A Machine Learning Quasar Candidate Catalog with Photometric Redshifts from KiDS DR5 and AllWISE
The Astrophysical Journal Supplement Series · 01.11.2026 · 287 (1) · 14
DOI: 10.3847/1538-4365/aea41d ↗Kurz gefasst
Fachartikel in der Zeitschrift The Astrophysical Journal Supplement Series, online erschienen am 19.10.2026. Verfasst von Sen Pang und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MOST ∣ National Key Research and Development Program of China, MOST ∣ National Natural Science Foundation of China, China Manned Space Project.
Abstract (Originalsprache)
We present two complementary machine-readable catalogs for quasar (QSO) candidate selection in the Kilo-Degree Survey (KiDS) DR5. The KiDS-only catalog covers the full survey source sample and provides optical/near-infrared-based classifications together with QSO photometric redshift estimates derived without Wide-field Infrared Survey Explorer (WISE) information. The KiDS–AllWISE catalog is restricted to sources with AllWISE counterparts and provides WISE-assisted classifications and photometric redshifts. Separate stacking ensembles are trained to distinguish galaxies, stars, and QSOs. On a stratified held-out test set, the WISE-assisted classifier achieves an overall accuracy of 98.34%, a macroaveraged area under the receiver operating characteristic curve (ROC AUC) of 99.78%, and a QSO F1-score of 97.09%. Spatially disjoint R.A.-block validation yields QSO F1-scores of 95.87%–96.31%, indicating only modest spatial degradation. Feature-ablation tests show that W1/W2-based mid-infrared information provides the largest gain in QSO recovery, whereas Bayesian photometric redshift (BPZ)-derived quantities have only a minor effect. For QSO photometric redshift estimation, we train a LightGBM–XGBoost ensemble on Sloan Digital Sky Survey (SDSS) DR16 Quasar Catalog (DR16Q) quasars with valid optical and WISE photometry. On 94,057 held-out quasars, the WISE-assisted model achieves σ NMAD = 0.0633 and a catastrophic-outlier fraction of η = 12.0%; excluding WISE features degrades these values to σ NMAD = 0.0948 and η = 26.8%. Both catalogs provide probability-ranked QSO candidates and thresholded p Q samples for different follow-up priorities. As the candidates are not spectroscopically confirmed, statistical applications require independent calibration of the corresponding selection functions.
Förderung
- MOST ∣ National Key Research and Development Program of China
- MOST ∣ National Natural Science Foundation of China
- China Manned Space Project
Zitieren
APA
Pang, S., Zhang, Y., & Shi, J. (2026). A Machine Learning Quasar Candidate Catalog with Photometric Redshifts from KiDS DR5 and AllWISE. The Astrophysical Journal Supplement Series, 287(1), 14. https://doi.org/10.3847/1538-4365/aea41d
Vancouver
Pang S, Zhang Y, Shi J. A Machine Learning Quasar Candidate Catalog with Photometric Redshifts from KiDS DR5 and AllWISE. The Astrophysical Journal Supplement Series. 2026;287(1):14. doi:10.3847/1538-4365/aea41d
BibTeX
@article{Pang2026,
author = {Pang, Sen and Zhang, Yanxia and Shi, Jinghang},
title = {A Machine Learning Quasar Candidate Catalog with Photometric Redshifts from KiDS DR5 and AllWISE},
journal = {The Astrophysical Journal Supplement Series},
year = {2026},
volume = {287},
number = {1},
pages = {14},
doi = {10.3847/1538-4365/aea41d}
}
EUVIMED