What is it about?
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 events of LIGO we obtain a significant improvement of inverse false alarm rate. Our work highlights the potential of large neural networks in GW data analysis and, while primarily demonstrated on LIGO data, its adaptable design indicates promise for broader application within the International Gravitational-Wave Observatories Network in future observational runs.
Featured Image
Photo by Artur Adilkhanian on Unsplash
Why is it important?
MLST-IOPscience-Header.png Purpose-Led Publishing, find out more. Paper • The following article isOpen access WaveFormer: transformer-based denoising method for gravitational-wave data He Wang7,1,2,3, Yue Zhou7,4, Zhoujian Cao8,5,6, Zongkuan Guo3,6 and Zhixiang Ren8,4 Published 13 March 2024 • © 2024 The Author(s). Published by IOP Publishing Ltd Machine Learning: Science and Technology, Volume 5, Number 1 Focus on Generative AI in Science Citation He Wang et al 2024 Mach. Learn.: Sci. Technol. 5 015046 DOI 10.1088/2632-2153/ad2f54 DownloadArticle PDF Figures Tables References Open science Download PDF Article metrics 548 Total downloads 33 total citations on Dimensions.Article has an altmetric score of 2 Submit Submit to this Journal Share this article Article and author information 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 events of LIGO we obtain a significant improvement of inverse false alarm rate. Our work highlights the potential of large neural networks in GW data analysis and, while primarily demonstrated on LIGO data, its adaptable design indicates promise for broader application within the International Gravitational-Wave Observatories Network in future observational runs. Export citation and abstract BibTeX RIS Previous article in issue Next article in issue Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. 1. Introduction In September 2015, the Laser Interferometer Gravitational-Wave Observatory (LIGO) [1] detected gravitational waves (GWs) from distant colliding black holes [2–4], ushering in the era of GW astronomy. Since then, dozens of merging black-hole and neutron-star binaries [5–8] have been observed by LIGO and Virgo [9]. Currently, while some GW detection methods [10–12] that do not need templates are emerging, searching for sources of GW still typically utilizes template-matching-based analysis [13], which performs better in the case of stationary Gaussian noise superimposed on a precisely known signal waveform. However, data collected by the LIGO-Virgo-KAGRA detectors contains time series of GW strains that are heavily contaminated by loud noise artifacts that are analogous to the waveforms of the actual signals, and conversely bias the analysis results of the parameters of the putative astrophysical sources [14]. In addressing these challenges, several non-linear noise subtraction frameworks (e.g. DeepClean [15], NonSENS [16]) and glitch subtraction methods (e.g. BayesWave [17]) have been developed, aiming to improve the reliability of catalog parameter estimation. When a candidate signal is identified, rigorous studies are carried out to verify whether the candidate is related to instrumental causes [18, 19] or data quality issues [20–22] that could potentially impact the analysis of the candidate event with poor significance estimates, and even confute the astrophysical origin. In GW data analysis, noise sources can generally be categorized into two types: persistent wide band noise and short-duration noise artifacts, commonly known as glitches. The former represents noise that is continuously present at certain frequencies, while the latter refers to abrupt, transient disturbances. Although the noise subtraction process [23] can help reduce the wide band noise in the LIGO-Virgo-KAGRA detectors, it has no effect on the amplitude of noise artifacts that are unrelated to the addressed noise sources, making the rate of loud noise artifacts one of the primary limitations of an astrophysical search strategy's signal recovery ability [20–22]. Therefore, it is of paramount importance to quickly assess the data quality around a candidate signal by suppressing the overall level of noise while ensuring that the astrophysical signal can be recovered before initiating the subsequent analysis that determines the presence or significance of GW candidate events.
Perspectives
We proposed a large-scale AI model, WaveFormer, with science-driven innovations, including the combination of convolutional neural network and transformer for rich waveform information extraction from a wide frequency range, and masked loss for stable convergence and better denoising performance. We evaluated WaveFormer on pure noise realizations (the off-source data) and found that noise suppression was evident. The noise level percentile of the amplitude decreased from 52.5 to 0.47 and the noise amplitude spectral density (ASD) of the whole frequency range is significantly decreased from 1 to 3 orders of magnitude. With regard to GW signals that are contaminated by different categories of glitch, the average of glitch amplitudes is 30–800 times smaller than before. We further investigated WaveFormer's capacity to recover signals from observational data in terms of phase and amplitude recovery. We achieved state-of-the-art accuracy compared with other deep learning methods [29–32]. On majority of the detected binary black hole (BBH) events, the phase overlaps are higher than 0.99 (1% error). And no matter the circumstances, like low network SNR, we could recover the waveform amplitude with a root mean square error of for matched-filtering SNR, and the typical signal recovery error is approximately 7%. Finally, we assessed the performance of our WaveFormer-based workflow by evaluating the inverse false alarm rate (IFAR) on all reported 75 BBH events in the Gravitational-Wave Transient Catalog (GWTC), and achieved significant IFAR improvement, which indicated that data quality was significantly improved after noise suppression for the first time.
Zhixiang Ren
Peng Cheng Laboratory
Read the Original
This page is a summary of: WaveFormer: transformer-based denoising method for gravitational-wave data, Machine Learning Science and Technology, March 2024, Institute of Physics Publishing,
DOI: 10.1088/2632-2153/ad2f54.
You can read the full text:
Contributors
The following have contributed to this page
