Bayesian optimization of single-atom alloys and other bimetallics: efficient screening for alkane transformations, CO<sub>2</sub> reduction, and hydrogen evolution
Gbolade O. Kayode, Avery F. Hill, M. M. Montemore
Abstract
We leveraged Bayesian optimization (BO) to search for potential high-performing catalysts. Our BO workflow can be initialized with as few as 2 to 8 data points, and often identifies the optimal single-atom alloy surface in just a few iterations.
Topics & Concepts
WorkflowReduction (mathematics)Bayesian optimizationBayesian probabilityHydrogenCatalysisAlkaneAtom (system on chip)Hydrogen atomComputer scienceChemistryMaterials scienceMathematicsParallel computingArtificial intelligenceOrganic chemistryDatabaseAlkylGeometryMachine Learning in Materials ScienceCatalytic Processes in Materials ScienceCatalysis and Oxidation Reactions