Year: 2025
Type: article
Abstract: Intelligent use of fossil energy has become a pivotal topic in contemporary energy development. The quantification of coal seam methane adsorption capacity is crucial for assessing coalbed methane (CBM) reserves and methane-related greenhouse effects. Currently, experimental procedure for methane adsorption isotherm measurement remains challenging because of its extended equilibrium durations and procedural complexity. Moreover, the conventional adsorption model is constrained by restrictive assumptions and has limited application with alternative adsorption conditions. Given their effective problem-solving capabilities, artificial intelligence algorithms are increasingly adopted by researchers. This work systematically reviews of recent advancements in intelligent algorithms used for predicting gas adsorption characteristics, e.g. artificial neural network, deep neural network, recurrent neural network, support vector machine, etc., focusing on three key areas: experimental measurement of adsorption isotherms, development of mathematical models for adsorption evaluation, and identification of dominant factors influencing coal adsorption. We further critically compare algorithmic strengths/limitations and identify future research directions. These findings enable improved CBM reserve assessment and inform greenhouse gas emission strategies.
DOI: 10.1093/jge/gxaf086
Authors: Wei Zhao, Yujia Wan, Dan Zhao, Chenmin Zhang, Kai Wang, Jingzhe Yu
Language: English
Subfield: Ocean Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,550
OpenAlex ID: W4411958619