Machine Learning-Assisted Screening of Stepped Alloy Surfaces for C1 Catalysis

Efficient reactivity assessment for stepped alloy surfaces presents a major challenge in designing effective catalysts for industrial catalyticconversion of single-carbon (C1) molecules. In this work, we propose a machinelearning (ML)-assisted approach to screen active and stable binary alloys forvarious C1catalytic processes. Leveraging only non-ab initio, simple bulkmaterial properties as input features, the ML models exhibit impressive accuracyfor predicting site-specific adsorption energies of atomic carbon and oxygen,which enable not only fast navigation through abundant material space but alsoextraction of explicable physical insights. The effectiveness of the ML models isfurther validated by applying their predictions to catalyst screening for commonreactions in C1catalysis, as well as a detailed kinetic study on one examplecandidate, Cu3Pd. This data-driven approach with fully interpretable physicalfeatures demonstrates the possibility of unearthing underlying catalyst design principles from apparent data and paves the road for the discovery of desirable alloy catalysts