Density Functional Theory-Machine Learning Characterization of the Adsorption Energy of Oxygen Intermediates on High-Entropy Alloys Made of Earth-Abundant Metals

High-entropyalloys (HEAs) have emerged as promising electrocatalystsdue to their high tunability. Among HEAs, those made of earth-abundantmetals have shown high stability and corrosion resistance, makingthem attractive as low-cost alternatives to noble metal electrocatalysts.However, the catalytic characteristics of these HEAs remain largelyunexplored, mainly due to computational challenges posed by the vastnumber of local binding environments on their surfaces. Here, we combinedensity functional theory calculations and machine learning (ML) regressionmodels to reconstruct the distribution of adsorption energies of O*and HO* on HEAs containing CoFeNi-X, where X represents Mo, Mn, orCr. Our ML models predict the adsorption energies on different HEAbinding sites with reasonable accuracy despite the modest size ofthe training data sets. We find that although hollow binding sitesare preferred for both O* and HO*, the elemental composition of theHEAs significantly influences the preferred binding site types, withMo and Cr promoting bridge and on-top binding sites, particularlyfor HO*. We also find that while the scaling relationship betweenaverage adsorption energies of O* and HO* holds for equimolar HEAs,local disruptions to the scaling relationship can occur induced byspecific stoichiometric changes. Our study also provides insight intothe contributions of different chemical environments to the adsorptionenergy distribution, providing valuable guidance for the future designof HEA electrocatalysts.