Low-cost, efficient catalyst high-throughput screening is crucial for future renewable energy technology. Interpretable machine learning is a powerful method for accelerating catalyst design by extracting physical meaning but faces huge challenges. This paper describes an interpretable descriptor model to unify activity and selectivity prediction for multiple electrocatalytic reactions (i.e., O2/CO2/N2 reduction and O2 evolution reactions), utilizing only easily accessible intrinsic properties.
Read more in our recent publication at Nature Commun.:
Machine learning-assisted dual-atom sites design with interpretable descriptors unifying electrocatalytic reactions