Complex $\mathrm{Ga}_{2}\mathrm{O}_{3}$ Polymorphs Explored by Accurate and General-Purpose Machine-Learning Interatomic Potentials

TL;DR

This paper develops accurate and efficient machine-learning interatomic potentials for various polymorphs and disordered structures of Ga2O3, enabling detailed simulations of its phase transitions and properties.

Contribution

The authors introduce two kernel-based ML-GAPs for Ga2O3 that achieve high accuracy across multiple polymorphs and disordered states, surpassing previous computational speeds.

Findings

Both potentials accurately reproduce structural properties of all five polymorphs.

The potentials significantly accelerate simulations, with speedups of 500x and 200,000x over DFT.

The phase transition involves three stages with distinct atomic migration behaviors.

Abstract

$\mathrm{Ga}_{2}\mathrm{O}_{3}$ is a wide-bandgap semiconductor of emergent importance for applications in electronics and optoelectronics. However, vital information of the properties of complex coexisting $\mathrm{Ga}_{2}\mathrm{O}_{3}$ polymorphs and low-symmetry disordered structures is missing. In this work, we develop two types of kernel-based machine-learning Gaussian approximation potentials (ML-GAPs) for $\mathrm{Ga}_{2}\mathrm{O}_{3}$ with high accuracy for $\beta$/$\kappa$/$\alpha$/$\delta$/$\gamma$ polymorphs and generality for disordered stoichiometric structures. We release two versions of interatomic potentials in parallel, namely soapGAP and tabGAP, for excellent accuracy and exceeding speedup, respectively. We systematically show that both the soapGAP and tabGAP can reproduce the structural properties of all the five polymorphs in an exceptional agreement with ab initio results, meanwhile boost the computational efficiency with $5\times10^{2}$ and $2\times10^{5}$ computing speed increases compared to density functional theory, respectively. The results show that the liquid-solid phase transition proceeds in three different stages, a "slow transition", "fast transition" and "only Ga migration". We show that this complex dynamics can be understood in terms of different behavior of O and Ga sublattices in the interfacial layer.