Moment tensor Potentials as a Promising Tool to Study Diffusion Processes

TL;DR

This paper evaluates Moment Tensor Potentials (MTPs), a machine-learning approach, demonstrating their accuracy in reproducing ab initio data and effectively modeling vacancy diffusion in various materials.

Contribution

The study shows that MTPs can accurately reproduce energies, forces, stresses, and diffusion rates, highlighting their potential as a versatile tool in materials modeling.

Findings

MTPs accurately reproduce ab initio energies, forces, and stresses.

MTPs effectively predict vacancy diffusion rates in Al, Mo, and Si.

Results show good agreement between MTP predictions and ab initio data.

Abstract

A recently proposed class of machine-learning interatomic potentials --- Moment tensor potentials (MTPs) --- is investigated in this work. MTPs are able to actively select configurations and parametrize the potential on-the-fly. It is shown that MTPs accurately reproduce energies, forces and stresses calculated ab initio. As a more comprehensive test, MTPs are employed to calculate vacancy diffusion rates in Al, Mo and Si. We demonstrate that the results are in a good agreement with ab initio data for the materials considered.