Time-domain reconstruction of signals and glitches in gravitational wave data with deep learning
利用深度学习对引力波数据中的信号和毛刺进行时域重建
Gravitational wave (GW) detectors, such as LIGO, Virgo, and KAGRA, detect faint signals from distant astrophysical events. However, their high sensitivity also makes them susceptible to background noise, which can obscure these signals. This noise often includes transient artifacts called ``glitches'' that can mimic genuine astrophysical signals or mask their true characteristics. In this study, we present DeepExtractor, a deep learning framework that is designed to reconstruct signals and glitches with power exceeding interferometer noise, regardless of their source. We design DeepExtractor to model the inherent noise distribution of GW detectors, following conventional assumptions that the noise is Gaussian and stationary over short timescales. It operates by predicting and subtracting the noise component of the data, retaining only the clean reconstruction of the signal or glitch. We focus on applications related to glitches and validate DeepExtractor's effectiveness through three experiments: (1) reconstructing simulated glitches injected into simulated detector noise, (2) comparing its performance with the state-of-the-art BayesWave algorithm, and (3) analyzing real data from the Gravity Spy dataset to demonstrate effective glitch subtraction from LIGO strain data. We further demonstrate its potential by reconstructing three real GW events from LIGO's third observing run, without being trained on GW waveforms. Our proposed model achieves a median mismatch of only 0.9% for simulated glitches, outperforming several deep learning baselines. Additionally, DeepExtractor surpasses BayesWave in glitch recovery, offering a dramatic computational speedup by reconstructing one glitch sample in approximately 0.1 s on a CPU, compared to BayesWave's processing time of approximately one hour per glitch.
展开 ▾创新性地学习噪声分布而非直接建模信号/毛刺,结合 STFT 幅相双通道 U-Net,在模拟毛刺上匹配度中位数仅 0.9%;首次将深度学习全面用于毛刺重建,且比 BayesWave 快万倍以上。
引力波探测器易受瞬态非高斯噪声(毛刺)干扰,影响信号检测与参数估计(Abbott+ 2020b)。目前主流的毛刺建模与扣除方法如 BayesWave(Cornish+ 2015)和 gwsubtract(Davis+ 2019)分别存在计算耗时长或依赖辅助通道的问题。本文提出的 DeepExtractor 通过预测背景噪声间接重建信号/毛刺,不仅在模拟对比中重建精度和速度均优于 BayesWave,还首次将深度学习成功用于真实引力波数据的毛刺扣除。未来可通过扩展至信号-毛刺重叠场景,并结合第三代探测器的零流等设计进一步发展(Narola+ 2024)。
预印本 2025-01-30 · 刊出 2025-08-13 · 收录 2026-10-12