Machine-learning interatomic potentials for materials science

Large-scale atomistic computer simulations of materials rely on interatomic potentials providing computationally efficient predictions of energy and Newtonian forces. Traditional potentials have served in this capacity for over three decades. Recently, a new class of potentials has emerged, which is based on a radically different philosophy. The new potentials are constructed using machine-learning (ML) methods and a massive reference database generated by quantum-mechanical calculations. While the traditional potentials are derived from physical insights into the nature of chemical bonding, the ML potentials utilize a high-dimensional mathematical regression to interpolate between the reference energies. We review the current status of the interatomic potential field, comparing the strengths and weaknesses of the traditional and ML potentials. A third class of potentials is introduced, in which an ML model is coupled with a physics-based potential to improve the transferability to unknown atomic environments. The discussion is focused on potentials intended for materials science applications. Possible future directions in this field are outlined. (c) 2021 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Automated summary

This article reviews the current status of interatomic potentials in the field of materials science, comparing the strengths and weaknesses of traditional potentials and machine learning potentials. It introduces a new class of potentials that combine physics-based potential with machine learning models to enhance transferability to unknown atomic environments. Potential future directions in this field are outlined.