Machine learning hydrogen adsorption on nanoclusters through structural descriptors

TLDR

Catalytic activity of the hydrogen evolution reaction on nanoclusters depends on diverse adsorption site structures. The study uses machine learning to reduce the cost of modelling hydrogen adsorption sites on nanoclusters by evaluating structural descriptors. The authors applied kernel ridge regression to potential energy scans of hydrogen on molybdenum disulphide and copper–gold nanoclusters, comparing structural descriptors such as Smooth Overlap of Atomic Positions, Many-Body Tensor Representation, and Atom-Centered Symmetry Functions. Training on multiple nanoclusters simultaneously lowered the mean absolute error, and the local descriptor Smooth Overlap of Atomic Positions alone explained adsorption energy, showing that merging data across clusters significantly reduces the effort needed to fit potential energy surfaces.

Abstract

Abstract Catalytic activity of the hydrogen evolution reaction on nanoclusters depends on diverse adsorption site structures. Machine learning reduces the cost for modelling those sites with the aid of descriptors. We analysed the performance of state-of-the-art structural descriptors Smooth Overlap of Atomic Positions, Many-Body Tensor Representation and Atom-Centered Symmetry Functions while predicting the hydrogen adsorption (free) energy on the surface of nanoclusters. The 2D-material molybdenum disulphide and the alloy copper–gold functioned as test systems. Potential energy scans of hydrogen on the cluster surfaces were conducted to compare the accuracy of the descriptors in kernel ridge regression. By having recourse to data sets of 91 molybdenum disulphide clusters and 24 copper–gold clusters, we found that the mean absolute error could be reduced by machine learning on different clusters simultaneously rather than separately. The adsorption energy was explained by the local descriptor Smooth Overlap of Atomic Positions, combining it with the global descriptor Many-Body Tensor Representation did not improve the overall accuracy. We concluded that fitting of potential energy surfaces could be reduced significantly by merging data from different nanoclusters.