Metal-nitrogen-carbon (M-N-C) single-atom catalysts (SACs) have emerged as a potential substitute for the costly platinum-group catalysts in oxygen reduction reaction (ORR). However, several critical aspects of M-N-C SACs in ORR remain poorly understood, including their pH-dependent activity, selectivity for 2- or 4-electron transfer pathways, and the identification of the rate-determining steps. Herein, by analyzing >100 M-N-C structures and >2000 sets of energetics, we unveil a pH-dependent evolution in ORR activity volcanos─from a single peak in alkaline media to a double peak in acids. We found that this pH-dependent behavior in M-N-C catalysts fundamentally stems from their moderate dipole moments and polarizability for O* and HOO* adsorbates, as well as unique scaling relations among ORR adsorbates. To validate our theoretical discovery, we synthesized a series of molecular M-N-C catalysts, each characterized by well-defined atomic coordination environments. Impressively, the experiments matched our theoretical predictions on kinetic current, Tafel slope, and turnover frequency in both acidic and alkaline environments. These new insights also refine the famous Sabatier principle by emphasizing the need to avoid an "acid trap" while designing M-N-C catalysts for ORR or any other pH-dependent electrochemical applications.

Machine learning has proven to be a powerful technique during the past decades. Artificial neural network (ANN), as one of the most popular machine learning algorithms, has been widely applied to various areas. However, their applications for catalysis were not well-studied until recent decades. In this review, we aim to summarize the applications of ANNs for catalysis research reported in the literature. We show how this powerful technique helps people address the highly complicated problems and accelerate the progress of the catalysis community. From the perspectives of both experiment and theory, this review shows how ANNs can be effectively applied for catalysis prediction, the design of new catalysts, and the understanding of catalytic structures.