Leveraging machine learning in porous media†
Abstract
The emergence of artificial intelligence (AI) and, more particularly, machine learning (ML), has had a significant impact on engineering and the fundamental sciences, resulting in advances in various fields. The use of ML has significantly enhanced data processing and analysis, eliciting the development of new and improved technologies. Specifically, ML is projected to play an increasingly significant role in helping researchers better understand and predict the behavior of porous media. Furthermore, ML models will be able to make use of sizable datasets, such as subsurface data and experiments, to produce accurate predictions and simulations of porous media systems. This capability could help optimize the design of porous materials for specific applications and improve the effectiveness of industrial processes. To this end, this review paper attempts to provide an overview of the present status quo in this context, i.e., the interface of ML and porous media in six different applications, namely, heat exchanger and storage, energy storage and combustion, electrochemical devices, hydrocarbon reservoirs, carbon capture and sequestration, and groundwater, stressing the advances made in the application of ML to porous media and offering insights into the challenges and opportunities for future research. Each section also entails a supplementary database of the literature as a spreadsheet, which includes the details of ML models, datasets, key findings, etc., and mentions relevant available online datasets that can be used to train ML models. Future research trends include employing hybrid models by combining ML models with physics-based models of porous media to improve predictions concerning accuracy and interpretability.
- This article is part of the themed collections: Journal of Materials Chemistry A Recent Review Articles, Today's Simulations: Pioneering the Experiments of Tomorrow and Machine learning and artificial neural networks: Celebrating the 2024 Nobel Prize in Physics