28 Geoscience and Hydrogeology in the AI Era: From Predictive Models to Real-Time Applications (Posters)

This session offers a unique platform to showcase advancements in Artificial Intelligence (AI), Machine Learning (ML), and physics-informed methodologies, focusing on topics in hydrogeology, subsurface flow and transport, real-time geophysical inversion, critical minerals, and energy applications.

Sunday, 19 October 2025
8:00 AM - 5:30 PM
HBGCC, Hall 1

Deep Learning for Automated Mineral Classification Using ResNet in the AI Era

Paper number: 28-1
Program: Technical Sessions
Time: 8:00 AM – 8:00 AM

Authors

Abstract

Accurate mineral classification plays a critical role in geoscientific analysis and resource exploration. Conventional methods often require manual inspection of petrographic or hyperspectral images, which can be both labor-intensive and subjective. In this work, we present a deep learning-based approach for automated mineral type identification using a ResNet-based convolutional neural network (CNN). The model is trained on a diverse dataset of high-resolution microscopic images representing common silicate, oxide, and sulfide minerals with varied textures and grain boundaries.

Our ResNet architecture captures hierarchical spatial features effectively, enabling robust classification with over 90% accuracy across multiple mineral classes. To ensure field applicability, we incorporate image augmentation and domain adaptation techniques, allowing the model to generalize across imaging conditions and geological contexts. Additionally, we develop a lightweight inference pipeline that supports near real-time mineral recognition in field environments, such as during core logging or drilling.

This study demonstrates the power of deep learning—particularly ResNet architectures—in transforming traditional geoscientific workflows. By bridging predictive modeling with real-time applications, our approach contributes to a more efficient, consistent, and scalable solution for mineral classification in the AI-driven geoscience era.

Geological Society of America Abstracts with Programs. Vol. 57, No. 6

doi: 10.1130/abs/2025AM-412193

© Copyright 2025 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.