Novel deep learning approach to detecting binary black hole mergers
一种检测双黑洞并合的新颖深度学习方法
Gravitational wave detection has opened up new avenues for exploring and understanding some of the fundamental principles of the Universe. The optimal method for detecting modeled gravitational-wave events involves template-based matched filtering and performing a multidetector coincidence search in the resulting signal-to-noise ratio time series. In recent years, advancements in machine learning and deep learning have led to a flurry of research into using these techniques to replace matched filtering searches and for efficient and robust parameter estimation of the gravitational wave sources. This paper presents a feasibility study for a novel approach to detecting binary black hole gravitational wave signals, which utilizes deep learning techniques on the signal-to-noise ratio time series produced from matched filtering. We show that a deep-learning search can efficiently detect binary black hole gravitational waves from the signal-to-noise ratio time series in simulated Gaussian noise with simulated transient glitches. Furthermore, our search method can outperform a maximum SNR-based matched filtering search on simulated data of the Hanford and Livingston LIGO detectors in the presence of glitches. Lastly, since we are building upon the foundations of a matched filtering search pipeline, we can extract estimates for the signal-to-noise ratio and detector frame chirp mass of a gravitational wave event with similar accuracy as existing pipelines.
展开 ▾首次将深度卷积残差网络直接应用于全模板库的 SNR 时变序列,而非应变或谱图;在包含模拟 glitch 的数据中灵敏度显著优于传统最大 SNR 搜索,并可无缝衔接现有匹配滤波管道抽取源参数。
此前基于深度学习的引力波探测多直接利用探测器应变数据或时频谱图(如 George & Huerta 2018a、Gabbard+ 2018),虽在高质量端达到接近管道灵敏度,但对低质量双中子星等信号表现受限。少数工作尝试以极少模板的 SNR 峰值为输入(Wang+ 2020、Jiang+ 2022)。本文另辟蹊径,使用完整的 SNR 时间序列和 1.9 万模板库,将匹配滤波的天然抗噪性与深度学习模式识别结合。近期机器学习搜索挑战(Schäfer+ 2023)和实时管道设计(Marx+ 2024)凸显了对噪声瞬态鲁棒性的需求,本文方法通过模拟 glitch 注入初步验证了该能力。未来可部署于真实探测器数据,与现有在线搜索管道(如 GstLAL、SPIIR)直接对比,并有望扩展至双中子星和中子星-黑洞并合等低频长信号,进一步提升实时多信使天体物理的探测效率。
预印本 2023-08-16 · 刊出 2025-01-03 · 收录 2026-10-12