Machine learning framework for GW calculations across molecular dynamics trajectories
Open Access
- 2 July 2026
- journal article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (4) , 045003
Abstract
Machine learning offers a transformative approach to overcoming the computational bottlenecks of quasiparticle energy calculations in many-body perturbation theory. While the G 0 W 0 approximation provides a rigorous description of excited-state electronic properties, its high computational cost—driven by the evaluation of the inverse dielectric matrix—renders it prohibitive for molecular dynamics (MD) simulations that require sampling thousands of thermal configurations. We present a gradient-boosting framework (LightGBM) that predicts G 0 W 0 quasiparticle energies with high efficiency using only computationally inexpensive mean-field density functional theory eigenvalues and exchange-correlation potentials. Trained on a minimal subset (25%) of MD snapshots for silicon and boron nitride, the model achieves root-mean-square errors below 0.1 eV, accurately reproducing full k -resolved band structures and density of states. Crucially, we demonstrate the model’s transferability and robustness: it successfully generalizes to unseen simulation times, different thermal regimes, and distinct crystal polymorphs excluded from the training data. This data-driven approach effectively bypasses the explicit calculation of the self-energy operator, offering a scalable pathway for high-throughput excited-state simulations and the study of finite-temperature electronic properties in complex materials.Keywords
Funding Information
- Asian Office of Aerospace Research and Development (FA2386-23-1-4104)
- National Science and Technology Council (113-2112-M-032-013)
This publication has 51 references indexed in Scilit:
- Automatic Prediction of Band Gaps of Inorganic Materials Using a Gradient Boosted and Statistical Feature Selection WorkflowJournal of Chemical Information and Modeling, 2024
- Representing individual electronic states for machine learning GW band structures of 2D materialsNature Communications, 2022
- Time-Resolved Excited-State Analysis of Molecular Electron Dynamics by TDDFT and Bethe–Salpeter Equation FormalismsJournal of Chemical Theory and Computation, 2021
- Structure and Energetics of Dye-Sensitized NiO Interfaces in Water from Ab Initio MD and Large-Scale GW CalculationsJournal of Chemical Theory and Computation, 2021
- Machine Learning of Quasiparticle Energies in Molecules and ClustersJournal of Chemical Theory and Computation, 2021
- Machine Learning Force FieldsChemical Reviews, 2021
- Compression-Induced Modification of Boron Nitride Layers: A Conductive Two-Dimensional BN CompoundACS Nano, 2018
- Predictive Determination of Band Gaps of Inorganic Halide PerovskitesThe Journal of Physical Chemistry Letters, 2017
- Machine Learning Force Fields: Construction, Validation, and OutlookThe Journal of Physical Chemistry C, 2016
- BerkeleyGW: A massively parallel computer package for the calculation of the quasiparticle and optical properties of materials and nanostructuresComputer Physics Communications, 2012