GWSkyNet. II. A refined machine-learning pipeline for real-time classification of public gravitational wave alerts

Chan, Man Leong, McIver, Jess, Mahabal, Ashish, Messick, Cody, Haggard, Daryl, Raza, Nayyer, Lecoeuche, Yannick, Sutton, Patrick J. ORCID: https://orcid.org/0000-0003-1614-3922, Ewing, Becca, Di Renzo, Francesco, Cabero, Miriam, Ng, Raymond, Coughlin, Michael W., Ghosh, Shaon and Godwin, Patrick 2024. GWSkyNet. II. A refined machine-learning pipeline for real-time classification of public gravitational wave alerts. The Astrophysical Journal 972 , 50. 10.3847/1538-4357/ad496a

PDF - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

Electromagnetic follow-up observations of gravitational wave events offer critical insights and provide significant scientific gain from this new class of astrophysical transients. Accurate identification of gravitational wave candidates and rapid release of sky localization information are crucial for the success of these electromagnetic follow-up observations. However, searches for gravitational wave candidates in real time suffer from a nonnegligible false alarm rate. By leveraging the sky localization information and other metadata associated with gravitational wave candidates, GWSkyNet, a machine-learning classifier developed by Cabero et al., demonstrated promising accuracy for the identification of the origin of event candidates. We improve the performance of the classifier for LIGO–Virgo–KAGRA's (LVK) fourth observing run by reviewing and updating the architecture and features used as inputs by the algorithm. We also retrain and fine-tune the classifier with data from the third observing run. To improve the prospect of electromagnetic follow-up observations, we incorporate GWSkyNet into LVK's low-latency infrastructure as an automatic pipeline for the evaluation of gravitational wave alerts in real time. We test the readiness of the algorithm on an LVK mock data challenge campaign. The results show that by thresholding on the GWSkyNet score, noise masquerading as astrophysical sources can be rejected efficiently and the majority of true astrophysical signals can be correctly identified.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Physics and Astronomy
Additional Information:	License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by/4.0/, Type: cc-by
Publisher:	American Astronomical Society
ISSN:	0004-637X
Date of First Compliant Deposit:	27 August 2024
Date of Acceptance:	7 May 2024
Last Modified:	27 Aug 2024 16:30
URI:	https://orca.cardiff.ac.uk/id/eprint/171593

Actions (repository staff only)

Edit Item