Neural network self-consistent fields for density functional theory
- 1International Center for Quantum Materials, School of Physics, Peking University, Beijing, China
- 2Beijing Key Laboratory of Quantum Devices, Peking University, Beijing, China
- 3Hefei National Laboratory, Hefei, China
Abstract
Kohn-Sham density functional theory (KS-DFT) has found widespread application in accurate electronic structure calculations. However, it can be computationally demanding especially for large-scale simulations, motivating recent efforts toward its machine-learning (ML) acceleration. We propose a neural network self-consistent fields (NeuralSCF) framework that establishes the Kohn-Sham density map as a deep learning objective, which encodes the mechanics of the Kohn-Sham equations. Modeling this map with an SE(3)-equivariant graph transformer, NeuralSCF emulates the Kohn-Sham self-consistent iterations to obtain electron densities, from which other properties can be derived. NeuralSCF achieves state-of-the-art accuracy in electron density prediction and derived properties, featuring exceptional zero-shot generalization to a remarkable range of out-of-distribution systems. NeuralSCF reveals that learning from KS-DFT’s intrinsic mechanics significantly enhances the model’s accuracy and transferability, offering a promising stepping stone for accelerating electronic structure calculations through mechanics learning.
Related
- Learning consistent molecular mechanics force fields from first principles
- Grassmannian Density Learning for Physically Consistent Kohn–Sham Electronic Structure Prediction
- Coexisting Charge Density Wave and Superconducting Order in Quantizing Magnetic Fields
- Effects due to the solvent density distribution on the dynamics of polymer coils in solution under rheological flow fields
- Completing the Jacob’s ladder of multiconfiguration pair-density functional theory with a doubly hybrid functional
BibTeX
@article{song2026neural,
title = {{Neural network self-consistent fields for density functional theory}},
author = {Feitong Song and J N Feng},
journal = {npj Computational Materials},
year = {2026},
month = may,
doi = {10.1038/s41524-026-02110-0},
url = {https://doi.org/10.1038/s41524-026-02110-0},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Neural network self-consistent fields for density functional theory
AU - Feitong Song
AU - J N Feng
PY - 2026
DA - 2026/05/30
JO - npj Computational Materials
DO - 10.1038/s41524-026-02110-0
UR - https://doi.org/10.1038/s41524-026-02110-0
AB - Kohn-Sham density functional theory (KS-DFT) has found widespread application in accurate electronic structure calculations. However, it can be computationally demanding especially for large-scale simulations, motivating recent efforts toward its machine-learning (ML) acceleration. We propose a neural network self-consistent fields (NeuralSCF) framework that establishes the Kohn-Sham density map as a deep learning objective, which encodes the mechanics of the Kohn-Sham equations. Modeling this map with an SE(3)-equivariant graph transformer, NeuralSCF emulates the Kohn-Sham self-consistent iterations to obtain electron densities, from which other properties can be derived. NeuralSCF achieves state-of-the-art accuracy in electron density prediction and derived properties, featuring exceptional zero-shot generalization to a remarkable range of out-of-distribution systems. NeuralSCF reveals that learning from KS-DFT’s intrinsic mechanics significantly enhances the model’s accuracy and transferability, offering a promising stepping stone for accelerating electronic structure calculations through mechanics learning.
SN - 2057-3960
ER -