A convolutional neural network to distinguish glitches from minute-long gravitational wave transients

TL;DR

This paper introduces a convolutional neural network designed to identify and distinguish glitches from gravitational wave transients in LIGO data, improving detection sensitivity for poorly modeled astrophysical signals.

Contribution

The paper presents a novel CNN approach that effectively detects glitches in gravitational wave data, even for previously unseen glitch classes, enhancing burst search reliability.

Findings

Detects over 95% of glitches in LIGO data

Effective on both known and new glitch classes

Improves the sensitivity of gravitational wave burst searches

Abstract

Gravitational wave bursts are transient signals distinct from compact binary mergers that arise from a wide variety of astrophysical phenomena. Because most of these phenomena are poorly modeled, the use of traditional search methods such as matched filtering is excluded. Bursts include short ($<$10 seconds) and long (from 10 to a few hundreds of seconds) duration signals for which the detection is constrained by environmental and instrumental transient noises called glitches. Glitches contaminate burst searches, reducing the amount of useful data and limiting the sensitivity of current algorithms. It is therefore of primordial importance to locate and distinguish them from potential burst signals. In this paper, we propose to train a convolutional neural network to detect glitches in the time-frequency space of the cross-correlated LIGO noise. We show that our network is retrieving more than 95$\%$ of the glitches while being trained only on a subset of the existing glitch classes highlighting the sensitivity of the network to completely new glitch classes.