Early Identification of Optical Tidal Disruption Events: A science module for the Fink broker

Abstract

The detection of tidal disruption events (TDEs) is one of the key science goals of large optical time-domain surveys such as the Zwicky Transient Facility (ZTF) and the upcoming Vera C. Rubin Observatory Legacy Survey of Space and Time. However, identifying TDEs in the vast alert streams produced by these surveys requires automated and reliable classification pipelines that can select promising candidates in real time. We developed a module within the Fink alert broker to identify TDEs during their rising phase. It was built to autonomously operate within the ZTF alert stream, producing a list of candidates every night and enabling spectral and multi-wavelength follow-up near peak brightness. All rising alerts are submitted to selection cuts and feature extraction using the Rainbow multi-band lightcurve fit. Best-fit values were used as input to train an XGBoost classifier with the goal of identifying TDEs. The training set was constructed using ZTF observations for objects with available classification in the Transient Name Server. Finally, candidates with high enough probability were visually inspected. The classifier achieves 76% recall, indicating strong performance in early-phase identification, despite the limited available information before peak. We show that, out of the known TDEs that pass the selection cuts, half of them are flagged as TDE before halfway in their rise, proving the feasibility of early classification. Additionally, new candidates were identified by applying the classifier on archival data, including a likely repeated TDE and some potential TDEs occurring in active galaxies. The module is implemented into the Fink alert processing framework, reporting each night a small number of candidates to dedicated communication channels through a user-friendly interface, for manual vetting and potential follow-up.