Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials

TL;DR

This paper introduces a neural network-based method using Gaussian moments as molecular descriptors to accurately and efficiently model potential energy surfaces for molecules, enabling scalable molecular simulations.

Contribution

It presents a novel, extendable invariant local molecular descriptor based on geometric moments for neural network potentials, improving accuracy and computational efficiency.

Findings

Comparable accuracy to established models in representing chemical and configurational spaces

Efficient GPU implementation of the molecular descriptor

Versatile application in molecular geometry optimization and dynamics

Abstract

Machine learning techniques allow a direct mapping of atomic positions and nuclear charges to the potential energy surface with almost ab-initio accuracy and the computational efficiency of empirical potentials. In this work we propose a machine learning method for constructing high-dimensional potential energy surfaces based on feed-forward neural networks. As input to the neural network we propose an extendable invariant local molecular descriptor constructed from geometric moments. Their formulation via pairwise distance vectors and tensor contractions allows a very efficient implementation on graphical processing units (GPUs). The atomic species is encoded in the molecular descriptor, which allows the restriction to one neural network for the training of all atomic species in the data set. We demonstrate that the accuracy of the developed approach in representing both chemical and configurational spaces is comparable to the one of several established machine learning models. Due to its high accuracy and efficiency, the proposed machine-learned potentials can be used for any further tasks, for example the optimization of molecular geometries, the calculation of rate constants or molecular dynamics.