Comparative Analysis and Optimization of Machine Learning Algorithms for Prediction of Adsorption Energy of Methane Related Species on Cu-based Alloys

Machine Learning (ML)has helped to accelerate research and innovation in multifarious domains. In this study, ML models have been used to predict adsorption energies of Methane Related Species on Cu-based Alloy. Comparative study of different ML algorithms integrated with GA were performed to improve the ML model’s architecture and parameters selection. The results proposed that Categorical boosting (Catboost) model with RMSE = 0.0977, CC = 96.5 % outperformed all other models and effectively predicts adsorption energies. The partial dependence plots (PDPs) analysis shows the potential effects of each influencing parameter impact on the prediction of the respective adsorption energies and as well as shows that how these factors will interact during oxidative coupling of methane (OCM). In addition, SHAP analysis was employed to further interpret the contribution of individual descriptors to adsorption energies, allowing for the identification of key factors such as electronegativity, atomic radius, ionization energy, and surface energy. These insights highlight how dopant selection alters catalytic performance, demonstrating the ability of ML not only to provide accurate predictions but also to generate design-relevant knowledge. Overall, this approach provides a reliable and efficient methodology for reducing experimental screening and accelerating the discovery of promising Cu-based alloy catalysts for methane conversion.

Haseeb Ahmad, Iftikhar Ahmad, Qazi Ahmed and Meshal Shutaywi