大核卷积神经网络用于连续引力波宽参数空间搜索
Large-kernel Convolutional Neural Networks for Wide Parameter-Space Searches of Continuous Gravitational Waves
AI总结：
本文提出大核卷积神经网络架构，用于连续引力波宽参数空间搜索，在多个基准案例中灵敏度优于现有方法，并验证了单一网络覆盖全频带的可行性。
摘要：
宽参数空间连续引力波（CWs）搜索的灵敏度受限于其高昂的计算成本。深度学习正被研究作为替代方法，以取代连续引力波搜索的各个方面。在先前的工作 arXiv:2305.01057[gr-qc] 中，提出了用于连续引力波搜索的深度神经网络（DNN）的新设计原则，并训练了此类 DNN 以执行具有匹配滤波灵敏度的定向搜索。在本文中，我们调整这些设计原则，构建了一个用于在来自两个探测器（H1 和 L1）的 10 天数据中进行宽参数空间搜索的 DNN 架构。我们针对每个基准案例训练一个 DNN：在 20 - 1000 Hz 搜索频带内，六个全天搜索和八个不同频率的定向搜索。我们将结果与 Dreissigacker 和 Prix arXiv:2005.04140[gr-qc] 所达到的 DNN 灵敏度进行比较，发现我们训练的 DNN 在所有情况下都更灵敏。在检测概率上的绝对提升，全天搜索从 20 Hz 时的 6.5% 到 1000 Hz 时的 38%，定向搜索从 20 Hz 时的 1.5% 到 500 Hz 时的 59.4%。一个在 20 - 1000 Hz 整个搜索频带上训练的全天 DNN 在所有频率上都表现出高灵敏度，为训练单个 DNN 执行整个搜索提供了概念验证。我们还研究了 DNN 性能对不同信号幅度、频率的泛化能力，以及 DNN 灵敏度对天空位置的依赖性。
英文摘要：
The sensitivity of wide-parameter-space searches for continuous gravitational waves (CWs) is limited by their high computational cost. Deep learning is being studied as an alternative method to replace various aspects of a CW search. In previous work arXiv:2305.01057[gr-qc], new design principles were presented for deep neural network (DNN) search of CWs and such DNNs were trained to perform a targeted search with matched filtering sensitivity. In this paper, we adapt these design principles to build a DNN architecture for wide parameter-space searches in 10 days of data from two detectors (H1 and L1). We train a DNN for each of the benchmark cases: six all-sky searches and eight directed searches at different frequencies in the search band of 20 - 1000 Hz. We compare our results to the DNN sensitivity achieved from Dreissigacker and Prix arXiv:2005.04140[gr-qc] and find that our trained DNNs are more sensitive in all the cases. The absolute improvement in detection probability ranges from 6.5% at 20 Hz to 38% at 1000 Hz in the all-sky cases and from 1.5% at 20 Hz to 59.4% at 500 Hz in the directed cases. An all-sky DNN trained on the entire search band of 20 - 1000 Hz shows a high sensitivity at all frequencies providing a proof of concept for training a single DNN to perform the entire search. We also study the generalization of the DNN performance to signals with different signal amplitude, frequency and the dependence of the DNN sensitivity on sky position.
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。
