Representing molecule-surface interactions with symmetry-adapted neural networks

TL;DR

This paper introduces a symmetry-adapted neural network approach for accurately modeling molecule-surface interactions, specifically applied to oxygen molecules on Al(111), improving the representation of the potential-energy surface.

Contribution

The paper develops a new symmetry function-based neural network that exactly incorporates surface symmetry into PES modeling, enhancing accuracy and efficiency.

Findings

Achieved high accuracy in modeling oxygen-Al(111) interactions.

Demonstrated the effectiveness of symmetry-adapted NNs for complex PES.

Improved interpolation of PES compared to previous methods.

Abstract

The accurate description of molecule-surface interactions requires a detailed knowledge of the underlying potential-energy surface (PES). Recently, neural networks (NNs) have been shown to be an efficient technique to accurately interpolate the PES information provided for a set of molecular configurations, e.g. by first-principles calculations. Here, we further develop this approach by building the NN on a new type of symmetry functions, which allows to take the symmetry of the surface exactly into account. The accuracy and efficiency of such symmetry-adapted NNs is illustrated by the application to a six-dimensional PES describing the interaction of oxygen molecules with the Al(111) surface.