The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning

One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This endeavor presents a significant challenge due to the complex and lengthy EMRI signals, further compounded by their inherently faint nature. In this letter, we intr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yun, Qianyun, Han, Wen-Biao, Guo, Yi-Yang, Wang, He, Du, Minghui
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Yun, Qianyun
Han, Wen-Biao
Guo, Yi-Yang
Wang, He
Du, Minghui
description One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This endeavor presents a significant challenge due to the complex and lengthy EMRI signals, further compounded by their inherently faint nature. In this letter, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors, achieving a true positive rate (TPR) of 96.9 % at a 1 % false positive rate (FPR) for signal-to-noise ratio (SNR) from 50 to 100. Especially, the key intrinsic parameters of EMRIs such as mass and spin of the supermassive black hole (SMBH) and the initial eccentricity of the orbit can be inferred directly by employing a VGG network. The mass and spin of the SMBH can be determined at 99 % and 92 % respectively. This will greatly reduce the parameter spaces and computing cost for the following Bayesian parameter estimation. Our model also has a low dependency on the accuracy of the waveform model. This study underscores the potential of deep learning methods in EMRI data analysis, enabling the rapid detection of EMRI signals and efficient parameter estimation .
doi_str_mv 10.48550/arxiv.2311.18640
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2311_18640</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2311_18640</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-c8ddfbbf18fb239bd83d1c379820673379cd141975211c210ca934b6722d24ff3</originalsourceid><addsrcrecordid>eNotj8tOwzAQRb1hgQofwAp_QBM8dh7OElW8pEpsso_G9ri11KSRHUH5e9zAaq7mjK7mMPYAoqx0XYsnjJfwVUoFUIJuKnHLqD8Sd7SQXcJ52nK6LBHXzHFyfMaIY6aRU1rCiCs4-_WMRipGTKmI1zUPU5pDxFPi32E55k6a-YkwTmE63LEbnwnd_88N619f-t17sf98-9g97wtsWlFY7Zw3xoP2RqrOOK0cWNV2WoqmVTlYBxV0bS0BrARhsVOVaVopnay8Vxv2-Fe7eg5zzB_Hn-HqO6y-6hdhY1HX</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning</title><source>arXiv.org</source><creator>Yun, Qianyun ; Han, Wen-Biao ; Guo, Yi-Yang ; Wang, He ; Du, Minghui</creator><creatorcontrib>Yun, Qianyun ; Han, Wen-Biao ; Guo, Yi-Yang ; Wang, He ; Du, Minghui</creatorcontrib><description>One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This endeavor presents a significant challenge due to the complex and lengthy EMRI signals, further compounded by their inherently faint nature. In this letter, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors, achieving a true positive rate (TPR) of 96.9 % at a 1 % false positive rate (FPR) for signal-to-noise ratio (SNR) from 50 to 100. Especially, the key intrinsic parameters of EMRIs such as mass and spin of the supermassive black hole (SMBH) and the initial eccentricity of the orbit can be inferred directly by employing a VGG network. The mass and spin of the SMBH can be determined at 99 % and 92 % respectively. This will greatly reduce the parameter spaces and computing cost for the following Bayesian parameter estimation. Our model also has a low dependency on the accuracy of the waveform model. This study underscores the potential of deep learning methods in EMRI data analysis, enabling the rapid detection of EMRI signals and efficient parameter estimation .</description><identifier>DOI: 10.48550/arxiv.2311.18640</identifier><language>eng</language><subject>Physics - General Relativity and Quantum Cosmology ; Physics - Instrumentation and Methods for Astrophysics</subject><creationdate>2023-11</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2311.18640$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2311.18640$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Yun, Qianyun</creatorcontrib><creatorcontrib>Han, Wen-Biao</creatorcontrib><creatorcontrib>Guo, Yi-Yang</creatorcontrib><creatorcontrib>Wang, He</creatorcontrib><creatorcontrib>Du, Minghui</creatorcontrib><title>The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning</title><description>One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This endeavor presents a significant challenge due to the complex and lengthy EMRI signals, further compounded by their inherently faint nature. In this letter, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors, achieving a true positive rate (TPR) of 96.9 % at a 1 % false positive rate (FPR) for signal-to-noise ratio (SNR) from 50 to 100. Especially, the key intrinsic parameters of EMRIs such as mass and spin of the supermassive black hole (SMBH) and the initial eccentricity of the orbit can be inferred directly by employing a VGG network. The mass and spin of the SMBH can be determined at 99 % and 92 % respectively. This will greatly reduce the parameter spaces and computing cost for the following Bayesian parameter estimation. Our model also has a low dependency on the accuracy of the waveform model. This study underscores the potential of deep learning methods in EMRI data analysis, enabling the rapid detection of EMRI signals and efficient parameter estimation .</description><subject>Physics - General Relativity and Quantum Cosmology</subject><subject>Physics - Instrumentation and Methods for Astrophysics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAQRb1hgQofwAp_QBM8dh7OElW8pEpsso_G9ri11KSRHUH5e9zAaq7mjK7mMPYAoqx0XYsnjJfwVUoFUIJuKnHLqD8Sd7SQXcJ52nK6LBHXzHFyfMaIY6aRU1rCiCs4-_WMRipGTKmI1zUPU5pDxFPi32E55k6a-YkwTmE63LEbnwnd_88N619f-t17sf98-9g97wtsWlFY7Zw3xoP2RqrOOK0cWNV2WoqmVTlYBxV0bS0BrARhsVOVaVopnay8Vxv2-Fe7eg5zzB_Hn-HqO6y-6hdhY1HX</recordid><startdate>20231130</startdate><enddate>20231130</enddate><creator>Yun, Qianyun</creator><creator>Han, Wen-Biao</creator><creator>Guo, Yi-Yang</creator><creator>Wang, He</creator><creator>Du, Minghui</creator><scope>GOX</scope></search><sort><creationdate>20231130</creationdate><title>The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning</title><author>Yun, Qianyun ; Han, Wen-Biao ; Guo, Yi-Yang ; Wang, He ; Du, Minghui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-c8ddfbbf18fb239bd83d1c379820673379cd141975211c210ca934b6722d24ff3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Physics - General Relativity and Quantum Cosmology</topic><topic>Physics - Instrumentation and Methods for Astrophysics</topic><toplevel>online_resources</toplevel><creatorcontrib>Yun, Qianyun</creatorcontrib><creatorcontrib>Han, Wen-Biao</creatorcontrib><creatorcontrib>Guo, Yi-Yang</creatorcontrib><creatorcontrib>Wang, He</creatorcontrib><creatorcontrib>Du, Minghui</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yun, Qianyun</au><au>Han, Wen-Biao</au><au>Guo, Yi-Yang</au><au>Wang, He</au><au>Du, Minghui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning</atitle><date>2023-11-30</date><risdate>2023</risdate><abstract>One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This endeavor presents a significant challenge due to the complex and lengthy EMRI signals, further compounded by their inherently faint nature. In this letter, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors, achieving a true positive rate (TPR) of 96.9 % at a 1 % false positive rate (FPR) for signal-to-noise ratio (SNR) from 50 to 100. Especially, the key intrinsic parameters of EMRIs such as mass and spin of the supermassive black hole (SMBH) and the initial eccentricity of the orbit can be inferred directly by employing a VGG network. The mass and spin of the SMBH can be determined at 99 % and 92 % respectively. This will greatly reduce the parameter spaces and computing cost for the following Bayesian parameter estimation. Our model also has a low dependency on the accuracy of the waveform model. This study underscores the potential of deep learning methods in EMRI data analysis, enabling the rapid detection of EMRI signals and efficient parameter estimation .</abstract><doi>10.48550/arxiv.2311.18640</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2311.18640
ispartof
issn
language eng
recordid cdi_arxiv_primary_2311_18640
source arXiv.org
subjects Physics - General Relativity and Quantum Cosmology
Physics - Instrumentation and Methods for Astrophysics
title The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T19%3A23%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20detection,%20extraction%20and%20parameter%20estimation%20of%20extreme-mass-ratio%20inspirals%20with%20deep%20learning&rft.au=Yun,%20Qianyun&rft.date=2023-11-30&rft_id=info:doi/10.48550/arxiv.2311.18640&rft_dat=%3Carxiv_GOX%3E2311_18640%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true