The development of inexpensive metal-nitrogen-carbon (M-N-C) catalysts for electrochemical CO₂ reduction reaction (CO₂RR) on an industrial scale has come to a standstill. Although the number of related studies and reviews has grown fast, the complexity of the M-N-C composite has limited researchers to focus on only a few variables and carry out sluggish trial-and-error optimizations in their studies. As a result, the conclusions are drawn only by artificial analysis based on a few orthogonal experimental results. To obtain more general design strategies, we have innovatively introduced machine learning (ML) into this field to address this bottleneck. A standard workflow that comprehensively utilizes different ML algorithms and black-box interpretation methods is proposed for this purpose. Besides predicting CO₂RR performance metrics for M-N-C catalysts, such as maximum faradaic efficiency with great accuracy, the ML models have also indicated simple and clear design strategies that would guide future exploration from a data science perspective. Besides, we have also demonstrated the potential of the models in guiding the development of new material systems. We thereby believe that the new research paradigm proposed may accelerate the development of this field soon.

Single-atom catalysts (SACs) have become one of the most considered research directions today, owing to their maximum atom utilization and simple structures, to investigate structure-activity relationships. In the field of non-precious-metal electrocatalysts, atomically dispersed Fe-N₄ active sites have been proven to possess the best oxygen reduction activity. Yet the majority of preparation methods remains complex and costly with unsatisfying controllability. Herein, we have designed a surface-grafting strategy to directly synthesize an atomically dispersed Fe-N₄/C electrocatalyst applied to the oxygen reduction reaction (ORR). Through an esterification process in organic solution, metal-containing precursors were anchored on the surface of carbon substrates. The covalent bonding effect could suppress the formation of aggregated particles during heat treatment. Melamine was further introduced as both a cost-effective nitrogen resource and blocking agent retarding the migration of metal atoms. The optimized catalyst has proven to have abundant atomically dispersed Fe-N₄ active sites with enhanced ORR catalytic performance in acid condition. This method has provided new feasible ideas for the synthesis of SACs.