Convolutional Neural Networks for signal detection in real LIGO data

TL;DR

This paper presents a machine learning approach for detecting gravitational-wave signals in LIGO data, demonstrating its effectiveness on real O3b data and comparing it with traditional methods within a unified evaluation framework.

Contribution

The paper introduces a machine learning algorithm for gravitational-wave signal detection and evaluates it on real LIGO data within a standardized challenge framework.

Findings

Successfully detected signals in real O3b LIGO data

Compared machine learning method with traditional analyses

Achieved competitive detection performance

Abstract

Searching the data of gravitational-wave detectors for signals from compact binary mergers is a computationally demanding task. Recently, machine learning algorithms have been proposed to address current and future challenges. However, the results of these publications often differ greatly due to differing choices in the evaluation procedure. The Machine Learning Gravitational-Wave Search Challenge was organized to resolve these issues and produce a unified framework for machine-learning search evaluation. Six teams submitted contributions, four of which are based on machine learning methods and two are state-of-the-art production analyses. This paper describes the submission from the team TPI FSU Jena and its updated variant. We also apply our algorithm to real O3b data and recover the relevant events of the GWTC-3 catalog.