Sample-efficient non-Gaussian noise reduction in gravitational wave data via learnable wavelets

TL;DR

WaveletNet is a neural network architecture that efficiently reduces non-Gaussian noise in gravitational wave data by learning optimal wavelet families, improving detection sensitivity with fewer data samples.

Contribution

We propose WaveletNet, a novel, sample-efficient neural network that learns wavelet families to model glitches, enhancing gravitational wave search pipelines over traditional CNN approaches.

Findings

Improves search sensitive volume by up to 15% for certain binary signals.

More sample-efficient than CNN-based methods.

Effective in downweighting noisy candidate regions.

Abstract

We introduce $\texttt{WaveletNet}$, a wavelet-based neural network architecture to identify and reduce non-Gaussian noise in gravitational wave data. Traditionally, convolutional neural networks (CNNs) have been widely used as a flexible machine learning method to mitigate non-Gaussian noise. However, training CNNs requires many data samples, especially when the input data segments are long. Glitches that mimic high-mass black hole signals are empirically known to have a wavelet-like structure. We exploit this property in $\texttt{WaveletNet}$ by using simple neural networks to learn the best family of wavelets to model glitches in the LIGO-Virgo-KAGRA O3 data. Due to its simplicity, our framework is significantly more sample-efficient than CNNs. As a use case, we build upon the $\texttt{TIER}$ method and show how $\texttt{WaveletNet}$ can improve the performance of any search pipeline. We take potential GW candidates from the pipeline, and then downweight the candidates having noisy strain regions in their vicinity. We use our framework in a modular way: we provide an output score which can be added to the pipeline's existing detection statistic score for the candidates. We test our method using candidates from the $\texttt{IAS-HM}$ search pipeline and show that it improves the search sensitive volume by up to 15% for high-mass, asymmetric binaries.