Accelerating the calculation of electron-phonon coupling by machine learning methods

2023/02/01 by Yang Zhong, Zhong, Yang, Zhiguo Tao +7 · 1 citation
Chemistry · Materials Science · Physics and Astronomy · #Advanced Chemical Physics Studies #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Inorganic Fluorides and Related Compounds #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.2302.00439

openalex publication_date 2023/02/01 · openalex created_date 2023/02/04 · openalex updated_date 2026/07/28

Abstract

Electron-phonon coupling (EPC) plays an important role in many fundamental physical phenomena, but the high computational cost of the EPC matrix hinders the theoretical research on them. In this paper, an analytical formula is derived to calculate the EPC matrix in terms of the Hamiltonian and its gradient in the nonorthogonal atomic orbital bases. The recently-developed E(3) equivariant neural network is used to directly predict the Hamiltonian and its gradient needed by the formula, thus bypassing the expensive self-consistent iterations in DFT. The correctness of the proposed EPC calculation formula and the accuracy of the predicted EPC values of the network are illustrated by the tests on a water molecule and a MoS2 crystal.

Cited by

• MBFormer: A General Transformer-based Learning Paradigm for Many-body Interactions in Real Materials

Related

• Evaluating First-Principles Electron-Phonon Couplings: Consistency Across Methods and Implementations
• Structure and dynamics of electron-phonon coupled systems using neural quantum states
• Phonon predictions with E(3)-equivariant graph neural networks
• Ab initio solution of the many-electron Schrödinger equation with deep neural networks
• DeepErwin