2021/07/31 by Nikolaj Rørbæk Knøsgaard, Kristian Sommer Thygesen · 2 citations
Physics and Astronomy · #physics.comp-ph
paper · pdf · doi:10.1038/s41467-022-28122-0
published as Nature Communications volume 13, Article number: 468 (2022)
arxiv created 2022/02/07 · arxiv updated 2022/02/08
Choosing optimal representation methods of atomic and electronic structures is essential when machine learning properties of materials. We address the problem of representing quantum states of electrons in a solid for the purpose of machine leaning state-specific electronic properties. Specifically, we construct a fingerprint based on energy decomposed operator matrix elements (ENDOME) and radially decomposed projected density of states (RAD-PDOS), which are both obtainable from a standard density functional theory (DFT) calculation. Using such fingerprints we train a gradient boosting model on a set of 46k G0W0 quasiparticle energies. The resulting model predicts the self-energy correction of states in materials not seen by the model with a mean absolute error of 0.14 eV. By including the material's calculated dielectric constant in the fingerprint the error can be further reduced by 30%, which we find is due to an enhanced ability to learn the correlation/screening part of the self-energy. Our work paves the way for accurate estimates of quasiparticle band structures at the cost of a standard DFT calculation.