Machine-Learning-Accelerated Screening of Double-Atom/Cluster Electrocatalysts for the Oxygen Reduction Reaction

Carbon-based double-atom/nanocluster electrocatalysts usually demonstrate high reactivity toward the oxygen reduction reaction (ORR). However, experimental screening of optimized double-atom- and nanocluster-based ORR catalysts is often expensive and time-consuming. In this work, density functional theory (DFT) calculation is combined with the machine learning (ML) method to accelerate the screening and prediction of high-performance double-atom and nanocluster-based ORR catalysts. A database consisting of 330 ORR intermediate adsorption energies on 110 catalyst models is constructed by DFT calculations, which allows a quick ML screening of 1200 candidate ORR catalysts. The reliability of the ML model is evaluated by the R-square score (R2) and mean absolute error methods. A set of 25 potential active double-atom and nanocluster-based ORR catalysts are selected. On the basis of this ML screening, the binding energy, Bader charge transfer, and ORR reaction kinetics of the ML-predicted catalysts are considered further. The carbon-based Fe–Ce double-atom catalyst is predicted to be the best-performing ORR catalyst in the sample space. The adsorption energy-based DFT–ML framework provides an attractive approach to accelerate the screening of efficient double-atom- or cluster-based ORR electrocatalysts.