation on the Jiaojia gold deposit dataset demonstrates the model's superior performance in distinguishing ore-bearing instances and predicting mineral prospectivity, outperforming other models in result analyses. Ablation studies further reveal the benefits of joint feature utilization and CCA incorporation. This research not only advances mineral prospectivity modeling but also highlights the pivotal role of data integration and feature alignment for enhanced exploration decision-making.