Machine learning hydrogen adsorption on nanoclusters through structural descriptors

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.

From DFT to machine learning: recent approaches to materials science–a review

“…A recent review of applications of high-dimensional neural neural network potentials [430] summarized the notable number of molecular and materials systems studied, which ranges from simple semiconductors such as silicon [233,431,432] and ZnO [433], to more complex systems such as water and metallic clusters [434], molecules [435][436][437], surfaces [438,439], and liquid/solid interfaces [414,440]. Force fields for nanoclusters have been developed with 2-, 3-, and many-body descriptors [441], and the hydrogen adsorption on nanoclusters was described with structural descriptors such as SOAP [442].…”

Band Gap Prediction for Large Organic Crystal Structures with Machine Learning

“…Many different descriptors have been introduced in the literature, such as the Coulomb matrix [24], Bag-of-Bonds [25], Sine Matrix [26] and MBTR [27]. An alternative strategy is to skip the intermediate step of fixed-size descriptors, which often involve ad-hoc decisions, and directly define the kernel between two structures as in the Smooth Overlap of Atomic Positions (SOAP) kernel, which has shown superior performance on a variety of problems [21,60].…”

Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials

“…In this paper we have presented a modified form of the many-body atomic descriptor known as SOAP [6] and a series of mathematical and computational recipes for its efficient evaluation. This type of descriptor is routinely used as essential input for novel ML-based Gaussian approximation potentials [3,8] and other ML models used to understand and predict the properties of solids and molecules [16,[19][20][21]. While the primary objective of this work was to improve the computational efficiency of SOAP calculations, the new formulation also allows for a significant boost in accuracy.…”