Abstract
•Adsorption energy, adsorption height, and buckling of the surface was predicted utilizing machine learning, specifically the hierarchically interacting particle neural network (HIP-NN), for H, N, and O on bimetallic transition metal surfaces.•These adsorption properties were predicted employing clean surface geometries.•Including periodic boundary conditions into the machine learning algorithm improved results.•Buckling of surface, as predicted by a machine learning mode, was successfully employed to prune the training dataset.
We present a machine learning study utilizing the Hierarchically Interacting Particle Neural Network to predict the adsorption properties of atomic H, N, and O on various single metal and bimetallic single crystal FCC surfaces. Our trained HIP-NN models directly predict, from atomic species and coordinates of the clean surface, and initial adsorption site, adsorption energies with a MAE of 0.08 eV to 0.16 eV, adsorption heights with a MAE of 0.08 Å to 0.09 Å, and a buckling of the first layer of the substrate with a MAE of 0.07 Å to 0.12 Å, illustrating that a neural network can calculate the physical properties of a surface/adsorbate system along with adsorption energy. Our MAEs for adsorption energy also compare favorably with MAEs presented by other works predicting the adsorption energies of H, N, and O. We also demonstrate that while HIP-NN can predict on these systems without explicit periodic boundary conditions, the inclusion of explicit periodic boundary conditions drastically improves the results. Our results also reveal that the buckling of the first layer of the substrate can be utilized to prune datasets, removing unstable surfaces.
[Display omitted]