Machine learning screening of high-performance single-atom electrocatalysts for two-electron oxygen reduction reaction.

Electrocatalysis has emerged as one of the most promising alternatives to conventional anthraquinone for preparing hydrogen peroxide (HO) with high energy consumption and pollution because of its simplicity, convenience, and environmental friendliness. However, the oxygen reduction reaction (ORR) generating HOviathe2e path is acompetitive path for 4eORR to generate HO. Therefore, it is crucial to identify an electrocatalyst with high selectivity and activity of 2eORR. Here, we established five machine learning (ML) models based on the adsorption free energy of O* (△G (O*)) of 149 single-atom catalysts (SACs) collected and the limiting potential (U) of 31 SACs calculated using density functional theory (DFT) from the literature. We then obtained descriptors that could accurately describe SACs. Furthermore, 690 unknown SACs' 2eORR catalytic performance was well predicted. Four 2eORR materials with high selectivity and activity were screened: Zn@Pc-NC, Au@Pd-N, Au@Pd-NC, and Au@Py-NC. We verified the U of these SACs through DFT calculation, which was higher than the standard value, proving the ML model's validity. The ML-based method to predict the material properties with highly selective and active electrocatalysts provides an efficient, rapid, and low-cost method for discovering and designing more valuable SACs catalysts.