On-the-fly training of polynomial machine learning potentials in computing lattice thermal conductivity

Atsushi Togo; Atsuto Seko

doi:10.1063/5.0211296

Article On-the-fly training of polynomial machine learning potentials in computing lattice thermal conductivity

Atsushi Togo (National Institute for Materials Science) ; Atsuto Seko

Download file (471 KB)
Download as zip (428 KB)

Collection

Citation

Atsushi Togo, Atsuto Seko. On-the-fly training of polynomial machine learning potentials in computing lattice thermal conductivity. The Journal of Chemical Physics. 2024, 160 (21), 211001. https://doi.org/10.1063/5.0211296

(BibTeX)

Description:

(abstract)

The application of first-principles calculations for predicting lattice thermal conductivity (LTC) in crystalline materials, in conjunction with the linearized phonon Boltzmann equation, has gained increasing popularity. In this calculation, the determination of force constants through first-principles calculations is critical for accurate LTC predictions. For material exploration, performing first-principles LTC calculations in a high-throughput manner is now expected, although it requires significant computational resources. To reduce computational demands, we integrated polynomial machine learning potentials on-the-fly during the first-principles LTC calculations. This paper presents a systematic approach to first-principles LTC calculations. We designed and optimized an efficient workflow that integrates multiple modular software packages. We applied this approach to calculate LTCs for 103 compounds of the wurtzite, zincblende, and rocksalt types to evaluate the performance of the polynomial machine learning potentials in LTC calculations. We demonstrate a significant reduction in the computational resources required for the LTC predictions.

Rights: