QZO: A Catalog of 5 Million Quasars from the Zwicky Transient Facility
S. J. Nakoneczny, M. J. Graham, D. Stern, G. Helou, S. G. Djorgovski, E. C. Bellm, T. X. Chen, R. Dekany, A. Drake, A. A. Mahabal, T. A. Prince, R. Riddle, B. Rusholme, N. Sravan

TL;DR
This paper presents a catalog of 4.85 million quasars identified from ZTF light curves using advanced machine learning techniques, demonstrating superior classification performance and providing redshift estimates for a subset.
Contribution
It introduces a novel approach combining transformer neural networks and gradient boosting to classify quasars from light curves, significantly expanding existing catalogs.
Findings
Achieved 97% F1 score for quasar classification with 100 epochs per light curve.
Found ZTF classification outperforms static surveys like Pan-STARRS and matches WISE and Gaia.
Determined survey duration and cadence requirements for high-accuracy quasar identification.
Abstract
Machine learning methods are well established in the classification of quasars (QSOs). However, the advent of light curve observations adds a great amount of complexity to the problem. Our goal is to use the Zwicky Transient Facility (ZTF) to create a catalog of QSOs. We process the ZTF DR20 light curves with a transformer artificial neural network and combine different surveys with extreme gradient boosting. Based on ZTF g-band and WISE observations, we find 4,849,574 objects classified as QSOs with confidence higher than 90%. We robustly classify objects fainter than the SNR limit at by requiring . For 33% of QZO objects, with available WISE data, we publish redshifts with estimated error . We find that ZTF classification is superior to the Pan-STARRS static bands, and on par with WISE and Gaia measurements,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParticle Accelerators and Free-Electron Lasers · Astronomy and Astrophysical Research · Computational Physics and Python Applications
