Application of Machine Learning to Discover New Intermetallic Catalysts for the Hydrogen Evolution and the Oxygen Reduction Reactions

The hydrogen economy strongly depends on two critical reactions for the production of hydrogen and the generation of green energy, namely the hydrogen evolution reaction (HER) and the oxygen reduction reaction (ORR). Pt is the best catalyst in both cases (HER and ORR) and allows high reaction rates to be reached in an acidic environment with very small overpotentials. Nevertheless, Pt cost and scarcity limit the widespread application of this strategy to use hydrogen as a clean energy source. Thus, there is a significant interest in discovering cheaper and more abundant catalysts to replace Pt.<br/><br/>In this investigation, the adsorption energies for hydrogen, oxygen, and hydroxyl were calculated by means of density functional theory on the lowest energy surface of 24 pure metals and 332 binary intermetallic compounds with stoichiometries AB, A2B, and A3B taking into account the effect of biaxial elastic strains. This information was used to train two random forest regression models, one for the hydrogen adsorption and another for the oxygen and hydroxyl adsorption, based on 9 descriptors that characterized the geometrical and chemical features of the adsorption site as well as the applied strain. All the descriptors for each compound in the models could be obtained from physico-chemical databases. The random forest models were used to predict the adsorption energy for hydrogen, oxygen, and hydroxyl of binary intermetallic compounds with stoichiometries AB, A2B, and A3B made of metallic elements, excluding those that were environmentally hazardous, radioactive, or toxic. This information was used to search for potential good catalysts for the HER and ORR from the criteria that their adsorption energy for H and O/OH, respectively, should be close to that of Pt. This investigation shows that the suitably trained machine learning models can predict adsorption energies with an accuracy not far away from density functional theory calculations with minimum computational cost from descriptors that are readily available in physico-chemical databases for any compound. Moreover, the strategy presented in this paper can be easily extended to other compounds and catalytic reactions, and is expected to foster the use of machine learning methods in catalysis.<br/><br/><b>References</b><br/>C. Martínez-Alonso, V. Vassilev-Galindo, B. M. Comer, F. Abild-Pedersen, K. T. Winther, J. LLorca. Application of machine learning to discover new intermetallic catalysts for the hydrogen evolution and the oxygen reduction reactions, Catalysis Science and Technology (2024) doi: 10.1039/D4CY00491D