arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.06266gr-qcastro-ph.IM
收藏

基于深度学习的双中子星并合搜索流水线

Binary Neutron Star Merger Search Pipeline Powered by Deep Learning

Alistair McLeod, Damon Beveridge, Linqing Wen, Andreas Wicenec

AI总结:

本研究提出基于卷积神经网络的双中子星并合深度学习搜索流水线,通过信噪比时间序列检测提升鲁棒性,灵敏度与现有离线流水线相当,误报率为每2个月1次时探测数提升12%,还成功检出两例已知并合事件。

摘要:

引力波如今已能从致密双体并合事件中被常规探测到,其中双中子星并合事件因已被观测到会产生电磁对应体,在多信使天文学中备受关注。针对这类并合事件的新型搜索流水线既能提升综合搜索灵敏度,也能增强在存在数据突变(glitch)和非平稳探测器噪声的情况下探测真实引力波信号的能力。深度学习已在引力波数据分析的其他领域取得成功,但由于双中子星并合的信号长度较长,构建高灵敏度的基于深度学习的双中子星并合搜索方法一直难以实现。在本研究中,我们提出了一种用于探测双中子星并合事件的深度学习流水线。通过训练卷积神经网络在信噪比时间序列中检测双中子星并合事件,我们将信号功率集中到比基于应变的方法更短、更一致的时间尺度上,同时还能训练网络对数据突变(glitch)具备鲁棒性。我们通过在真实引力波数据中注入模拟信号的方式,将该流水线的灵敏度与三种离线探测流水线进行了对比,发现在每2个月1次的探测阈值以下,我们的流水线灵敏度与现有流水线相当。此外,我们发现在每2个月1次的误报率下,该流水线能将双中子星并合事件的总探测数量提升12%。该流水线还成功探测到了LIGO-Virgo-KAGRA合作组迄今发现的两例双中子星并合事件——GW170817和GW190425,尽管GW170817事件中存在强数据突变(glitch)。

英文摘要:

Gravitational waves are now routinely detected from compact binary mergers, with binary neutron star mergers being of note for multi-messenger astronomy as they have been observed to produce electromagnetic counterparts. Novel search pipelines for these mergers could increase the combined search sensitivity, and could improve the ability to detect real gravitational wave signals in the presence of glitches and non-stationary detector noise. Deep learning has found success in other areas of gravitational wave data analysis, but a sensitive deep learning-based search for binary neutron star mergers has proven elusive due to their long signal length. In this work, we present a deep learning pipeline for detecting binary neutron star mergers. By training a convolutional neural network to detect binary neutron star mergers in the signal-to-noise ratio time series, we concentrate signal power into a shorter and more consistent timescale than strain-based methods, while also being able to train our network to be robust against glitches. We compare our pipeline's sensitivity to the three offline detection pipelines using injections in real gravitational wave data, and find that our pipeline has a comparable sensitivity to the current pipelines below the 1 per 2 months detection threshold. Furthermore, we find that our pipeline can increase the total number of binary neutron star detections by 12% at a false alarm rate of 1 per 2 months. The pipeline is also able to successfully detect the two binary neutron star mergers detected so far by the LIGO-Virgo-KAGRA collaboration, GW170817 and GW190425, despite the loud glitch present in GW170817.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑