Scalable early warning for binary neutron-star mergers in third-generation gravitational-wave detectors
第三代引力波探测器中双中子星并合的规模化预警
Third-generation gravitational-wave observatories will observe binary neutron-star coalescences for hours before merger. Over these extended time windows, Earth's motion and the long signal durations make standard search methods computationally demanding for low-latency detection. We propose an approach based on short-time Fourier transforms and convolutional neural networks that implicitly marginalizes over extrinsic parameters, effectively reducing the search to the chirp mass. The network learns the signals' nonlinear time-frequency morphology, approximating the optimal Bayesian detection statistic. Using a large-scale campaign of simulated signal injections, we compare the network's performance with a GPU-optimized matched-filtering baseline for both the ET$Δ$ and ET2L configurations of the Einstein Telescope and signal durations from approximately 25 minutes ($f_{\rm min} = 5$ Hz) to approximately 6 hours ($f_{\rm min} = 2$ Hz). The network achieves comparable detection sensitivity while reducing computational costs by over four orders of magnitude, bringing processing times from minutes to milliseconds. This efficiency paves the way for rapid early-warning alerts for multi-messenger astronomy in the third-generation detector era.
展开 ▾不让神经网络端到端替代物理建模,而是只让它承担最难的外禀参数边缘化,把探测统计量化为离线求解一次的变分问题:模板数由 10^7 降到 10^3,评估延迟由分钟级降到毫秒级,仍能保留匹配滤波 ≥86% 的灵敏视界。
第三代探测器把双中子星的可观测时间拉长到小时量级,地球自转与公转带来的振幅、相位调制使短信号近似失效,搜索空间必须扩入天区、偏振等外禀参数 Jaranowski+ 1998 Chen & Johnson-McDaniel 2024,模板数随维度爆炸,直接威胁低延迟预警与多信使科学 Hu & Veitch 2025。已有深度学习方案中,端到端分类器在长信号下须隐式学习高维参数空间、易引入学习偏差 Gabbard+ 2018 Nagarajan+ 2025,另一些工作则只把机器学习用于中间数据产品的后处理 Yamamoto & Tanaka 2021 Modafferi+ 2023,少数双中子星预警尝试也只处理几分钟的数据帧 Baltus+ 2022。本文承接基于 SFT 的贝叶斯检测统计量框架 Tenorio+ 2025 Tenorio & Gerosa 2025,把原本不可解的边缘化积分转成只需离线求解一次的变分问题,仅对啁啾质量做模板最大化,从而在保持灵敏度的同时把计算量压低四个量级以上。展望来看,这种“物理建模+学习型边缘化”的混合范式有望推广到 Cosmic Explorer 等其他 3G 装置乃至其他长信号源,但走向实用还需解决非平稳噪声与 glitch 的鲁棒性,以及长观测窗下事件重叠概率升高带来的多信号分离问题 Samajdar+ 2021 Papalini+ 2025。
预印本 2026-11-06 · 收录 2026-11-10