Systematic development of polynomial machine learning potentials for metallic and alloy systems

TL;DR

This paper introduces a systematic framework for developing polynomial machine learning potentials tailored for metallic and alloy systems, enhancing accuracy and efficiency in large-scale atomistic simulations.

Contribution

The paper presents a novel polynomial-based machine learning potential framework and provides a comprehensive set of potentials for various elemental and binary alloy systems.

Findings

Polynomial MLPs achieve high accuracy in predicting material properties.

The developed potentials are computationally efficient for large-scale simulations.

A publicly accessible repository of polynomial MLPs is provided.

Abstract

Machine learning potentials (MLPs) developed from extensive datasets constructed from density functional theory (DFT) calculations have become increasingly appealing for many researchers. This paper presents a framework of polynomial-based MLPs, called polynomial MLPs. The systematic development of accurate and computationally efficient polynomial MLPs for many elemental and binary alloy systems and their predictive powers for various properties are also demonstrated. Consequently, many polynomial MLPs are available in a repository website. The repository will help many scientists perform accurate and efficient large-scale atomistic simulations and crystal structure searches.