Ensemble-Based Explainable Machine Learning Framework to Predict CO2 Adsorption Capacity of Coal
Energy & Fuels · 30.07.2026 · 40 (30) · 16327-16343
DOI: 10.1021/acs.energyfuels.6c01197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energy & Fuels, online erschienen am 22.07.2026. Verfasst von Madhurima Mazumder und 6 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Gefördert von: Indian Institute of Technology (Indian School of Mines), Dhanbad.
Abstract (Originalsprache)
Integration of carbon capture, utilization, and storage (CCUS) and CO2-enhanced CBM recovery (ECBM) serves as a key strategy for mitigating global warming while achieving global net-zero targets. However, precisely predicting gas sorption profiles remains challenging as traditional tests and empirical methods are expensive, time-consuming, and limited by experimental constraints.This study employs ensemble-based ML algorithms, along with explainable AI, to accurately predict the CO2 adsorption capacity in coal samples across diverse ranks, compositions, and reservoir conditions. The robustness and reliability of the models were validated using 5-fold cross-validation and grid-based hyperparameter tuning. On the basis of the results, the ensemble learning methods were the most competent predictors, with XGBoost performing best (R2 = 0.9769, RMSE = 0.064, MAE = 0.033). The developed model could closely describe Langmuir-type adsorption behavior, with good accuracy compared to experimental isotherms. Shapley’s explanations reveal that reservoir pressure and volatile matter exert dominant control on CO2 adsorption, consistent with adsorption thermodynamics. This rapid, data-driven approach serves as a cost-effective screening-level complement to laboratory adsorption tests, enabling the preliminary evaluation of coal seams for CO2-enhanced coalbed methane (ECBM) projects prior to detailed site characterization. By optimizing methane recovery while securely sequestering CO2, the work advances cleaner coal utilization and contributes to sustainable development and clean energy transitions.
Förderung
- Indian Institute of Technology (Indian School of Mines), Dhanbad
Zitieren
APA
Mazumder, M., Kumar, A., Tripathy, A., Sahoo, A., Khandelwal, M., Singh, T. N., & Liu, S. (2026). Ensemble-Based Explainable Machine Learning Framework to Predict CO2 Adsorption Capacity of Coal. Energy & Fuels, 40(30), 16327-16343. https://doi.org/10.1021/acs.energyfuels.6c01197
Vancouver
Mazumder M, Kumar A, Tripathy A, Sahoo A, Khandelwal M, Singh TN, et al. Ensemble-Based Explainable Machine Learning Framework to Predict CO2 Adsorption Capacity of Coal. Energy & Fuels. 2026;40(30):16327-16343. doi:10.1021/acs.energyfuels.6c01197
BibTeX
@article{Mazumder2026,
author = {Mazumder, Madhurima and Kumar, Ashutosh and Tripathy, Ashutosh and Sahoo, Arijit and Khandelwal, Manoj and Singh, T. N. and Liu, Shiqi},
title = {Ensemble-Based Explainable Machine Learning Framework to Predict CO2 Adsorption Capacity of Coal},
journal = {Energy & Fuels},
year = {2026},
volume = {40},
number = {30},
pages = {16327--16343},
doi = {10.1021/acs.energyfuels.6c01197}
}
EUVIMED