CoBiTS: Single-detector discrimination of binary black hole signals from glitches using deep learning

TL;DR

CoBiTS is a deep learning model that effectively distinguishes binary black hole gravitational wave signals from noise artifacts in LIGO-Virgo-KAGRA data, reducing false positives and aiding in accurate detection.

Contribution

This paper introduces CoBiTS, a Conformer-based neural network that improves discrimination of BBH signals from glitches using single-detector data, combining convolutional and Transformer features.

Findings

CoBiTS accurately identifies BBH signals even with overlapping glitches.

The model outperforms previous methods in discriminating high-mass BBH signals from noise.

Conformer architecture enhances sequence modeling for gravitational wave data.

Abstract

We develop a Conformer neural network, called Conformer Binary neTwork Search, or CoBiTS, for distinguishing binary black hole (BBH) gravitational wave (GW) signals from non-Gaussian and non-stationary noise artifacts in the data from current generation LIGO-Virgo-KAGRA detectors. A large subset of these transient noise artifacts, termed as ``glitches'' for short, trigger BBH search templates. Some of them go on to produce detection candidates and require human vetting, supported by data quality tools, to be correctly identified and vetoed. In its current version, CoBiTS takes as inputs single-detector strain timeseries snippets, claimed by other search pipelines to be containing GW candidates, and outputs the significance of each snippet to contain a BBH signal and a glitch. CoBiTS is shown to be particularly effective in discriminating high-mass BBH signals from blips and scattered light glitches, even when a signal is near concurrent or overlapping with a glitch. The performance of CoBiTS gains from employing Conformer, which is a specialized model that combines convolutional layers and Transformer architecture for sequence modeling tasks. Conformer is especially good at leveraging the strengths of both convolutional layers -- for local feature extraction -- and self-attention layers -- for capturing long-range dependencies.