Anomaly Detection in the Fink Community Broker
par
Amphi Recherche
The detection of new astronomical events is one of the most anticipated outcomes of the next generation of large-scale sky surveys. Experiments such as the Vera Rubin Observatory Legacy Survey of Space and Time (LSST) are expected to continuously monitor large areas of the sky with remarkable deliberation, which will undoubtedly lead to the detection of unforeseen astrophysical phenomena. At the same time, the volume of data gathered every night will also increase to unprecedented levels, rendering serendipitous discoveries unlikely. In the era of big data, most detected sources will never be visually inspected, and the use of automated algorithms is unavoidable. I would like to present the anomaly detection module developed for the Fink community broker to search for unusual astrophysical events in the Zwicky Transient Facility alert stream and LSST in future. I will show the first discoveries made with the module including a rare subtype of cataclysmic variables, supernova with a precursor, fast transients of unknown nature. I will also introduce the Fink anomaly detection bot for Slack and Telegram messengers, as well as the active anomaly detection that has been recently implemented to make the search for anomalies more efficient.
