Gravitational-wave selection effects using neural-network classifiers

Research output: Contribution to journalArticlepeer-review

Colleges, School and Institutes


We present a novel machine-learning approach to estimate selection effects in gravitational-wave observations. Using techniques similar to those commonly employed in image classification and pattern recognition, we train a series of neural-network classifiers to predict the LIGO/Virgo detectability of gravitational-wave signals from compact-binary mergers. We include the effect of spin precession, higher-order modes, and multiple detectors and show that their omission, as it is common in large population studies, tends to overestimate the inferred merger rate in selected regions of the parameter space. Although here we train our classifiers using a simple signal-to-noise ratio threshold, our approach is ready to be used in conjunction with full pipeline injections, thus paving the way toward including actual distributions of astrophysical and noise triggers into gravitational-wave population analyses.

Bibliographic note

Funding Information: We thank Riccardo Buscicchio, Kaze Wong, Patricia Schmidt, Emanuele Berti, Carl-Johan Haster, and Eve Chase for discussions. D. G. is supported by European Union’s H2020 ERC Starting Grant No. 945155–GWmining, Leverhulme Trust Grant No. RPG-2019-350, and Royal Society Grant No. RGS-R2-202004. A. V. acknowledges the support of the Royal Society and Wolfson Foundation, and the UK Science and Technology Facilities Council through Grant No. ST/N021702/1. Computational work was performed on the University of Birmingham BlueBEAR cluster, the Athena cluster at HPC funded by EPSRC Grant No. EP/P020232/1, and the Maryland Advanced Research Computing Center (MARCC). Publisher Copyright: © 2020 American Physical Society.


Original languageEnglish
Article number103020
Number of pages7
JournalPhysical Review D - Particles, Fields, Gravitation and Cosmology
Issue number10
Publication statusPublished - 15 Nov 2020

ASJC Scopus subject areas