Oxygen reduction reaction activity of Fe-based dual-atom catalysts with different local configurations via graph neural representation

The performance of proton exchange membrane fuel cells depends heavily on the oxygen reduction reaction (ORR) at the cathode, for which platinum-based catalysts are currently the standard. The high cost and limited availability of platinum have driven the search for alternative catalysts. While FeN4 single-atom catalysts have shown promising potential, their ORR activity needs to be further enhanced. In contrast, dual-atom catalysts (DACs) offer not only higher metal loading but also the ability to break the ORR scaling relations. However, the diverse local structures and tunable coordination environments of DACs create a vast chemical space, making large-scale computational screening challenging. In this study, we developed a graph neural network (GNN)-based framework to predict the ORR activity of Fe-based DACs, effectively addressing the challenges posed by variations in local catalyst structures. Our model, trained on a dataset of 180 catalysts, accurately predicted the Gibbs free energy of ORR intermediates and overpotentials, and identified 32 DACs with superior catalytic activity compared to FeN4 SAC. This approach not only advances the design of high-performance DACs, but also offers a powerful computational tool that can significantly reduce the time and cost of catalyst development, thereby accelerating the commercialization of fuel cell technologies.