Transferable Machine Learning Approach for Predicting Electronic Structures of Charged Defects

Abstract: The study of the electronic properties of charged defects is crucial for our understanding of various electrical properties of materials. However, the high computational cost of density functional theory (DFT) hinders the research on large defect models. In this study, we present an E(3) equivariant graph neural network framework (HamGNN-Q), which can predict the tight-binding Hamiltonian matrices for various defect types with different charges using only one set of network parameters. By incorporating features of background charge into the element representation, HamGNN-Q enables a direct mapping from structure and background charge to the electronic Hamiltonian matrix of charged defect systems without DFT calculation. We demonstrate the model's high precision and transferability through testing on GaAs systems with various charged defect configurations. Our approach provides a practical solution for accelerating charged defect electronic structure calculations and advancing the design of materials with tailored electronic properties.