Neural network-based search for unmodeled transients in LIGO-Virgo-KAGRA's third observing run
基于神经网络的LIGO-Virgo-KAGRA第三次观测运行无模板瞬变引力波搜索
This paper presents the results of a neural network (NN)-based search for short-duration gravitational-wave transients in data from the third observing run of LIGO, Virgo, and KAGRA. The search targets unmodeled transients with durations of milliseconds to a few seconds in the 30--1500 Hz frequency band, without assumptions about the incoming signal direction, polarization, or morphology. Using the gravitational wave anomalous knowledge (GWAK) method, three compact binary coalescences (CBCs) identified by existing pipelines are successfully detected, and a range of detector glitches are identified. The algorithm constructs a low-dimensional embedded space to capture the physical features of signals, enabling the detection of CBCs, detector glitches, and unmodeled transients. This study explores the potential of GWAK to generalize gravitational-wave searches and complement existing pipelines and demonstrates sensitivity to several classes of simulated short-duration GW transients, including core-collapse supernovae and other modeled sources, which have not yet been observed.
展开 ▾首次将GWAK方法应用于完整O3数据开展无模板瞬变搜索,通过多自编码器嵌入空间与启发式模型有效抑制假警报,并成功处理传统分析丢弃的CAT2高故障数据,展现了AI在引力波数据挖掘中的独特潜力。
传统引力波瞬变探测主要依赖匹配滤波Allen+ 2012,但模板库限制了发现未知波形。无模板方法如cWBKlimenko+ 2008和BayesWaveCornish+ 2015打破了这一局限,而基于自编码器的异常检测方法Morawski+ 2021为进一步的无监督搜索提供了思路。作者此前提出的GWAK框架Raikman+ 2024通过半监督学习构建多维嵌入空间,将背景、故障和多种信号特征融合。本文将该方法首次应用于O3全量数据,并与官方无模板搜索结果LIGO Scientific+ 2021比对,在包含CAT2高故障时段的条件下仍能稳健检测已知CBC,表明该方法具有超越现有管线的泛化能力。展望未来,GWAK有望融入更多物理先验并优化计算效率,在即将到来的第四观测运行中捕捉核心坍缩超新星等未建模瞬变信号,开启数据驱动的引力波天文学新途径。
预印本 2024-12-27 · 刊出 2025-07-15 · 收录 2026-10-12