An XML-guided five-feature SVR model predicts GW band gaps with in-domain MAE of 0.254 eV (vs 0.247) and out-of-domain MAE of 0.348 eV (vs 0.460).
Regression shrinkage and selection via the lasso.J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accurate predictive model of band gap with selected important features based on explainable machine learning
An XML-guided five-feature SVR model predicts GW band gaps with in-domain MAE of 0.254 eV (vs 0.247) and out-of-domain MAE of 0.348 eV (vs 0.460).