Two studies assess interpretable compact features for photometric Type Ia supernova classification

Compact and Physically Interpretable Feature Models for Photometric Type Ia Supernova Classification

arXiv:2603.14500v2 Announce Type: replace Abstract: Photometric classification of Type Ia supernovae is essential for modern time-domain surveys, where spectroscopic confirmation is not always feasible for the full transient sample. We investigate a compact and physically interpretable feature representation derived from multi-band light curves and evaluate its performance using gradient-boosted decision trees on the Supernova Photometric Classification Challenge (SPCC) dataset. The compact representation is derived from an initial pool of 31 light-curve features, reduced to 30 after removing redundant variables and further optimized to a 16-feature model through systematic ablation analysis. The final compact model achieves an F1-score of 0.844 on the held-out test set, consistent with k-fold cross-validation results (0.841 +/- 0.006). The precision-recall area under the curve (PR-AUC) is 0.928, with similarly low variance across folds. Ablation experiments show that temporal evolution provides the dominant classification signal, while brightness, color, and variability features contribute complementary information. A reduced core of approximately ten physically meaningful features retains most of the performance of the compact model, with only a small decrease in F1-score, indicating that reliable classification does not require large high-dimensional feature spaces. These results demonstrate that interpretable feature-based models can capture the essential astrophysical information needed for Type Ia photometric classification, with implications for survey cadence, filter coverage, and the design of transparent and efficient machine-learning pipelines for time-domain surveys.

1 day ago

Testing the Generalization and Domain Stability of Compact Feature Representations for Photometric Supernova Classification

arXiv:2606.22879v1 Announce Type: new Abstract: Photometric classification of supernovae increasingly requires models that are not only accurate within a single survey but also robust to changes in cadence, noise properties, filter coverage, and survey domain. We investigate the generalization and domain stability of a compact 16-feature representation for Type Ia supernova classification. The feature set consists of physically interpretable descriptors of brightness, color, variability, and temporal evolution. Using the Supernova Photometric Classification Challenge (SPCC) dataset as the reference domain, we confirm that a compact XGBoost classifier achieves strong within-survey performance, reaching an F1 score of 0.844 and a PR-AUC of 0.928 on a held-out test set. We then evaluate robustness under alternative classifiers, repeated resampling, feature perturbations, missing-band proxies, shortened temporal coverage, and cross-survey transfer to PLAsTiCC. The compact representation remains stable under resampling and moderate perturbations, but direct SPCC$\rightarrow$PLAsTiCC transfer produces a substantial performance degradation. Class-conditional centroid analysis shows that the SPCC and PLAsTiCC Type Ia populations occupy different regions of the compact feature space. The cross-survey Ia centroid shift exceeds the Ia/non-Ia separation within either survey, indicating that the transfer gap is driven primarily by feature-space domain shift rather than classifier instability. These results show that compact physically interpretable features are robust within a survey and useful for diagnostic analysis, but are not automatically survey-invariant. Cross-survey deployment therefore requires feature harmonization, domain adaptation, or restriction to a smaller set of survey-stable features.

1 day ago