Machine learning survey uncovers novel supernova candidates in Zwicky Transient Facility data, highlighting the effectiveness of active anomaly detection for astronomical discovery.
We report several interesting candidates identified during exploratory test runs of the SNAD anomaly detection pipeline on Zwicky Transient Facility (ZTF) DR24 light curves. The work was carried out in preparation for a broader search for nuclear transients and was developed during the SNAD IX Workshop. We applied active anomaly detection algorithms from the coniferest library, together with similarity-search methods, to selected Galactic and extragalactic ZTF fields. Among the most interesting by-products of these tests, we identified three new transients reported to the Transient Name Server: two possible supernovae and one superluminous supernova candidate. We also found a dipper-like variable source among the top-ranked anomalies. Follow-up spectroscopic observations are encouraged to clarify the nature of the unclassified candidates.
No takes yet. Share an insight, caveat, or question.
Pruzhinskaya et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: