Modeling the Ga/As binary system across temperaturesand compositions from first principles

TL;DR

This paper introduces a machine-learning potential trained on density functional theory data to accurately model the Ga/As binary system across various temperatures and compositions, enabling reliable predictions of phase behavior and properties.

Contribution

It presents a transferable ML potential for Ga/As, validated through rigorous tests, and demonstrates how a committee model can quantify uncertainty and guide iterative improvements.

Findings

Accurately predicts finite-temperature properties of Ga/As

Identifies phase boundaries with ab initio accuracy

Uses committee model to assess prediction uncertainty

Abstract

Materials composed of elements from the third and fifth columns of the periodic table display a very rich behavior, with the phase diagram usually containing a metallic liquid phase and a polar semiconducting solid. As a consequence, it is very hard to achieve transferable empirical models of interactions between the atoms that can reliably predict their behavior across the temperature and composition range that is relevant to the study of the synthesis and properties of III/V nanostructures and devices. We present a machine-learning potential trained on density functional theory reference data that provides a general-purpose model for the Ga$_x$As$_{1-x}$ system. We provide a series of stringent tests that showcase the accuracy of the potential, and its applicability across the whole binary phase space, computing with ab initio accuracy a large number of finite-temperature properties as well as the location of phase boundaries. We also show how a committe model can be used to reliably determine the uncertainty induced by the limitations of the ML model on its predictions, to identify regions of phase space that are predicted with insufficient accuracy, and to iteratively refine the training set to achieve consistent, reliable modeling.