Beyond DFT electronic band structures via dual-space orbital learning
Abstract
Accurate electronic band structures are essential for predicting material properties, but high-fidelity calculations are computationally demanding. We introduce O-kRystal, a dual-space orbital-learning framework that uses a lower-cost Perdew-Burke-Ernzerhof (PBE) calculation as both an energy baseline and a source of structured orbital information. Combining PBE band energies with real- and reciprocal-space orbital matrices, O-kRystal predicts higher-level corrections for individual electronic states as a function of crystal momentum and spin. For states within 5 eV of the band-edge midpoint, it predicts Heyd-Scuseria-Ernzerhof (HSE06) band energies with a mean absolute error of 0.171 ± 0.009 eV across nearly 6,000 three-dimensional materials spanning insulating, metallic, magnetic, and nonmagnetic systems. On a separate benchmark of six strongly correlated materials, it reduces the corresponding PBE band-energy MAE by 68.7% and resolves orbital-dependent changes in the relative placement of transition-metal d and ligand p states. Despite training only at high-symmetry points, it maintains comparable accuracy at unseen points along band paths and reconstructs HSE06 densities of states from dense Brillouin-zone predictions. Finally, training O-kRystal on G0W0 quasiparticle energies for two-dimensional materials demonstrates its applicability across levels of theory and the potential of orbital learning for higher-fidelity, momentum-resolved electronic-structure prediction beyond density functional theory.
Related
- Electronic Orbital Angular Momentum Driven by Finite-Momentum Phonons: Beyond Chiral and Axial Phonons
- Equivariant Deep Learning in Direct-Product Space for Electronic-Structure Hamiltonian Prediction
- Orbital-selective electronic modes induced by doping and originating from distinct spin excitations: an essential feature of orbital-selective Mott transition
- Electronic driving of torsional modes in carbon nanotubes via orbital-phonon coupling
- Nuclear-Electronic Orbital Theory: Exploring Nuclear Quantum Effects in Chemistry, Biology, and Materials.
BibTeX
@misc{kang2026beyond,
title = {{Beyond DFT electronic band structures via dual-space orbital learning}},
author = {Minhyuk Kang and Beom Seok Kang and Nikolai Argatoff and Miguel Nouman and Danish Khan and William A. Goddard III and Anima Anandkumar},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.19919},
eprint = {2610.19919},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.19919},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Beyond DFT electronic band structures via dual-space orbital learning
AU - Minhyuk Kang
AU - Beom Seok Kang
AU - Nikolai Argatoff
AU - Miguel Nouman
AU - Danish Khan
AU - William A. Goddard III
AU - Anima Anandkumar
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.19919
UR - https://arxiv.org/abs/2610.19919
AB - Accurate electronic band structures are essential for predicting material properties, but high-fidelity calculations are computationally demanding. We introduce O-kRystal, a dual-space orbital-learning framework that uses a lower-cost Perdew-Burke-Ernzerhof (PBE) calculation as both an energy baseline and a source of structured orbital information. Combining PBE band energies with real- and reciprocal-space orbital matrices, O-kRystal predicts higher-level corrections for individual electronic states as a function of crystal momentum and spin. For states within 5 eV of the band-edge midpoint, it predicts Heyd-Scuseria-Ernzerhof (HSE06) band energies with a mean absolute error of 0.171 ± 0.009 eV across nearly 6,000 three-dimensional materials spanning insulating, metallic, magnetic, and nonmagnetic systems. On a separate benchmark of six strongly correlated materials, it reduces the corresponding PBE band-energy MAE by 68.7% and resolves orbital-dependent changes in the relative placement of transition-metal d and ligand p states. Despite training only at high-symmetry points, it maintains comparable accuracy at unseen points along band paths and reconstructs HSE06 densities of states from dense Brillouin-zone predictions. Finally, training O-kRystal on G_0W_0 quasiparticle energies for two-dimensional materials demonstrates its applicability across levels of theory and the potential of orbital learning for higher-fidelity, momentum-resolved electronic-structure prediction beyond density functional theory.
ER -