Porous media and materials are ubiquitous and found everywhere. Some of them are referred to as rock-like porous media (RLPM), which include soil, concrete, asphalt, and oil and gas reservoirs. A second group consists of biological porous materials (BPMs), ranging from skin to organs such as the brain and lungs. The use of digital images of BPMs for the diagnosis and treatment of illnesses has a relatively long history, whereas their utilization in modeling various phenomena in RLPM is relatively recent. Due to the complexity of such images, along with the need to extract as much information from them as possible, the use of machine-learning (ML) approaches—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 the 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 similar issues must be addressed when using and analyzing the images. As a result, the application of ML algorithms to both types of porous materials is largely similar, even though the goals may be very different.
Sahimi et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: