Exploring a potential energy surface by machine learning for characterizing atomic transport

TL;DR

This paper introduces a machine learning approach using Gaussian processes to efficiently evaluate potential energy surfaces and identify dominant points for atomic transport, improving over traditional methods.

Contribution

The novel method leverages probabilistic modeling to select key points on the PES, enhancing robustness and efficiency in atomic transport analysis.

Findings

Demonstrated robustness on multiple proton diffusion models

Compared favorably with the nudge elastic band method

Achieved efficient sampling of potential energy surfaces

Abstract

We propose a machine-learning method for evaluating the potential barrier governing atomic transport based on the preferential selection of dominant points for the atomic transport. The proposed method generates numerous random samples of the entire potential energy surface (PES) from a probabilistic Gaussian process model of the PES, which enables defining the likelihood of the dominant points. The robustness and efficiency of the method are demonstrated on a dozen model cases for proton diffusion in oxides, in comparison with a conventional nudge elastic band method.