Construction of Machine Learning Potentials toward the Exploration of Alloy Cluster Catalysts

Abstract

High entropy alloys (HEAs) are expected to show excellent performance in various fields, such as catalysts and high-temperature structural materials, but the huge number of configurations makes it difficult to find the optimal compositions for HEAs. In this study, machine learning potentials were developed to accurately predict the total and H/CO adsorption energies of multi-element slab models and cluster models of various sizes and shapes, based on density functional theory calculations.