Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies

TL;DR

This paper introduces a Gaussian regression-based interatomic potential that accurately models phonon transport in crystalline silicon with and without vacancies, bridging the gap between ab initio accuracy and computational efficiency.

Contribution

The development of a Gaussian approximation potential (GAP) that accurately predicts phonon transport properties in silicon, outperforming empirical potentials and approaching density functional theory accuracy.

Findings

GAP accurately reproduces phonon dispersion and scattering rates.

GAP outperforms empirical potentials in accuracy.

Computational cost of GAP is feasible for large systems.

Abstract

We report that single interatomic potential, developed using Gaussian regression of density functional theory calculation data, has high accuracy and flexibility to describe phonon transport with ab initio accuracy in two different atomistic configurations: perfect crystalline Si and crystalline Si with vacancies. The high accuracy of second- and third-order force constants from the Gaussian approximation potential (GAP) are demonstrated with phonon dispersion, Gr\"uneisen parameter, three-phonon scattering rate, phonon-vacancy scattering rate, and thermal conductivity, all of which are very close to the results from density functional theory calculation. We also show that the widely used empirical potentials (Stillinger-Weber and Tersoff) produce much larger errors compared to the GAP. The computational cost of GAP is higher than the two empirical potentials, but five orders of magnitude lower than the density functional theory calculation. Our work shows that GAP can provide a new opportunity for studying phonon transport in partially disordered crystalline phases with the high predictive power of ab initio calculation but at a feasible computational cost.