摘要：SummaryTo achieve net-zero emissions, a particular interest has been raised in the electrochemical evolution of H2by using catalysts. Considering the complexity of designing catalyst, we demonstrate a data-driven strategy to develop optimized catalysts for H2evolution. This work starts by collecting data of Pt/carbon catalysts, and applying machine learning to reveal the importance of ranking various features. The algorithms reveal that the Pt content and Pt size have the greatest impact on the catalyst overpotentials. Following the data-driven analysis, a space-confined method is used to fabricate the size-controllable Pt nanoclusters that anchor on nitrogen-doped (N-doped) mesoporous carbon nanosheet network. The obtained catalysts use less platinum and exhibit better catalytic activity than current commercial catalysts in alkaline electrolytes. Moreover, the data formed in this work can be used as feedback to further improve the data-driven model, thereby accelerating the development of high-performance catalysts.Graphical abstractDisplay OmittedHighlights•Built a database of Pt/C catalysts for H2evolution•Provided quantitative guidance for catalyst design by machine learning•Developed a space-confined strategy to control the features of Pt/C composites•Formed a closed-loop from data-driven design to catalyst evaluationChemical reaction; Catalysis; Materials science; Computational method in materials science
