Accelerating Phonon Thermal Conductivity Prediction by an Order of Magnitude Through Machine Learning-Assisted Extraction of Anharmonic Force Constants

TL;DR

This paper introduces a machine learning method that significantly accelerates the calculation of phonon thermal conductivity by efficiently extracting anharmonic force constants, enabling high-throughput material screening.

Contribution

The authors develop a machine learning-assisted technique that reduces the computational cost of anharmonic force constant evaluation by over an order of magnitude while maintaining accuracy.

Findings

Reduced computational time from 480,000 to 12,000 CPU-hours.

Maintained thermal conductivity prediction accuracy within 10%.

Applied successfully to 220 ternary materials.

Abstract

The calculation of material phonon thermal conductivity from density functional theory calculations requires computationally expensive evaluation of anharmonic interatomic force constants and has remained a computational bottleneck in the high-throughput discovery of materials. In this work, we present a machine learning-assisted approach for the extraction of anharmonic force constants through local learning of the potential energy surface. We demonstrate our approach on a diverse collection of 220 ternary materials for which the total computational time for anharmonic force constants evaluation is reduced by more than an order of magnitude from 480,000 cpu-hours to less than 12,000 cpu-hours while preserving the thermal conductivity prediction accuracy to within 10%. Our approach removes a major hurdle in computational thermal conductivity evaluation and will pave the way forward for the high-throughput discovery of materials.