Machine learning hydrogen adsorption on nanoclusters through structural descriptors

Marc O J Jäger,Adam S Foster,Filippo Federici Canova,Eiaki V Morooka,Lauri Himanen

doi:10.1038/s41524-018-0096-5

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.

Highlights

Due to their remarkable properties, nanoclusters have gained attention in heterogeneous catalysis.[1,2,3] Nanoclusters differ from bulk metal behaviour, and their catalytic properties are sensitive to changes in size and morphology.[4,5,6,7] For example, gold clusters with a diameter of a few nanometres exhibit non-metallic properties due to quantum size effects.[8]
The fact that ManyBody Tensor Representation (MBTR) and Smooth Overlap of Atomic Positions (SOAP) surface of a single cluster can be inferred from a data set of combined did not improve the overall accuracy, strongly suggests that the relevant information is contained around the adsorption site
We analysed the performance of state-of-the-art atomic structural descriptors (SOAP, MBTR and Atom-Centered Symmetry Functions (ACSF)) when used to predict the hydrogen adsorption energy on the surface of nanoclusters

Summary

INTRODUCTION

Due to their remarkable properties, nanoclusters have gained attention in heterogeneous catalysis.[1,2,3] Nanoclusters differ from bulk metal behaviour, and their catalytic properties are sensitive to changes in size and morphology.[4,5,6,7] For example, gold clusters with a diameter of a few nanometres exhibit non-metallic properties due to quantum size effects.[8]. The data sets MoS2(single) and Au40Cu40(single) contained 10,000 DFT-based ΔEH single-point calculations of hydrogen positioned on the surface of the same cluster. In this example only, we included the results for the Coulomb Matrix accuracy at all training set sizes. The fact that MBTR and SOAP surface of a single cluster can be inferred from a data set of combined did not improve the overall accuracy, strongly suggests that the relevant information is contained around the adsorption site. It can be noted that the parity plot featured two clusters which indicated that only part of the local environments of Au40Cu40 were represented in the training set

DISCUSSION

Findings

METHODS