Active learning of linearly parametrized interatomic potentials

TL;DR

This paper presents an active learning method for efficiently fitting machine learning interatomic potentials using the D-optimality criterion, enabling reliable and accurate atomistic simulations without extrapolation.

Contribution

It introduces a novel active learning approach based on D-optimality for fitting interatomic potentials, improving efficiency and reliability in atomistic simulations.

Findings

High efficiency in training potentials on the fly

Ensures no extrapolation during simulations

Maintains accuracy in atomistic modeling

Abstract

This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the D-optimality criterion for selecting atomic configurations on which the potential is fitted. It is shown that the proposed active learning approach is highly efficient in training potentials on the fly, ensuring that no extrapolation is attempted and leading to a completely reliable atomistic simulation without any significant decrease in accuracy. We apply our approach to molecular dynamics and structure relaxation, and we argue that it can be applied, in principle, to any other type of atomistic simulation. The software, test cases, and examples of usage are published at http://gitlab.skoltech.ru/shapeev/mlip/.