{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T04:12:01Z","timestamp":1742271121320,"version":"3.40.1"},"reference-count":54,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Nuclear Physics Program of the National Science Foundation","award":["PHY- 1812374"],"award-info":[{"award-number":["PHY- 1812374"]}]},{"name":"Department of Energy, Office of Science, Office of Nuclear Physics","award":["DE-FG02- 97ER41041"],"award-info":[{"award-number":["DE-FG02- 97ER41041"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"Abstract<\/jats:title>\n Neutrinoless double-beta decay (\n \n \n \n 0<\/mml:mn>\n \u03bd<\/mml:mi>\n \u03b2<\/mml:mi>\n \u03b2<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>) is a rare nuclear process that, if observed, will provide insight into the nature of neutrinos and help explain the matter-antimatter asymmetry in the Universe. The large enriched germanium experiment for neutrinoless double-beta decay (LEGEND) will operate in two phases to search for \n \n \n \n 0<\/mml:mn>\n \u03bd<\/mml:mi>\n \u03b2<\/mml:mi>\n \u03b2<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>. The first (second) stage will employ 200 (1000) kg of High-Purity Germanium (HPGe) enriched in 76<\/jats:sup>Ge to achieve a half-life sensitivity of 1027<\/jats:sup> (1028<\/jats:sup>) years. In this study, we present a semi-supervised data-driven approach to remove non-physical events captured by HPGe detectors powered by a novel artificial intelligence model. We utilize affinity propagation to cluster waveform signals based on their shape and a support vector machine to classify them into different categories. We train, optimize, and test our model on data taken from a natural abundance HPGe detector installed in the Full Chain Test experimental stand at the University of North Carolina at Chapel Hill. We demonstrate that our model yields a maximum sacrifice of physics events of \n \n \n \n \n 0.024<\/mml:mn>\n \n \u2212<\/mml:mo>\n 0.003<\/mml:mn>\n <\/mml:mrow>\n \n +<\/mml:mo>\n 0.004<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msubsup>\n %<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula> after data cleaning. Our model is being used to accelerate data cleaning development for LEGEND-200 and will serve to improve data cleaning procedures for LEGEND-1000.<\/jats:p>","DOI":"10.1088\/2632-2153\/adbb37","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T22:54:16Z","timestamp":1740696856000},"page":"015064","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-powered data cleaning for LEGEND: a semi-supervised approach using affinity propagation and support vector machines"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0073-5512","authenticated-orcid":true,"given":"E","family":"Le\u00f3n","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4844-9339","authenticated-orcid":false,"given":"A","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7892-8691","authenticated-orcid":false,"given":"M A","family":"Bahena Schott","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5828-1745","authenticated-orcid":false,"given":"B","family":"Bos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9336-3937","authenticated-orcid":false,"given":"M","family":"Busch","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9815-2981","authenticated-orcid":false,"given":"J R","family":"Chapman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3047-478X","authenticated-orcid":false,"given":"G L","family":"Duran","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3777-2237","authenticated-orcid":true,"given":"J","family":"Gruszko","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8651-2960","authenticated-orcid":false,"given":"R","family":"Henning","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5008-1596","authenticated-orcid":false,"given":"E L","family":"Martin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0342-0217","authenticated-orcid":false,"given":"J F","family":"Wilkerson","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,3,17]]},"reference":[{"article-title":"LEGEND-1000 preconceptual design report","year":"2021","author":"Abgrall","key":"mlstadbb37bib1"},{"key":"mlstadbb37bib2","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.95.025002","article-title":"Toward the discovery of matter creation with neutrinoless \u03b2\u03b2 decay","volume":"95","author":"Agostini","year":"2023","journal-title":"Rev. Mod. Phys."},{"key":"mlstadbb37bib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.252502","article-title":"Final results of GERDA on the search for neutrinoless double-\u03b2 Decay","volume":"125","author":"Agostini","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstadbb37bib4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.130.062501","article-title":"Final result of the Majorana Demonstrator\u2019s search for neutrinoless double- \u03b2 decay in 76Ge","volume":"130","author":"Arnquist","year":"2023","journal-title":"Phys. Rev. Lett."},{"key":"mlstadbb37bib5","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/606\/1\/012005","article-title":"MAJORANA Collaboration\u2019s experience with germanium detectors","volume":"606","author":"Mertens","year":"2015","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadbb37bib6","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1140\/epjc\/s10052-014-3253-0","article-title":"Production, characterization and operation of 76 Ge enriched BEGe detectors in GERDA","volume":"75","author":"Agostini","year":"2015","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib7","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.nima.2011.10.008","article-title":"A novel HPGe detector for gamma-ray tracking and imaging","volume":"665","author":"Cooper","year":"2011","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstadbb37bib8","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1140\/epjc\/s10052-021-09184-8","article-title":"Characterization of inverted coaxial 76Ge detectors in GERDA for future double-\u03b2 decay experiments","volume":"81","author":"Agostini","year":"2021","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib9","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1016\/j.nima.2012.11.053","article-title":"Characterization of BEGe detectors in the HADES underground laboratory","volume":"718","author":"Andreotti","year":"2013","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstadbb37bib10","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1140\/epjc\/s10052-022-10884-y","article-title":"A novel wide-angle Compton Scanner setup to study bulk events in germanium detectors","volume":"82","author":"Abt","year":"2022","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib11","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/368\/1\/012047","article-title":"Off-line data processing and analysis for the GERDA experiment","volume":"368","author":"Agostini","year":"2012","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadbb37bib12","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1342\/1\/012123","article-title":"Data quality assurance for the Majorana Demonstrator","volume":"1342","author":"Myslik","year":"2020","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadbb37bib13","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1140\/epjc\/s10052-019-6869-2","article-title":"Deep learning based pulse shape discrimination for germanium detectors","volume":"79","author":"Holl","year":"2019","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevC.107.014321","article-title":"Interpretable boosted-decision-tree analysis for the Majorana Demonstrator","volume":"107","author":"Arnquist","year":"2023","journal-title":"Phys. Rev. C"},{"key":"mlstadbb37bib15","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1140\/epjc\/s10052-024-12980-7","article-title":"Generative models for simulation of KamLAND-Zen","volume":"84","author":"Zhenghao","year":"2024","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevC.107.014323","article-title":"KamNet: An integrated spatiotemporal deep neural network for rare event searches in KamLAND-Zen*","volume":"107","author":"Li","year":"2023","journal-title":"Phys. Rev. C"},{"key":"mlstadbb37bib17","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1134\/S1063778824010320","article-title":"Determination of dead layer parameters of semiconductor Germanium detectors using machine learning for the legend experiment","volume":"86","author":"Levashko","year":"2023","journal-title":"Phys. Atom. Nucl."},{"key":"mlstadbb37bib18","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1007\/s10909-022-02741-9","article-title":"Machine learning techniques for pile-up rejection in cryogenic calorimeters","volume":"209","author":"Fantini","year":"2022","journal-title":"J. Low Temp. Phys."},{"article-title":"Ad-hoc pulse shape simulation using cyclic positional U-Net","year":"2022","author":"Aobo","key":"mlstadbb37bib19"},{"key":"mlstadbb37bib20","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","article-title":"Clustering by passing messages between data points","volume":"315","author":"Frey","year":"2007","journal-title":"Science"},{"key":"mlstadbb37bib21","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"article-title":"AP-SVM data cleaning","year":"2024","author":"Le\u00f3n","key":"mlstadbb37bib22"},{"key":"mlstadbb37bib23","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.13693789","article-title":"Training and testing data for AP-SVM","author":"Le\u00f3n","year":"2024","journal-title":"Zenodo"},{"key":"mlstadbb37bib24","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/17\/05\/T05003","article-title":"The Majorana Demonstrator readout electronics system","volume":"17","author":"Abgrall","year":"2022","journal-title":"J. Instrum."},{"key":"mlstadbb37bib25","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1468\/1\/012113","article-title":"Signal readout electronics for LEGEND-200","volume":"1468","author":"Willers","year":"2020","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadbb37bib26","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/10\/01\/C01014","article-title":"FlashCam: a novel Cherenkov telescope camera with continuous signal digitization","volume":"10","author":"Gadola","year":"2015","journal-title":"J. Instrum."},{"key":"mlstadbb37bib27","article-title":"Object-oriented real-time control and acquisition","author":"Wilkerson","year":"2024","unstructured":"Wilkerson J F Howe M 2024 Object-oriented real-time control and acquisition (available at: https:\/\/github.com\/unc-enap\/Orca )"},{"key":"mlstadbb37bib28","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10614246","article-title":"pygama","author":"Agostini","year":"2024","unstructured":"Agostini M et al 2024 pygama 10.5281\/zenodo.10614246"},{"key":"mlstadbb37bib29","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10721223","article-title":"legend-daq2lh5","author":"Pertoldi","year":"2024","unstructured":"Pertoldi L Detwiler J Borden S Watkins S L Nave C Browning J Mathew T 2024 legend-daq2lh5 10.5281\/zenodo.10721223"},{"key":"mlstadbb37bib30","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10592107","article-title":"legend-pydataobj","author":"Detwiler","year":"2024","unstructured":"Detwiler J Pertoldi L Guinn I Song G Borden S Neuberger M Krause P Huber M 2024 legend-pydataobj 10.5281\/zenodo.10592107"},{"key":"mlstadbb37bib31","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10684779","article-title":"dspeed","author":"Guinn","year":"2024","unstructured":"Guinn I et al 2024 dspeed 10.5281\/zenodo.10684779"},{"key":"mlstadbb37bib32","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.phpro.2014.12.014","article-title":"A Dark Matter Search with MALBEK","volume":"61","author":"Giovanetti","year":"2015","journal-title":"Phys. Proc."},{"key":"mlstadbb37bib33","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1468\/1\/012040","article-title":"A low energy rare event search with the MAJORANA DEMONSTRATOR","volume":"1468","author":"Clint Wiseman and for the MAJORANA Collaboration","year":"2020","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadbb37bib34","doi-asserted-by":"publisher","DOI":"10.17615\/hj0v-8263","article-title":"A direct dark matter search with the Majorana low-background broad energy germanium detector","author":"Finnerty","year":"2013"},{"key":"mlstadbb37bib35","first-page":"pp 226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"vol 96","author":"Ester","year":"1996"},{"key":"mlstadbb37bib36","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/235968.233324","article-title":"Birch: an efficient data clustering method for very large databases","volume":"25","author":"Zhang","year":"1996","journal-title":"SIGMOD Rec."},{"key":"mlstadbb37bib37","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"year":"2006","author":"Rasmussen","key":"mlstadbb37bib38"},{"key":"mlstadbb37bib39","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"mlstadbb37bib40","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","article-title":"The perceptron: a probabilistic model for information storage and organization in the brain","volume":"65","author":"Rosenblatt","year":"1958","journal-title":"Psychol. Rev."},{"key":"mlstadbb37bib41","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1214\/009053607000000677","article-title":"Kernel methods in machine learning","volume":"36","author":"Hofmann","year":"2008","journal-title":"Ann. Stat."},{"key":"mlstadbb37bib42","first-page":"265","article-title":"On the Algorithmic implementation of multiclass Kernel-based vector machines","volume":"2","author":"Crammer","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"mlstadbb37bib43","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"year":"2024","author":"LONGLEAF CLUSTER","key":"mlstadbb37bib44"},{"key":"mlstadbb37bib45","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstadbb37bib46","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10039710","article-title":"scikit-learn\/scikit-learn: Scikit-learn 1.3.2","author":"Grisel","year":"2023","unstructured":"Grisel O et al 2023 scikit-learn\/scikit-learn: Scikit-learn 1.3.2 10.5281\/zenodo.10039710"},{"key":"mlstadbb37bib47","doi-asserted-by":"publisher","first-page":"p 261","DOI":"10.22323\/1.441.0261","article-title":"Muon Veto of the LEGEND Experiment","volume":"vol","author":"(LEGEND Collaboration)","year":"2024","journal-title":"PoS TAUP2023"},{"key":"mlstadbb37bib48","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1140\/epjc\/s10052-022-10163-w","article-title":"Pulse shape analysis in GERDA Phase II","volume":"82","author":"Agostini","year":"2022","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib49","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevC.99.065501","article-title":"Multisite event discrimination for the majorana demonstrator","volume":"99","author":"Alvis","year":"2019","journal-title":"Phys. Rev. C"},{"key":"mlstadbb37bib50","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1093\/biomet\/26.4.404","article-title":"The use of confidence or fiducial limits illustrated in the case of the binomial","volume":"26","author":"Clopper","year":"1934","journal-title":"Biometrika"},{"key":"mlstadbb37bib51","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1140\/epjc\/s10052-022-10161-y","article-title":"\u03b1-event characterization and rejection in point-contact HPGe detectors","volume":"82","author":"Arnquist","year":"2022","journal-title":"Eur. Phys. J. C"},{"key":"mlstadbb37bib52","doi-asserted-by":"publisher","first-page":"489","DOI":"10.3390\/particles4040036","article-title":"Surface characterization of p-type point contact germanium detectors","volume":"4","author":"Edzards","year":"2021","journal-title":"Particles"},{"key":"mlstadbb37bib53","doi-asserted-by":"publisher","first-page":"p 256","DOI":"10.22323\/1.441.0256","article-title":"The LEGEND-200 liquid argon instrumentation: from a simple veto to a full-fledged detector","volume":"vol","author":"(LEGEND Collaboration)","year":"2024","journal-title":"PoS TAUP2023"},{"article-title":"Juleana.jl","year":"2024","author":"Schulz","key":"mlstadbb37bib54"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T13:07:04Z","timestamp":1742216824000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adbb37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,17]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3,17]]},"published-print":{"date-parts":[[2025,3,31]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adbb37","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,3,17]]},"assertion":[{"value":"Machine learning-powered data cleaning for LEGEND: a semi-supervised approach using affinity propagation and support vector machines","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-11-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-02-27","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-03-17","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}