Fitting to magnetic forces improves the reliability of magnetic Moment Tensor Potentials

TL;DR

This paper introduces a machine-learning approach for fitting magnetic interatomic potentials by incorporating magnetic forces, leading to improved accuracy and reliability in modeling magnetic materials like bcc Fe-Al.

Contribution

The authors develop a novel method for fitting magnetic Moment Tensor Potentials using magnetic forces from DFT, enhancing structure relaxation reliability and finite-temperature predictions.

Findings

Accurate DFT-like formation energies and lattice parameters

Successful finite-temperature lattice expansion modeling

Increased reliability in structure relaxation processes

Abstract

We developed a method for fitting machine-learning interatomic potentials with magnetic degrees of freedom, namely, magnetic Moment Tensor Potentials (mMTP). The main feature of our method consists in fitting mMTP to magnetic forces (negative derivatives of energies with respect to magnetic moments) as obtained spin-polarized density functional theory calculations. We test our method on the bcc Fe-Al system with different compositions. Specifically, we calculate formation energies, equilibrium lattice parameter, and total cell magnetization. Our findings demonstrate an accurate correspondence between the values calculated with mMTP and those obtained by DFT at zero temperature. Additionally, using molecular dynamics, we estimate the finite-temperature lattice parameter and capture the cell expansion as was previously revealed in experiment. Furthermore, we demonstrate that fitting to magnetic forces increases the reliability of structure relaxation (or, equilibration), in the sense of ensuring that every relaxation run ends up with a successfully relaxed structure (the failure may otherwise be caused by falsely driving a configuration away from the region covered in the training set).