Template-free search for gravitational wave events using coincident anomaly detection
基于一致性异常检测的无模板引力波事件搜索
Gravitational wave (GW) observatories have used template-based search to detect hundreds of compact binary coalescences (CBCs). However, template-based search cannot detect astrophysical sources that lack accurate, computationally tractable waveform models. Here, we present a novel approach for template-free search using coincident anomaly detection (CoAD). CoAD requires neither labeled training examples nor background-only training sets, instead exploiting the coincidence of events across spatially separated detectors as the training loss itself: two neural networks independently analyze data from each detector and are trained to maximize coincident predictions. Additionally, we show that integrated gradient analysis can localize GW signals from the neural network weights, providing a path toward data-driven template construction of unmodeled sources and further improving precision by frequency matching. Using the Codabench dataset of real LIGO backgrounds with injected simulated CBCs and sine-Gaussian low-frequency bursts, CoAD achieves recall up to 0.91 and 0.85, respectively, at a false-alarm rate of one event per year and achieves recall above 0.5 at signal-to-noise ratios below 10. The fully unsupervised nature of CoAD makes it especially well suited for next-generation detectors with greater sensitivity and associated increases in GW event rates.
展开 ▾无需背景训练集或模拟信号,利用汉福德与利文斯顿探测器符合训练网络,结合积分梯度可定位信号并提升精度,对 BBH 和 SGLF 事件在 1 个/年虚警率下召回达 0.91 和 0.85。
当前引力波搜索主要依赖模板匹配 Abac+ 2025,但对无精确波形模型的源(如核坍缩超新星 Dimmelmeier+ 2008)难以奏效。传统无模板方法包括 cWB Klimenko+ 2008、BayesWave Cornish+ 2021 以及基于自编码器的异常检测 Raikman+ 2024,但多需背景训练集或对信号作假设。本文提出的 CoAD 源自前期工作 Humble+ 2024,将符合性直接作为损失函数,完全无监督且不依赖模拟,与 MLy Skliris+ 2024 以相关性作为输入的方式根本不同。CoAD 在高事件率场景下优势显著,尤其适合下一代探测器如爱因斯坦望远镜 Maggiore+ 2020 和宇宙探索者 Reitze+ 2019,未来可结合物理信息网络直接重构波形模板,其无监督符合学习思想亦可推广至暗物质探测 Amaral+ 2025 等多探测器物理搜索。
预印本 2026-01-17 · 刊出 2026-06-12 · 收录 2026-10-12