{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:58Z","timestamp":1772137918227,"version":"3.50.1"},"reference-count":62,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"tdm","delay-in-days":2,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006224","name":"Argonne National Laboratory","doi-asserted-by":"crossref","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100006224","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007523","name":"Division of Advanced Cyberinfrastructure","doi-asserted-by":"crossref","award":["OAC-1931561"],"award-info":[{"award-number":["OAC-1931561"]}],"id":[{"id":"10.13039\/100007523","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"Abstract<\/jats:title>\n \n We present a new class of AI models for the detection of quasi-circular, spinning, non-precessing binary black hole mergers whose waveforms include the higher order gravitational wave modes\n \n \n \n <\/jats:tex-math>\n \n \n (<\/mml:mo>\n \u2113<\/mml:mi>\n ,<\/mml:mo>\n \n |<\/mml:mo>\n <\/mml:mrow>\n m<\/mml:mi>\n \n |<\/mml:mo>\n <\/mml:mrow>\n )<\/mml:mo>\n =<\/mml:mo>\n {<\/mml:mo>\n (<\/mml:mo>\n 2<\/mml:mn>\n ,<\/mml:mo>\n 2<\/mml:mn>\n )<\/mml:mo>\n ,<\/mml:mo>\n (<\/mml:mo>\n 2<\/mml:mn>\n ,<\/mml:mo>\n 1<\/mml:mn>\n )<\/mml:mo>\n ,<\/mml:mo>\n (<\/mml:mo>\n 3<\/mml:mn>\n ,<\/mml:mo>\n 3<\/mml:mn>\n )<\/mml:mo>\n ,<\/mml:mo>\n (<\/mml:mo>\n 3<\/mml:mn>\n ,<\/mml:mo>\n 2<\/mml:mn>\n )<\/mml:mo>\n ,<\/mml:mo>\n (<\/mml:mo>\n 4<\/mml:mn>\n ,<\/mml:mo>\n 4<\/mml:mn>\n )<\/mml:mo>\n }<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n , and mode mixing effects in the\n \n \n \n <\/jats:tex-math>\n \n \n \u2113<\/mml:mi>\n =<\/mml:mo>\n 3<\/mml:mn>\n ,<\/mml:mo>\n \n |<\/mml:mo>\n <\/mml:mrow>\n m<\/mml:mi>\n \n |<\/mml:mo>\n <\/mml:mrow>\n =<\/mml:mo>\n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n harmonics. These AI models combine hybrid dilated convolution neural networks to accurately model both short- and long-range temporal sequential information of gravitational waves; and graph neural networks to capture spatial correlations among gravitational wave observatories to consistently describe and identify the presence of a signal in a three detector network encompassing the Advanced LIGO and Virgo detectors. We first trained these spatiotemporal-graph AI models using synthetic noise, using 1.2 million modeled waveforms to densely sample this signal manifold, within 1.7 h using 256 NVIDIA A100 GPUs in the Polaris supercomputer at the Argonne Leadership Computing Facility. This distributed training approach exhibited optimal classification performance, and strong scaling up to 512 NVIDIA A100 GPUs. With these AI ensembles we processed data from a three detector network, and found that an ensemble of 4 AI models achieves state-of-the-art performance for signal detection, and reports two misclassifications for every decade of searched data. We distributed AI inference over 128 GPUs in the Polaris supercomputer and 128 nodes in the Theta supercomputer, and completed the processing of a decade of gravitational wave data from a three detector network within 3.5 h. Finally, we fine-tuned these AI ensembles to process the entire month of February 2020, which is part of the O3b LIGO\/Virgo observation run, and found 6 gravitational waves, concurrently identified in Advanced LIGO and Advanced Virgo data, and zero false positives. This analysis was completed in one hour using one NVIDIA A100 GPU.\n <\/jats:p>","DOI":"10.1088\/2632-2153\/ad4c37","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T18:40:59Z","timestamp":1715798459000},"page":"025056","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8009-9116","authenticated-orcid":true,"given":"Minyang","family":"Tian","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9682-3604","authenticated-orcid":true,"given":"E A","family":"Huerta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-9552","authenticated-orcid":true,"given":"Huihuo","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Prayush","family":"Kumar","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"mlstad4c37bib1","doi-asserted-by":"publisher","first-page":"L12","DOI":"10.3847\/2041-8213\/aa91c9","volume":"848","author":"Abbott","year":"2017","journal-title":"Astrophys. J. Lett."},{"key":"mlstad4c37bib2","author":"Evans","year":"2021"},{"key":"mlstad4c37bib3","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1038\/s42254-021-00303-8","volume":"3","author":"Bailes","year":"2021","journal-title":"Nat. Rev. Phys."},{"key":"mlstad4c37bib4","doi-asserted-by":"publisher","first-page":"JCAP03(2020)050","DOI":"10.1088\/1475-7516\/2020\/03\/050","author":"Maggiore","year":"2020","journal-title":"J. Cosmol. Astropart. Phys."},{"key":"mlstad4c37bib5","doi-asserted-by":"publisher","DOI":"10.1088\/0264-9381\/33\/21\/215004","volume":"33","author":"Usman","year":"2016","journal-title":"Class. Quantum Grav."},{"key":"mlstad4c37bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2021.100680","volume":"14","author":"Cannon","year":"2021","journal-title":"SoftwareX"},{"key":"mlstad4c37bib7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.97.044039","volume":"97","author":"George","year":"2018","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib8","article-title":"Deep learning for real-time gravitational wave detection and parameter estimation with LIGO data","author":"George","year":"2017"},{"key":"mlstad4c37bib9","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.physletb.2017.12.053","volume":"778","author":"George","year":"2018","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.141103","volume":"120","author":"Gabbard","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstad4c37bib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.103.063034","volume":"103","author":"Lin","year":"2021","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.104003","volume":"101","author":"Wang","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib13","doi-asserted-by":"publisher","DOI":"10.1007\/s11433-018-9321-7","volume":"62","author":"Fan","year":"2019","journal-title":"Sci. China Phys. Mech. Astron."},{"key":"mlstad4c37bib14","doi-asserted-by":"publisher","DOI":"10.1007\/s11467-020-0966-4","volume":"15","author":"Li","year":"2020","journal-title":"Front. Phys."},{"key":"mlstad4c37bib15","doi-asserted-by":"publisher","first-page":"13859","DOI":"10.1007\/s00521-021-06024-4","volume":"33","author":"Deighan","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"mlstad4c37bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.100.044025","volume":"100","author":"Rebei","year":"2019","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.064009","volume":"101","author":"Beheshtipour","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.043003","volume":"105","author":"Sch\u00e4fer","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.043002","volume":"105","author":"Sch\u00e4fer","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/s41550-022-01651-w","volume":"6","author":"Gunny","year":"2022","journal-title":"Nat. Astron."},{"key":"mlstad4c37bib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.107.023021","volume":"107","author":"Sch\u00e4fer","year":"2023","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib22","author":"Andrews","year":"2022"},{"key":"mlstad4c37bib23","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.811563","volume":"5","author":"Yu","year":"2022","journal-title":"Front. Artif. Intell."},{"key":"mlstad4c37bib24","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac5435","volume":"3","author":"Moreno","year":"2022","journal-title":"Mach. Learn. Sci. Tech."},{"key":"mlstad4c37bib25","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1017\/S1743921320003981","volume":"15","author":"Nemmen","year":"2019","journal-title":"Proc. Int. Astron. Union"},{"key":"mlstad4c37bib26","doi-asserted-by":"publisher","first-page":"2150154","DOI":"10.1142\/S0219887821501541","volume":"18","author":"\u00d6vg\u00fcn","year":"2021","journal-title":"Int. J. Geom. Methods Mod. Phys."},{"key":"mlstad4c37bib27","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/124\/50002","volume":"124","author":"Arraut","year":"2018","journal-title":"Europhys. Lett."},{"key":"mlstad4c37bib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2020.135330","volume":"803","author":"Krastev","year":"2020","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.102.063015","volume":"102","author":"Sch\u00e4fer","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.100.062005","volume":"100","author":"Miller","year":"2019","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2021.136185","volume":"816","author":"Wei","year":"2021","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.104.062004","volume":"104","author":"Yu","year":"2021","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2023.137850","volume":"840","author":"Qiu","year":"2023","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib34","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3847\/1538-4357\/ac1121","volume":"919","author":"Wei","year":"2021","journal-title":"Astrophys. J."},{"key":"mlstad4c37bib35","first-page":"p 47","article-title":"Advances in machine and deep learning for modeling and real-time detection of multi-messenger sources","author":"Huerta","year":"2021"},{"key":"mlstad4c37bib36","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1038\/s42254-019-0097-4","volume":"1","author":"Huerta","year":"2019","journal-title":"Nat. Rev. Phys."},{"key":"mlstad4c37bib37","first-page":"pp 193","article-title":"Machine learning in cosmology and gravitational wave astronomy: recent trends","volume":"vol 22","author":"Burgazli","year":"2022"},{"key":"mlstad4c37bib38","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abb93a","volume":"2","author":"Cuoco","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad4c37bib39","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s40537-020-00361-2","volume":"7","author":"Huerta","year":"2020","journal-title":"J. Big Data"},{"key":"mlstad4c37bib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2020.135628","volume":"808","author":"Khan","year":"2020","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2022.137505","volume":"835","author":"Khan","year":"2022","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib42","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2020.136029","volume":"812","author":"Wei","year":"2021","journal-title":"Phys. Lett. B"},{"key":"mlstad4c37bib43","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1038\/s41550-021-01405-0","volume":"5","author":"Huerta","year":"2021","journal-title":"Nat. Astron."},{"key":"mlstad4c37bib44","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.828672","volume":"5","author":"Chaturvedi","year":"2022","journal-title":"Front. Artif. Intell."},{"key":"mlstad4c37bib45","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6382\/aab793","volume":"35","author":"Razzano","year":"2018","journal-title":"Class. Quantum Grav."},{"key":"mlstad4c37bib46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.103.123023","volume":"103","author":"Lee","year":"2021","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib47","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2019.135081","volume":"B800","author":"Wei","year":"2020","journal-title":"Phys. Lett."},{"key":"mlstad4c37bib48","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.103.104056","volume":"103","author":"Pratten","year":"2021","journal-title":"Phys. Rev. D"},{"key":"mlstad4c37bib49","doi-asserted-by":"crossref","first-page":"29","DOI":"10.3847\/1538-4365\/acdc9f","volume":"267","author":"(KAGRA, VIRGO, LIGO Scientific)","year":"2023","journal-title":"Astrophys. J. Suppl."},{"key":"mlstad4c37bib50","article-title":"PyCBC. free and open software to study gravitational waves","author":"Nitz","year":"2021"},{"key":"mlstad4c37bib51","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/610\/1\/012021","volume":"610","author":"Vallisneri","year":"2015","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstad4c37bib52","author":"(LIGO Scientific, VIRGO, KAGRA)","year":"2021"},{"key":"mlstad4c37bib53","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.93.044007","volume":"D93","author":"Khan","year":"2016","journal-title":"Phys. Rev."},{"key":"mlstad4c37bib54","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s41114-020-00026-9","volume":"23","author":"Abbott","year":"2020","journal-title":"Living Rev. Relativ."},{"key":"mlstad4c37bib55","article-title":"Noise curves used for simulations in the update of the observing scenarios","author":"LIGO Document Control Center Portal","year":"2022"},{"key":"mlstad4c37bib56","first-page":"p 125","article-title":"WaveNet: a generative model for raw audio","author":"van den Oord","year":"2016"},{"key":"mlstad4c37bib57","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2014"},{"key":"mlstad4c37bib58","first-page":"pp 1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"mlstad4c37bib59","article-title":"Inductive representation learning on large graphs","volume":"vol 30","author":"Hamilton","year":"2017"},{"key":"mlstad4c37bib60","first-page":"10","volume":"1050","author":"Velickovic","year":"2017","journal-title":"Stat"},{"key":"mlstad4c37bib61","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2019"},{"key":"mlstad4c37bib62","article-title":"Physics-inspired spatiotemporal-graph AI ensemble for gravitational wave detection","author":"Minyang","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T23:36:45Z","timestamp":1717371405000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4c37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":62,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6,3]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad4c37","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD4C37\/v1\/decision1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,1]]},"assertion":[{"value":"Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-02-02","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-15","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-03","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}