Complete Neural Electronic Initialization Accelerates Materials DFT
Abstract
We present the first complete machine learning method for accelerating plane-wave density functional theory (DFT) in materials under the projector augmented wave (PAW) formalism. We formalize seven criteria that a Complete Neural Electronic Initializer must satisfy for practical end-to-end PAW DFT acceleration. Applying these to prior work reveals two structure-dependent components, augmentation occupancies and spin initialization, whose absence prevents existing acceleration methods from providing complete reference-free initialization. We show that omitting these components can eliminate or reverse the acceleration obtained via models that only predict the smooth valence density. We satisfy the missing requirements by introducing AugNet, a general equivariant model for PAW augmentation occupancies, and the first general spin density model for materials, which predicts the smooth spin-difference density and spin-difference PAW augmentation occupancies using predicted magnetic moments to constrain the global magnetic state. Combined with existing valence density models, our full method satisfies all seven criteria and forms a fully reference-free electronic initializer for materials DFT, requiring no electronic quantities from a converged target calculation. We show that perfect initialization could cut PAW DFT wall time by 40-52%, and our method recovers up to 62% of this saving, reducing end-to-end DFT wall time by up to ~25% on unseen structures while preserving converged energies.
Related
- Electronic structure, magnetic interactions, and magnonics of 2D trichloride materials
- Geometry-Controlled Magnetic and Electronic Landscapes in Anisotropic van der Waals Materials
- Nuclear-Electronic Orbital Theory: Exploring Nuclear Quantum Effects in Chemistry, Biology, and Materials.
- Advanced semiconductor materials for future electronic systems: from conventional to quantum devices
- Detection Defines Dephasing in Two-Dimensional Electronic Spectroscopy of Materials: Coherent Field Emission versus Incoherent Population Observables
BibTeX
@misc{ærtebjerg2026complete,
title = {{Complete Neural Electronic Initialization Accelerates Materials DFT}},
author = {Felix Ærtebjerg and Jonas Elsborg and Arghya Bhowmik},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21759},
eprint = {2609.21759},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21759},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Complete Neural Electronic Initialization Accelerates Materials DFT
AU - Felix Ærtebjerg
AU - Jonas Elsborg
AU - Arghya Bhowmik
PY - 2026
DA - 2026/09/27
PB - arXiv
DO - 10.48550/arxiv.2609.21759
UR - https://arxiv.org/abs/2609.21759
AB - We present the first complete machine learning method for accelerating plane-wave density functional theory (DFT) in materials under the projector augmented wave (PAW) formalism. We formalize seven criteria that a Complete Neural Electronic Initializer must satisfy for practical end-to-end PAW DFT acceleration. Applying these to prior work reveals two structure-dependent components, augmentation occupancies and spin initialization, whose absence prevents existing acceleration methods from providing complete reference-free initialization. We show that omitting these components can eliminate or reverse the acceleration obtained via models that only predict the smooth valence density. We satisfy the missing requirements by introducing AugNet, a general equivariant model for PAW augmentation occupancies, and the first general spin density model for materials, which predicts the smooth spin-difference density and spin-difference PAW augmentation occupancies using predicted magnetic moments to constrain the global magnetic state. Combined with existing valence density models, our full method satisfies all seven criteria and forms a fully reference-free electronic initializer for materials DFT, requiring no electronic quantities from a converged target calculation. We show that perfect initialization could cut PAW DFT wall time by 40-52%, and our method recovers up to 62% of this saving, reducing end-to-end DFT wall time by up to ~25% on unseen structures while preserving converged energies.
ER -