Perovskite oxides show excellent catalytic performance for thermochemical CO2 splitting, with A/B-site cation substitution further enhancing redox activity. While traditional first-principles methods are computationally expensive, machine learning (ML) provides an efficient approach to perovskite optimization. In this paper, machine learning is employed to investigate and predict the performance of perovskite catalysts in CO2 decomposition reactions. Based on 227 perovskite compositions (A1A2) (B1B2) O3 curated from experimental literature, a total of five ML models are used, including Decision Tree, Bagging, Random Forest, Extra Trees, and Gradient Boosting Regression (GBR). The Random Forest model performed best. After hyperparameter optimization, the Random Forest model achieved an R2 of 0. 910 and an MAE of 41. 528 on an independent test set. SHAP analysis indicated that the thermal reduction temperature (T1) and the B1-site stoichiometric fraction (Cb1) are the most influential features governing the predicted CO yield. A higher CO yield is predicted when Cb1 ranges from 0. 6 to 0. 8, and T1 exceeds 1300 °C. This behavior can be attributed to the enhanced formation of oxygen vacancies at elevated temperatures and the optimized electronic structure induced by appropriate B-site stoichiometry.
Chen et al. (Tue,) studied this question.