Home
Scholarly Works
Enhancing Effective Thermal Conductivity...
Journal article

Enhancing Effective Thermal Conductivity Predictions in Digital Porous Media Using Transfer Learning

Abstract

Porous media beneath the Earth’s surface, including aquifers, oil and gas reservoirs, and geothermal systems, play a crucial role in various natural resource management and environmental engineering applications. The study of their physical properties, particularly thermo-physical properties like effective thermal conductivity (ETC), is essential for enhancing the efficiency of subsurface engineering technologies including nuclear waste disposal, geothermal energy utilization, and underground thermal energy storage. Traditionally, determining ETC has relied on either simplified empirical models, which often lack accuracy, or sophisticated laboratory experiments, which are time-consuming and resource intensive. The advent of three-dimensional (3D) imaging technologies has enabled digital characterization of subsurface media, but direct numerical simulations of ETC remain computationally prohibitive. In response to these challenges, we introduce a novel machine learning framework that leverages transfer learning to enhance the prediction of ETC in digital rock samples. Our approach utilizes state-of-the-art convolutional neural networks (CNNs), pre-trained on extensive datasets, and applies them to various porous media samples, including Berea sandstone, Bentheimer sandstone, and Ketton limestone. By employing transfer learning, we demonstrate that our models can achieve high prediction accuracy with significantly reduced training time, computational power, and data requirements. This study highlights the potential of transfer learning to advance the efficiency and accuracy of digital rock analysis, offering a promising tool for the rapid and reliable characterization of subsurface properties.

Authors

Elmorsy M; El-Dakhakhni W; Zhao B

Journal

InterPore Journal, Vol. 2, No. 3, pp. ipj250825–ipj250827

Publisher

The International Society for Porous Media (InterPore)

Publication Date

August 25, 2025

DOI

10.69631/ipj.v2i3nr75

ISSN

3007-410X

Labels

Fields of Research (FoR)

Sustainable Development Goals (SDG)

View published work (Non-McMaster Users)

Contact the Experts team