Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nguyen, Tri Minh, Tawfik, Sherif Abdulkader, Tran, Truyen, Venkatesh, Svetha
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.23943
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911543416848384
author Nguyen, Tri Minh
Tawfik, Sherif Abdulkader
Tran, Truyen
Venkatesh, Svetha
author_facet Nguyen, Tri Minh
Tawfik, Sherif Abdulkader
Tran, Truyen
Venkatesh, Svetha
contents Accurate charge densities are central to electronic-structure theory, but computing charge-state-dependent densities with density functional theory remains too expensive for large-scale screening and defect workflows. We present ChargeFlow, a flow-matching refinement model that transforms a charge-conditioned superposition of atomic densities into the corresponding DFT electron density on the native periodic real-space grid using a 3D U-Net velocity field. Trained on 9,502 charged Materials Project-derived calculations and evaluated on an external 1,671-structure benchmark spanning perovskites, charged defects, diamond defects, metal-organic frameworks, and organic crystals, ChargeFlow is not uniformly best on every in-distribution class but is strongest on problems dominated by nonlocal charge redistribution and charge-state extrapolation, improving deformation-density error from 3.62% to 3.21% and charge- response cosine similarity from 0.571 to 0.655 relative to a ResNet baseline. The predicted densities remain chemically useful under downstream analysis, yielding successful Bader partitioning on all 1,671 benchmark structures and high-fidelity electrostatic potentials, which positions flow matching as a practical density-refinement strategy for charged materials.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23943
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ChargeFlow: Flow-Matching Refinement of Charge-Conditioned Electron Densities
Nguyen, Tri Minh
Tawfik, Sherif Abdulkader
Tran, Truyen
Venkatesh, Svetha
Materials Science
Machine Learning
Accurate charge densities are central to electronic-structure theory, but computing charge-state-dependent densities with density functional theory remains too expensive for large-scale screening and defect workflows. We present ChargeFlow, a flow-matching refinement model that transforms a charge-conditioned superposition of atomic densities into the corresponding DFT electron density on the native periodic real-space grid using a 3D U-Net velocity field. Trained on 9,502 charged Materials Project-derived calculations and evaluated on an external 1,671-structure benchmark spanning perovskites, charged defects, diamond defects, metal-organic frameworks, and organic crystals, ChargeFlow is not uniformly best on every in-distribution class but is strongest on problems dominated by nonlocal charge redistribution and charge-state extrapolation, improving deformation-density error from 3.62% to 3.21% and charge- response cosine similarity from 0.571 to 0.655 relative to a ResNet baseline. The predicted densities remain chemically useful under downstream analysis, yielding successful Bader partitioning on all 1,671 benchmark structures and high-fidelity electrostatic potentials, which positions flow matching as a practical density-refinement strategy for charged materials.
title ChargeFlow: Flow-Matching Refinement of Charge-Conditioned Electron Densities
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2603.23943