Transient Classifiers for Fink: Benchmarks for LSST

Abstract

The upcoming Legacy Survey of Space and Time (LSST) is expected to detect a few million transients per night, which will generate a live alert stream during the entire ten years of the survey. This stream will be distributed via community brokers whose task is to select subsets of the stream and direct them to scientific communities. Given the volume and complexity of the anticipated data, machine learning algorithms will be paramount for this task. We present the infrastructure tests and classification methods developed within the Fink broker in preparation for LSST. This work aims to provide detailed information regarding the underlying assumptions and methods behind each classifier and enable users to make informed follow-up decisions from Fink photometric classifications. Using simulated data from ELAsTiCC, we showcase the performance of binary and multi-class ML classifiers available in Fink. These include tree-based classifiers coupled with tailored feature extraction strategies as well as deep learning algorithms. Moreover, we introduce CATS, a deep learning architecture specifically designed for this task. Our results show that Fink classifiers are able to handle the extra complexity that is expected from LSST data. CATS achieved $\ge 93\%$ precision for all classes except `long' (for which it achieved $\sim 83\%$), while our best performing binary classifier achieves $\ge 98\%$ precision and $\ge 99\%$ completeness when classifying the periodic class. ELAsTiCC was an important milestone in preparing the Fink infrastructure to deal with LSST-like data. Our results demonstrate that Fink classifiers are well prepared for the arrival of the new stream, but this work also highlights that transitioning from the current infrastructures to Rubin will require significant adaptation of the currently available tools. This work was the first step in the right direction.

19 pages, 28 figures. Revised version accepted to A&A

References in corpus (18)

• The Zwicky Transient Facility: System Overview, Performance, and First Results
• Galaxy Zoo: the dependence of morphology and colour on environment
• Results from the Supernova Photometric Classification Challenge
• The Zwicky Transient Facility Alert Distribution System
• The ANTARES Astronomical Time-Domain Event Broker
• Anomaly detection in the Zwicky Transient Facility DR3
• The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
• The Dark Energy Survey 5-year photometrically identified Type Ia Supernovae
• Fink: early supernovae Ia classification using active learning
• Combined spin orientation and phase function of asteroids
• The Dark Energy Survey Supernova Program: Cosmological biases from supernova photometric classification
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• ATAT: Astronomical Transformer for time series And Tabular data
• GRANDMA Observations of ZTF/Fink Transients during Summer 2021
• Enabling the discovery of fast transients: A kilonova science module for the Fink broker
• Supernova search with active learning in ZTF DR3
• Developing a Victorious Strategy to the Second Strong Gravitational Lensing Data Challenge
• Enabling discovery of solar system objects in large alert data streams

Cited by in corpus (6)

• A study in scarlet -- I. Photometric properties of a sample of Intermediate Luminosity Red Transients
• ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST
• Early Identification of Optical Tidal Disruption Events: A science module for the Fink broker
• The automation of optical transient discovery and classification in Rubin-era time-domain astronomy
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
• LStein: A new approach to visualizing sparse 2.5-dimensional data