WaveFormer: transformer-based denoising method for gravitational-wave data

TL;DR

WaveFormer is a transformer-based neural network that significantly reduces noise and accurately recovers gravitational-wave signals from LIGO data, improving data quality and detection confidence.

Contribution

The paper introduces WaveFormer, a novel deep neural network architecture with hierarchical feature extraction for enhanced noise suppression and signal recovery in gravitational-wave data.

Findings

Noise and glitches reduced by over tenfold

Signal phase error around 1%

Amplitude recovery error approximately 7%

Abstract

With the advent of gravitational-wave astronomy and the discovery of more compact binary coalescences, data quality improvement techniques are desired to handle the complex and overwhelming noise in gravitational wave (GW) observational data. Though recent machine learning-based studies have shown promising results for data denoising, they are unable to precisely recover both the GW signal amplitude and phase. To address such an issue, we develop a deep neural network centered workflow, WaveFormer, for significant noise suppression and signal recovery on observational data from the Laser Interferometer Gravitational-Wave Observatory (LIGO). The WaveFormer has a science-driven architecture design with hierarchical feature extraction across a broad frequency spectrum. As a result, the overall noise and glitch are decreased by more than one order of magnitude and the signal recovery error is roughly 1% and 7% for the phase and amplitude, respectively. Moreover, on 75 reported binary black hole (BBH) events of LIGO we obtain a significant improvement of inverse false alarm rate. Our work highlights the potential of large neural networks in gravitational wave data analysis and, while primarily demonstrated on LIGO data, its adaptable design indicates promise for broader application within the International Gravitational-Wave Observatories Network (IGWN) in future observational runs.