SiGMa-Net: Deep learning network to distinguish binary black hole signals from short-duration noise transients

TL;DR

This paper introduces SiGMa-Net, a deep learning approach utilizing sine-Gaussian projection maps to effectively distinguish binary black hole signals from short-duration noise transients in gravitational wave data, enhancing detection sensitivity.

Contribution

The paper presents a novel neural network using sine-Gaussian projection maps for improved classification of GW signals and noise, outperforming traditional methods in sensitivity and accuracy.

Findings

Significantly improves BBH signal identification sensitivity by 75%.

Correctly identifies 95% of real GW events in GWTC-3.

Operates efficiently with classification times of a few minutes for thousands of maps.

Abstract

Blip glitches, a type of short-duration noise transient in the LIGO--Virgo data, are a nuisance for the binary black hole (BBH) searches. They affect the BBH search sensitivity significantly because their time-domain morphologies are very similar, and that creates difficulty in vetoing them. In this work, we construct a deep-learning neural network to efficiently distinguish BBH signals from blip glitches. We introduce sine-Gaussian projection (SGP) maps, which are projections of GW frequency-domain data snippets on a basis of sine-Gaussians defined by the quality factor and central frequency. We feed the SGP maps to our deep-learning neural network, which classifies the BBH signals and blips. Whereas the BBH signals are simulated, the blips used are taken from real data throughout our analysis. We show that our network significantly improves the identification of the BBH signals in comparison to the results obtained using traditional-$\chi^2$ and sine-Gaussian $\chi^2$. For example, our network improves the sensitivity by 75% at a false-positive rate of $10^{-2}$ for BBHs with total mass in the range $[80,140]~M_{\odot}$ and SNR in the range $[3,8]$. Also, it correctly identifies 95% of the real GW events in GWTC-3. The computation time for classification is a few minutes for thousands of SGP maps on a single core. With further optimisation in the next version of our algorithm, we expect a further reduction in the computational cost. Our proposed method can potentially improve the veto process in the LIGO--Virgo GW data analysis and conceivably support identifying GW signals in low-latency pipelines.