A Caltech Library Service

GWSkyNet: A Real-time Classifier for Public Gravitational-wave Candidates

Cabero, Miriam and Mahabal, Ashish and McIver, Jess (2020) GWSkyNet: A Real-time Classifier for Public Gravitational-wave Candidates. Astrophysical Journal Letters, 904 (1). Art. No. L9. ISSN 2041-8213. doi:10.3847/2041-8213/abc5b5.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


The rapid release of accurate sky localization for gravitational-wave (GW) candidates is crucial for multi-messenger observations. During the third observing run of Advanced LIGO and Advanced Virgo, automated GW alerts were publicly released within minutes of detection. Subsequent inspection and analysis resulted in the eventual retraction of a fraction of the candidates. Updates could be delayed by up to several days, sometimes issued during or after exhaustive multi-messenger follow-up campaigns. We introduce GWSkyNet, a real-time framework to distinguish between astrophysical events and instrumental artifacts using only publicly available information from the LIGO-Virgo open public alerts. This framework consists of a non-sequential convolutional neural network involving sky maps and metadata. GWSkyNet achieves a prediction accuracy of 93.5% on a testing data set.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper ItemGravitational Wave Open Science Center
Cabero, Miriam0000-0003-4059-4512
Mahabal, Ashish0000-0003-2242-0244
McIver, Jess0000-0003-0316-1355
Additional Information:© 2020 The American Astronomical Society. Received 2020 September 22; revised 2020 October 19; accepted 2020 October 24; published 2020 November 19. We are thankful to the Gravity Spy team, and in particular Scott Coughlin, for sharing the collection of O1 and O2 glitches. We are also thankful to Deep Chatterjee, Tito Dal Canton, Derek Davis, Daryl Haggard, Ian Harry, Fergus Hayes, Alexander H. Nitz, Leo P. Singer, Nicholas Vieira, and the anonymous referee for useful comments and discussions. M.C. and J.M. acknowledge funding from the Natural Sciences and Engineering Research Council of Canada (NSERC). A.M. acknowledges support from the NSF (1640818, AST-1815034). A.M. and J.M. also acknowledge support from IUSSTF (JC-001/2017). This research has made use of data, software, and/or web tools obtained from the Gravitational Wave Open Science Center (, a service of LIGO Laboratory, the LIGO Scientific Collaboration, and the Virgo Collaboration. LIGO is funded by the U.S. National Science Foundation. Virgo is funded by the French Centre National de Recherche Scientifique (CNRS), the Italian Istituto Nazionale della Fisica Nucleare (INFN), and the Dutch Nikhef, with contributions by Polish and Hungarian institutes.
Funding AgencyGrant Number
Natural Sciences and Engineering Research Council of Canada (NSERC)UNSPECIFIED
Indo-US Science and Technology ForumJC-001/2017
Centre National de la Recherche Scientifique (CNRS)UNSPECIFIED
Istituto Nazionale di Fisica Nucleare (INFN)UNSPECIFIED
Subject Keywords:Convolutional neural networks ; Gravitational wave astronomy ; Observational astronomy
Issue or Number:1
Classification Code:Unified Astronomy Thesaurus concepts: Convolutional neural networks (1938); Gravitational wave astronomy (675); Observational astronomy (1145)
Record Number:CaltechAUTHORS:20201123-104059122
Persistent URL:
Official Citation:Miriam Cabero et al 2020 ApJL 904 L9
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:106780
Deposited By: Tony Diaz
Deposited On:23 Nov 2020 19:31
Last Modified:16 Nov 2021 18:56

Repository Staff Only: item control page