Dual-space orbital learning improves electronic band structure predictions
Beyond DFT electronic band structures via dual-space orbital learning
Machine Learning
Summary
Predicting electronic properties of materials usually requires slow and costly calculations. The authors created a method called O-kRystal that uses quicker, rougher calculations combined with learned corrections to predict more accurate electronic band structures. This approach works well for many types of materials and can capture details that simpler models miss. It may also be used to predict even more sophisticated electronic properties beyond current standard methods.
What this means in practice
- •For materials simulation teams: Predict high-fidelity electronic band energies with lower computational cost for diverse materials including metals and insulators.
- •For semiconductor device designers: Obtain more accurate band structure predictions to guide the design of novel electronic and optoelectronic devices.
Authors
Minhyuk Kang, Beom Seok Kang, Nikolai Argatoff, Miguel Nouman, Danish Khan, William A. Goddard, Anima Anandkumar
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 $0.171 \pm 0.009$ 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.