A moment tensor potential for lattice thermal conductivity calculations of alpha and beta phases of Ga2O3

Abstract

Calculations of heat transport in crystalline materials have recently become mainstream, thanks to machine-learned interatomic potentials that allow for significant computational cost reductions while maintaining the accuracy of first-principles calculations. Moment tensor potentials (MTP) are among the most efficient and accurate models in this regard. In this study, we demonstrate the application of MTP to the calculation of the lattice thermal conductivity of alpha and beta Ga2O3. Although MTP is commonly employed for lattice thermal conductivity calculations, the advantages of applying the active learning methodology for potential generation is often overlooked. Here, we emphasize its importance and illustrate how it enables the generation of a robust and accurate interatomic potential while maintaining a moderate-sized training dataset.