Enregistré dans:
Détails bibliographiques
Auteurs principaux: Venturella, Christian, Li, Jiachen, Hillenbrand, Christopher, Peralta, Ximena Leyva, Liu, Jessica, Zhu, Tianyu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.20384
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918045720510464
author Venturella, Christian
Li, Jiachen
Hillenbrand, Christopher
Peralta, Ximena Leyva
Liu, Jessica
Zhu, Tianyu
author_facet Venturella, Christian
Li, Jiachen
Hillenbrand, Christopher
Peralta, Ximena Leyva
Liu, Jessica
Zhu, Tianyu
contents Quantum many-body methods provide a systematic route to computing electronic properties of molecules and materials, but high computational costs restrict their use in large-scale applications. Due to the complexity in many-electron wavefunctions, machine learning models capable of capturing fundamental many-body physics remain limited. Here, we present a deep learning framework targeting the many-body Green's function, which unifies predictions of electronic properties in ground and excited states, while offering physical insights into many-electron correlation effects. By learning the $GW$ or coupled-cluster self-energy from mean-field features, our graph neural network achieves competitive performance in predicting one- and two-particle excitations and quantities derivable from one-particle density matrix. We demonstrate its high data efficiency and good transferability across chemical species, system sizes, molecular conformations, and correlation strengths in bond breaking, through multiple molecular and nanomaterial benchmarks. This work opens up opportunities for utilizing machine learning to solve many-electron problems.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20384
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
Venturella, Christian
Li, Jiachen
Hillenbrand, Christopher
Peralta, Ximena Leyva
Liu, Jessica
Zhu, Tianyu
Chemical Physics
Materials Science
Computational Physics
Quantum many-body methods provide a systematic route to computing electronic properties of molecules and materials, but high computational costs restrict their use in large-scale applications. Due to the complexity in many-electron wavefunctions, machine learning models capable of capturing fundamental many-body physics remain limited. Here, we present a deep learning framework targeting the many-body Green's function, which unifies predictions of electronic properties in ground and excited states, while offering physical insights into many-electron correlation effects. By learning the $GW$ or coupled-cluster self-energy from mean-field features, our graph neural network achieves competitive performance in predicting one- and two-particle excitations and quantities derivable from one-particle density matrix. We demonstrate its high data efficiency and good transferability across chemical species, system sizes, molecular conformations, and correlation strengths in bond breaking, through multiple molecular and nanomaterial benchmarks. This work opens up opportunities for utilizing machine learning to solve many-electron problems.
title Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
topic Chemical Physics
Materials Science
Computational Physics
url https://arxiv.org/abs/2407.20384