Presentation #203.06 in the session “Machine Learning in Astronomy: Transient Discovery with Machine Learning (Meeting-in-a-Meeting)”.
ALeRCE is an astronomical alert broker aiming at the rapid classification of large etendue telescope alert streams, such as that provided by the Zwicky Transient Facility (ZTF) and, in the future, the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). ALeRCE contains an ever evolving set of machine learning algorithms that are constantly being improved. We have developed different models for real-time classification of stamps, light curves and finding outliers. This talk will focus on the models under production, models in development, and challenges lying ahead, including moving towards a multistream ecosystem dominated by LSST.