TY  - EJOU
AU  - Liu, Zijian 
AU  - Shi, Yong 
AU  - Li, Chuanqi 
AU  - Zhang, Xiliang 
AU  - Zhou, Jian 
AU  - Khandelwal, Manoj 

TI  - Advanced Machine Learning and Gene Expression Programming Techniques for Predicting CO<sub>2</sub>-Induced Alterations in Coal Strength
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2025
VL  - 143
IS  - 1
SN  - 1526-1506

AB  - Given the growing concern over global warming and the critical role of carbon dioxide (CO<sub>2</sub>) in this phenomenon, the study of CO<sub>2</sub>-induced alterations in coal strength has garnered significant attention due to its implications for carbon sequestration. A large number of experiments have proved that CO<sub>2</sub> interaction time (T), saturation pressure (P) and other parameters have significant effects on coal strength. However, accurate evaluation of CO<sub>2</sub>-induced alterations in coal strength is still a difficult problem, so it is particularly important to establish accurate and efficient prediction models. This study explored the application of advanced machine learning (ML) algorithms and Gene Expression Programming (GEP) techniques to predict CO<sub>2</sub>-induced alterations in coal strength. Six models were developed, including three metaheuristic-optimized XGBoost models (GWO-XGBoost, SSA-XGBoost, PO-XGBoost) and three GEP models (GEP-1, GEP-2, GEP-3). Comprehensive evaluations using multiple metrics revealed that all models demonstrated high predictive accuracy, with the SSA-XGBoost model achieving the best performance (R<sup>2</sup>—Coefficient of determination = 0.99396, RMSE—Root Mean Square Error = 0.62102, MAE—Mean Absolute Error = 0.36164, MAPE—Mean Absolute Percentage Error = 4.8101%, RPD—Residual Predictive Deviation = 13.4741). Model interpretability analyses using SHAP (Shapley Additive exPlanations), ICE (Individual Conditional Expectation), and PDP (Partial Dependence Plot) techniques highlighted the dominant role of fixed carbon content (FC) and significant interactions between FC and CO<sub>2</sub> saturation pressure (P). The results demonstrated that the proposed models effectively address the challenges of CO<sub>2</sub>-induced strength prediction, providing valuable insights for geological storage safety and environmental applications.
KW  - CO<sub>2</sub>-induced coal strength; meta-heuristic optimization algorithms; XGBoost; gene expression programming; model interpretability

DO  - 10.32604/cmes.2025.062426