Machine-Learning-Based Interatomic Potentials for Group IIB to VIA Semiconductors: Toward a Universal Model

Abstract

Rapid advancements in machine-learning methods have led to the emergence of machine-learning-based interatomic potentials as a new cutting-edge tool for simulating large systems with ab initio accuracy. Still, the community awaits universal interatomic models that can be applied to a wide range of materials without tuning neural network parameters. We develop a unified deep-learning interatomic potential (the DPA-Semi model) for 19 semiconductors ranging from group IIB to VIA,