Harnessing machine learning potentials to understand the functional properties of phase-change materials

Abstract

The exploitation of phase-change materials (PCMs) in diverse technological applications can be greatly aided by a better understanding of the microscopic origins of their functional properties. Over the last decade, simulations based on electronic-structure calculations within density functional theory (DFT) have provided useful insights into the properties of PCMs. However, large simulation cells and long simulation times beyond the reach of DFT simulations are needed to address several key issues of relevance for the performance of devices. One way to overcome the limitations of DFT methods is to use machine learning (ML) techniques to build interatomic potentials for fast molecular dynamics simulations that still retain a quasi-ab initio accuracy. Here, we review the insights gained on the functional properties of the prototypical PCM GeTe by harnessing such interatomic potentials. Applications and future challenges of the ML techniques in the study of PCMs are also outlined.