Integrating density functional theory with machine learning for enhanced band gap prediction in metal oxides.

In this study, we used a combination of density functional theory with Hubbard correction (DFT+) and machine learning (ML) to accurately predict the band gaps and lattice parameters of metal oxides: TiO (rutile and anatase), cubic ZnO, cubic ZnO, cubic CeO, and cubic ZrO. Our results show that including values for oxygen 2p orbitals alongside for metal 3d or 4f orbitals significantly enhances the accuracy of these predictions. Through extensive DFT+ calculations, we identify optimal (, ) integer pairs that closely reproduce experimentally measured band gaps and lattice parameters for each oxide: (8 eV, 8 eV) for rutile TiO; (3 eV, 6 eV) for anatase TiO; (6 eV, 12 eV) for c-ZnO; (10 eV, 10 eV) for c-ZnO; (9 eV, 5 eV) for c-ZrO; and (7 eV, 12 eV) for c-CeO. Our ML analysis showed that simple supervised ML models can closely reproduce these DFT+ results at a fraction of the computational cost and generalize well to related polymorphs. Our approach builds on existing high-throughput DFT+ frameworks by providing fast pre-DFT estimates of structural properties and band gaps. Since this work does not aim to improve the underlying DFT+ method, the ML model shares its limitations. We also note that the reported values of strongly depend on the choice of correlated orbitals, and caution is recommended with a different choice of correlated orbitals.