Fink, a new generation of broker for the LSST community

TL;DR

Fink is an advanced broker for LSST that automates alert processing, incorporates real-time deep learning classification, and aims to enhance transient science and discovery potential from large time-domain data streams.

Contribution

It introduces Fink, a novel broker integrating real-time deep learning for transient classification and adaptive learning to improve scientific outcomes from LSST data.

Findings

Successful initial science verification with Zwicky Transient Facility data

Demonstrated real-time classification capabilities

Showed potential for increased discovery rate

Abstract

Fink is a broker designed to enable science with large time-domain alert streams such as the one from the upcoming Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). It exhibits traditional astronomy broker features such as automatised ingestion, annotation, selection and redistribution of promising alerts for transient science. It is also designed to go beyond traditional broker features by providing real-time transient classification which is continuously improved by using state-of-the-art Deep Learning and Adaptive Learning techniques. These evolving added values will enable more accurate scientific output from LSST photometric data for diverse science cases while also leading to a higher incidence of new discoveries which shall accompany the evolution of the survey. In this paper we introduce Fink, its science motivation, architecture and current status including first science verification cases using the Zwicky Transient Facility alert stream.