A charge-density machine-learning model trained on 96 small mixed-size supercells predicts large-supercell GaN defect formation energies with about 0.05 eV average error, outperforming energy-force MLIPs on the same data.
Overcoming the doping bottleneck in semiconductors.Comput
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Predicting large-supercell defect formation energies from machine-learning charge density models trained on small supercells
A charge-density machine-learning model trained on 96 small mixed-size supercells predicts large-supercell GaN defect formation energies with about 0.05 eV average error, outperforming energy-force MLIPs on the same data.