Rapid localization of gravitational wave sources from compact binary coalescences using deep learning

TL;DR

This paper introduces a deep learning method that rapidly localizes gravitational wave sources from binary mergers, significantly outperforming traditional Bayesian techniques in speed, enabling real-time multi-messenger astronomy.

Contribution

It presents the first deep learning-based approach for fast and accurate sky localization of all binary coalescence types, trained on matched-filtering outputs.

Findings

Localization in milliseconds using a single GPU

Speed improvement of three to six orders of magnitude over Bayesian methods

Applicable to neutron star and black hole binary mergers

Abstract

The mergers of neutron star-neutron star and neutron star-black hole binaries are the most promising gravitational wave events with electromagnetic counterparts. The rapid detection, localization and simultaneous multi-messenger follow-up of these sources is of primary importance in the upcoming science runs of the LIGO-Virgo-KAGRA Collaboration. While prompt electromagnetic counterparts during binary mergers can last less than two seconds, the time scales of existing localization methods that use Bayesian techniques, varies from seconds to days. In this paper, we propose the first deep learning-based approach for rapid and accurate sky localization of all types of binary coalescences, including neutron star-neutron star and neutron star-black hole binaries for the first time. Specifically, we train and test a normalizing flow model on matched-filtering output from gravitational wave searches. Our model produces sky direction posteriors in milliseconds using a single P100 GPU, which is three to six orders of magnitude faster than Bayesian techniques.