BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Francisco Förster Burón (Universidad de Chile) DTSTART:20240111T170000Z DTEND:20240111T180000Z DTSTAMP:20260423T003238Z UID:MPML/110 DESCRIPTION:Title: T he ALeRCE astronomical alert broker\nby Francisco Förster Burón (Uni versidad de Chile) as part of Mathematics\, Physics and Machine Learning ( IST\, Lisbon)\n\n\nAbstract\nA new generation of large aperture and large field of view telescopes is allowing the exploration of large volumes of t he Universe in an unprecedented fashion. In order to take advantage of the se new telescopes\, notably the Vera C. Rubin Observatory\, a new time dom ain ecosystem is developing. Among the tools required are fast machine lea rning aided discovery and classification algorithms\, interoperable tools to allow for an effective communication with the community and follow-up t elescopes\, and new models and tools to extract the most physical knowledg e from these observations. In this talk I will review the challenges and p rogress of building one of these systems: the Automatic Learning for the R apid Classification of Events (ALeRCE) astronomical alert broker. ALeRCE ( http://alerce.science/) is an alert annotation and classification system l ed by an interdisciplinary and interinstitutional group of scientists from Chile since 2019. ALeRCE is focused around three scientific cases: transi ents\, variable stars and active galactic nuclei. Thanks to its state-of-t he-art machine learning models\, ALeRCE has become the 3rd group to report most transient candidates to the Transient Name Server\, and it is enabli ng new science with different astrophysical objects\, e.g. AGN science. I will discuss some of the challenges associated with the problem of alert c lassification\, including the ingestion of multiple alert streams\, annota tion\, database management\, training set building\, feature computation a nd distributed processing\, machine learning classification and visualizat ion\, or the challenges of working in large interdisciplinary teams. I wil l also show some results based on the real‐time ingestion and classifica tion using the Zwicky Transient Facility (ZTF) alert stream as input\, as well as some of the tools available.\n LOCATION:https://researchseminars.org/talk/MPML/110/ END:VEVENT END:VCALENDAR