High-Throughput GW Calculations via Machine Learning

2025/05/05 by Ragab. A. Abdelghany, Chih‐En Hsu, Abdelghany, Ragab. A. +7
Engineering · #Advanced MEMS and NEMS Technologies #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci)

paper · pdf · doi:10.48550/arxiv.2505.02421

openalex publication_date 2025/05/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a machine learning (ML) framework that predicts G₀W₀ quasiparticle energies across molecular dynamics (MD) trajectories with high accuracy and efficiency. Using only DFT-derived mean-field eigenvalues and exchange-correlation potentials, the model is trained on 25% of MD snapshots and achieves RMSEs below 0.1 eV. It accurately reproduces k-resolved quasiparticle band structures and density of states, even for BN polymorphs excluded from the training data. This approach bypasses the computational bottlenecks of G₀W₀ simulations over dynamic configurations, offering a scalable route to excited-state electronic structure simulations with many-body accuracy.

Related

• Transfer learning of GW-Bethe-Salpeter Equation excitation energies
• Accelerating GW calculations through machine learned dielectric matrices
• qsGW quasiparticle and GW-BSE excitation energies of 133,885 molecules
• Machine Learning Many-Body Green's Functions for Molecular Excitation Spectra
• Automated Workflow for Accurate High-Throughput GW Calculations