The group’s machine learning work throughout first-principle models is published in Physical Chemistry Chemical Physics. We collaborated with Prof. Back group (Sogang Univ.) and Prof. Ulissi group (Carnegie Mellon Univ.).
We contributed to nonlinear manifold learning to identify the cluster of similar heterogeneous catalysts. Also, we highlight that the Pareto-optimal filtering can efficiently reduce candidates that can strongly advantage to multiple criteria such as stability, CO-tolerance, cost-effectiveness, and activity.
Various databases of density functional theory (DFT) calculations for materials and adsorption properties are currently available. Using the Materials Project and GASpy databases of material stability and binding energies (H* and CO*), respectively, we evaluate multiple aspects of catalysts to discover active, stable, CO-tolerant, and cost-effective hydrogen evolution and oxidation catalysts. Finally, we suggest a few candidate materials for future experimental validations. We highlight that the stability analysis is easily obtainable but provides invaluable information to assess thermodynamic and electrochemical stability, bridging the gap between simulations and experiments. Furthermore, it reduces the number of expensive DFT calculations required to predict catalytic activities of surfaces by filtering out unstable materials.