Tidal disruption events (TDEs) are astrophysical phenomena that occur when stars are disrupted by supermassive black holes. The Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), with its unprecedented depth and cadence, will detect thousands of TDEs, creating the need for robust photometric classifiers capable of efficiently distinguishing these events from other extragalactic transients. We developed and validated a machine learning pipeline for photometric TDE identification in LSST-scale datasets. Our classifier is designed to provide high precision and recall, enabling the construction of reliable TDE catalogs for multi-messenger follow-up and statistical studies. Using the second Extended LSST Astronomical Time Series Classification Challenge (ELAsTiCC2) dataset, we fit Gaussian processes (GPs) to light curves for feature extraction (e.g., color, rise and fade times, and GP length scales). We then trained and tuned boosted decision-tree models (XGBoost) with a custom scoring function that emphasizes the high-precision recovery of TDEs. Our pipeline was tested on diverse simulations of transient and variable events, including supernovae, active galactic nuclei, and superluminous supernovae. We achieve high precision (up to 95%) while maintaining competitive recall (about 72%) for TDEs, with minimal contamination from non-TDE classes. Key predictive features include post-peak colors and GP hyperparameters that reflect the characteristic timescales and spectral behaviors of TDEs. Our photometric classifier provides a practical and scalable approach to identifying TDEs in forthcoming LSST data. By capturing essential color and temporal properties through GP-based feature extraction, it enables the efficient construction of clean TDE candidate samples. Future refinements will incorporate real data and additional features (e.g., photometric redshifts), further enhancing the reliability and scientific impact of this classification framework.
Bhardwaj et al. (Thu,) studied this question.