ORIGINAL RESEARCH article
Front. Phys.
Sec. Interdisciplinary Physics
This article is part of the Research TopicAI for Physics and Physics for AIView all 8 articles
Machine Learning and Digital Images of Porous Materials: From Rock to Human Brain
Provisionally accepted
Ali Sahimi1
Muhammad Sahimi2*- 1NYU Langone Orthopedic Hospital, New York, United States
- 2University of Southern California, Los Angeles, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Porous media and materials are ubiquitous and are found everywhere. Some of them are what we refer to as rock-like porous media (RLPM), which include soil, concrete, asphalt, and oil and gas reservoirs. In a second group are biological porous materials (BPMs), ranging from skin to organs, such as brain and lungs. Using digital images of BPM for diagnosis and treatment of illnesses has a relatively long history, while their utilization in modeling of various phenomena in RLPM is relatively recent. Due to complexity of such images, as well as the need to extract as much information from them as possible, use of machine-learning (ML) approaches, and in particular neural networks (NNs), has been increasing at a rapid pace. We describe and discuss recent progress in the applications of ML algorithms, particularly NNs, for characterization of such images for the two classes of porous media and materials and show that, while they may seem vastly different, they actually have many similarities, and one must address similar issues when using and analyzing the images. As a result, the application of ML algorithms to both types of porous materials are completely similar, even though the goals may be very different.
Keywords: Biological porous media, Digital Image, machine le arning, Neural Network, rock-like porous material
Received: 23 Dec 2025; Accepted: 26 Dec 2025.
Copyright: © 2025 Sahimi and Sahimi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Muhammad Sahimi
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.