Machine-learning interatomic potentials for materials science

TL;DR

This paper reviews the development of machine-learning interatomic potentials for materials science, comparing them with traditional methods and discussing hybrid approaches to improve transferability and accuracy.

Contribution

It provides a comprehensive comparison of traditional, machine-learning, and hybrid interatomic potentials, highlighting recent advances and future directions in materials science applications.

Findings

ML potentials interpolate between quantum-mechanical reference data

Hybrid models combine ML with physics-based potentials for better transferability

ML potentials offer improved accuracy over traditional potentials in simulations

Abstract

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.