Predicting the Thermal Behavior of Semiconductor Defects with Equivariant Neural Networks

TL;DR

This paper introduces an equivariant neural network framework that efficiently predicts the temperature-dependent electronic properties of defective semiconductors, matching DFT accuracy at a fraction of the computational cost.

Contribution

It presents a novel active learning approach combining two advanced equivariant graph neural networks for accurate, scalable predictions of defective semiconductor properties at finite temperatures.

Findings

Achieves DFT-level accuracy in predicting band gaps of defective GaAs.

Reduces computational cost significantly compared to traditional methods.

Demonstrates effectiveness on large-scale molecular dynamics simulations.

Abstract

The presence of defects strongly influences semiconductor behavior. However, predicting the electronic properties of defective materials at finite temperatures remains computationally expensive even with density functional theory due to the large number of atoms in the simulation cell and the multitude of thermally accessible configurations. Here, we present a neural network-based framework to investigate the electronic properties of defective semiconductors at finite temperatures efficiently. We develop an active learning approach that integrates two advanced equivariant graph neural networks: MACE for atomic energies and forces and DeepH-E3 for the electronic Hamiltonian. Focusing on representative point defects in GaAs, we demonstrate computational accuracy comparable to density functional theory at a fraction of the computational cost, predicting the temperature-dependent band gap of defective GaAs directly from larger scale molecular dynamics trajectories with an accuracy of few tens of meV. Our results highlight the potential of equivariant neural networks for accurate atomic-scale predictions in complex, dynamically evolving materials.