发表机构
Marietta Blau Institute for Particle Physics, Austrian Academy of Sciences; Università degli Studi di Urbino ‘Carlo Bo’; INFN（奥地利科学院玛丽埃塔·布劳粒子物理研究所; 乌尔比诺“卡洛·博”大学; 意大利国家核物理研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MADGRAV是一种基于深度学习的多层级异常检测管道，用于LIGO数据中的高质量致密双星并合搜索，通过顺序卷积神经网络实现异常检测、毛刺分类和相干性测试，在第三和第四次观测运行中报告47个引力波探测，表明其可作为高信噪比高质量区域匹配滤波的独立补充通道。
AI 中文摘要
我们展示了MADGRAV的结果，这是一种基于深度学习的高质量致密双星并合搜索方法，应用于LIGO干涉仪在第三次观测运行以及第四次观测运行第一和第二部分期间收集的数据。MADGRAV管道由一系列顺序卷积神经网络组成，执行异常检测、毛刺分类、相干性测试和信号排序。通过1秒Q变换窗口，对LIGO的Hanford和Livingston探测器的数据（单独及相干地）进行研究。在通过管道每个阶段的候选事件中，有48个达到显著性阈值，我们报告了47个引力波探测，其特征是误报率低于$1\\,{\rm yr}^{-1}$，天体物理起源概率$p_{\rm astro}>0.9$。在这47个探测中，有44个与最小建模的相干WaveBurst搜索共享。从官方引力波瞬态目录中提取的观测到的总源帧质量在$14-236 M_{\odot}$范围内，中位数为$69 M_{\odot}$，中位信噪比为16。我们注意到，确信探测的恢复比例随质量增加而上升：对于LIGO探测器网络信噪比$>10$，管道恢复低于$30 M_{\odot}$的目录事件的$8.1\\%$，在$30$到$100 M_{\odot}$之间为$39.8\\%$，高于$100 M_{\odot}$为$53.3\\%$，对应于相干WaveBurst在同一区间检测到的事件的$33.3\\%$、$45.5\\%$和$53.3\\%$。这些结果表明，异常检测管道可以作为高信噪比高质量区域中匹配滤波的独立补充探测通道。
英文摘要
We present the results of \textbf{MADGRAV}, a deep-learning-based search for high-mass compact binary coalescences, applied to the data collected by the LIGO interferometers during the third observing run and during the first and second part of the fourth observing run. The \textbf{MADGRAV} pipeline consists of a series of sequential convolutional neural networks that perform anomaly detection, glitch classification, coherence testing, and signal ranking. Data from the Hanford and Livingston LIGO detectors are studied (both individually and in coherence) by way of 1 second Q-transform windows. Of the candidates that survive every stage of the pipeline, 48 reach the significance threshold, and we report 47 gravitational wave detections characterised by a false alarm rate below $1\,{\rm yr}^{-1}$ with a probability of astrophysical origin $p_{\rm astro}>0.9$. Of the 47 detections, 44 are shared with the minimally modelled coherent WaveBurst search. The observed total source-frame masses, extracted from official gravitational wave transient catalogues, are in the $14-236 M_{\odot}$ range with a median of $69 M_{\odot}$, and a median SNR of 16. We note that the recovered fraction of confident detections rises with mass: for LIGO detectors network SNR $>10$ the pipeline recovers $8.1\%$ of confident catalog events below $30 M_{\odot}$, $39.8\%$ between $30$ and $100 M_{\odot}$, and $53.3\%$ above $100 M_{\odot}$, corresponding to $33.3\%$, $45.5\%$ and $53.3\%$ of the events detected by coherent WaveBurst in the same bins. These results suggest that anomaly detection pipelines can serve as an independent detection channel complementary to matched filtering in the high-mass high-SNR regime.
Comments16 pages, 6 figures, submitted to CQG
