Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method

TL;DR

This paper introduces a modified physically-informed neural network (PINN) method to develop a highly accurate and transferable interatomic potential for aluminum, enabling large-scale atomistic simulations with improved efficiency and broad applicability.

Contribution

A modified PINN approach that accelerates training and enhances transferability of interatomic potentials, demonstrated by developing a highly accurate aluminum potential.

Findings

Reproduces first-principles energies within 2.6 meV per atom

Accurately predicts diverse physical properties of aluminum

Improves computational efficiency of PINN potentials

Abstract

Abstract Interatomic potentials constitute the key component of large-scale atomistic simulations of materials. The recently proposed physically-informed neural network (PINN) method combines a high-dimensional regression implemented by an artificial neural network with a physics-based bond-order interatomic potential applicable to both metals and nonmetals. In this paper, we present a modified version of the PINN method that accelerates the potential training process and further improves the transferability of PINN potentials to unknown atomic environments. As an application, a modified PINN potential for Al has been developed by training on a large database of electronic structure calculations. The potential reproduces the reference first-principles energies within 2.6 meV per atom and accurately predicts a wide spectrum of physical properties of Al. Such properties include, but are not limited to, lattice dynamics, thermal expansion, energies of point and extended defects, the melting temperature, the structure and dynamic properties of liquid Al, the surface tensions of the liquid surface and the solid-liquid interface, and the nucleation and growth of a grain boundary crack. Computational efficiency of PINN potentials is also discussed.