First machine learning gravitational-wave search mock data challenge

doi:10.1103/PhysRevD.107.023021

CORC > 理论物理研究所 > 中国科学院理论物理研究所 > 理论物理所科研产出 > 理论物理所1978-2010年知识产出

	First machine learning gravitational-wave search mock data challenge
	Schaefer, Marlin B.; Zelenka, Ondrej 2,3; Nitz, Alexander H.; Wang, He ; Wu, Shichao 1; Guo, Zong-Kuan ; Cao, Zhoujian 5; Ren, Zhixiang 6; Nousi, Paraskevi 7; Stergioulas, Nikolaos
刊名	PHYSICAL REVIEW D
	2023
卷号	107 期号:2 页码:23021
关键词	PUBLIC ADVANCED LIGO BINARY MERGERS CATALOG
ISSN号	2470-0010
DOI	10.1103/PhysRevD.107.023021
英文摘要	We present the results of the first Machine Learning Gravitational-Wave Search Mock Data Challenge. For this challenge, participating groups had to identify gravitational-wave signals from binary black hole mergers of increasing complexity and duration embedded in progressively more realistic noise. The final of the 4 provided datasets contained real noise from the O3a observing run and signals up to a duration of 20 s with the inclusion of precession effects and higher order modes. We present the average sensitivity distance and run-time for the 6 entered algorithms derived from 1 month of test data unknown to the participants prior to submission. Of these, 4 are machine learning algorithms. We find that the best machine learning based algorithms are able to achieve up to 95% of the sensitive distance of matched-filtering based production analyses for simulated Gaussian noise at a false-alarm rate (FAR) of one per month. In contrast, for real noise, the leading machine learning search achieved 70%. For higher FARs the differences in sensitive distance shrink to the point where select machine learning submissions outperform traditional search algorithms at FARs >= 200 per month on some datasets. Our results show that current machine learning search algorithms may already be sensitive enough in limited parameter regions to be useful for some production settings. To improve the state-of-the-art, machine learning algorithms need to reduce the false-alarm rates at which they are capable of detecting signals and extend their validity to regions of parameter space where modeled searches are computationally expensive to run. Based on our findings we compile a list of research areas that we believe are the most important to elevate machine learning searches to an invaluable tool in gravitational-wave signal detection.
学科主题	Astronomy & Astrophysics ; Physics
语种	英语
内容类型	期刊论文
源URL	[http://ir.itp.ac.cn/handle/311006/27981]
专题	理论物理研究所_理论物理所1978-2010年知识产出
作者单位	1.Albert Einstein Inst, Max Planck Inst Gravitat Phys, D-30167 Hannover, Germany 2.Leibniz Univ Hannover, D-30167 Hannover, Germany 3.Friedrich Schiller Univ Jena, D-07743 Jena, Germany 4.Michael Stifel Ctr Jena, D-07743 Jena, Germany 5.Chinese Acad Sci, Inst Theoret Phys, CAS Key Lab Theoret Phys, Beijing 100190, Peoples R China 6.Beijing Normal Univ, Dept Astron, Beijing 100875, Peoples R China 7.Peng Cheng Lab, Shenzhen 518055, Peoples R China 8.Aristotle Univ Thessaloniki, Dept Informat, GR-54124 Thessaloniki, Greece 9.Stergioulas, Nikolaos; Iosif, Panagiotis; Koloniari, Alexandra E.] Aristotle Univ Thessaloniki, Dept Phys, GR-54124 Thessaloniki, Greece 10.GSI Helmholtz Ctr Heavy Ion Res, Planckstr 1, D-64291 Darmstadt, Germany
推荐引用方式 GB/T 7714	Schaefer, Marlin B.,Zelenka, Ondrej,Nitz, Alexander H.,et al. First machine learning gravitational-wave search mock data challenge[J]. PHYSICAL REVIEW D,2023,107(2):23021.
APA	Schaefer, Marlin B..,Zelenka, Ondrej.,Nitz, Alexander H..,Wang, He.,Wu, Shichao.,...&Ohme, Frank.(2023).First machine learning gravitational-wave search mock data challenge.PHYSICAL REVIEW D,107(2),23021.
MLA	Schaefer, Marlin B.,et al."First machine learning gravitational-wave search mock data challenge".PHYSICAL REVIEW D 107.2(2023):23021.