English

The ZTF Source Classification Project: I. Methods and Infrastructure

Instrumentation and Methods for Astrophysics 2021-05-26 v1 Solar and Stellar Astrophysics

Abstract

The Zwicky Transient Facility (ZTF) has been observing the entire northern sky since the start of 2018 down to a magnitude of 20.5 (5σ5 \sigma for 30s exposure) in gg, rr, and ii filters. Over the course of two years, ZTF has obtained light curves of more than a billion sources, each with 50-1000 epochs per light curve in gg and rr, and fewer in ii. To be able to use the information contained in the light curves of variable sources for new scientific discoveries, an efficient and flexible framework is needed to classify them. In this paper, we introduce the methods and infrastructure which will be used to classify all ZTF light curves. Our approach aims to be flexible and modular and allows the use of a dynamical classification scheme and labels, continuously evolving training sets, and the use of different machine learning classifier types and architectures. With this setup, we are able to continuously update and improve the classification of ZTF light curves as new data becomes available, training samples are updated, and new classes need to be incorporated.

Keywords

Cite

@article{arxiv.2102.11304,
  title  = {The ZTF Source Classification Project: I. Methods and Infrastructure},
  author = {Jan van Roestel and Dmitry A. Duev and Ashish A. Mahabal and Michael W. Coughlin and Przemek Mróz and Kevin Burdge and Andrew Drake and Matthew J. Graham and Lynne Hillenbrand and C. Fremling and David Hale and Russ R. Laher and Frank J. Masci and Reed Riddle and Philippe Rosnet and Ben Rusholme and Roger Smith and Maayane T. Soumagnac and Richard Walters and Thomas A. Prince and S. R. Kulkarni},
  journal= {arXiv preprint arXiv:2102.11304},
  year   = {2021}
}
R2 v1 2026-06-23T23:25:02.520Z