Machine learning potentials for multicomponent systems: The Ti-Al binary system

TL;DR

This paper extends polynomial invariant-based machine learning potentials to multicomponent systems, demonstrating high accuracy and efficiency in modeling the Ti-Al binary system's properties.

Contribution

It introduces a systematic formulation of polynomial invariants for multicomponent systems and applies it to develop accurate MLPs for Ti-Al, outperforming previous models.

Findings

MLPs accurately predict formation energy and elastic constants.

The developed MLPs show high computational efficiency.

The scheme is applicable to other multicomponent systems.

Abstract

Machine learning potentials (MLPs) are becoming powerful tools for performing accurate atomistic simulations and crystal structure optimizations. An approach to developing MLPs employs a systematic set of polynomial invariants including high-order ones to represent the neighboring atomic density. In this study, a formulation of the polynomial invariants is extended to the case of multicomponent systems. The extended formulation is more complex than the formulation for elemental systems. This study also shows its application to Ti-Al binary system. As a result, an MLP with the lowest error and MLPs with high computational cost performance are selected from the many MLPs developed systematically. The predictive powers of the developed MLPs for many properties, such as the formation energy, elastic constants, thermodynamic properties, and mechanical properties, are examined. The MLPs exhibit high predictive power for the properties in a wide variety of ordered structures. The present scheme should be systematically applicable to other multicomponent systems.