{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T07:10:04Z","timestamp":1760512204314,"version":"build-2065373602"},"reference-count":25,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Laurentis Energy Partners","award":["IT25686"],"award-info":[{"award-number":["IT25686"]}]},{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"crossref","award":["IT25686"],"award-info":[{"award-number":["IT25686"]}],"id":[{"id":"10.13039\/501100004489","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":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>High-purity germanium (HPGe) detectors have been golden standard for gamma spectrometry in low-level radioactive waste (LLW) analysis; however, their notable shortcoming is prolonged measurement durations for weak radioactive waste materials. The present study aimed to develop the HPGe-Compton Net, a 1D physics-guided convolutional neural network to accelerate LLW analysis by taking advantage of the entire response function of a HPGe detector for each radionuclide of interest, in contrast to the traditional methods that analyze only peak regions of the response. This acceleration is supported by two core innovative strategies: (a) channel-prompt method, a feature enhancement incorporating additional physical information to guide the model to locate the designated radionuclide; (b) the specially designed database to achieve effective targeted feature learning. The performance evaluation carried out for test data set showed a five times reduction in measurement time compared to a conventional spectral analysis method while maintaining comparable precision. Compton perturbation tests confirmed the model\u2019s \u2018smart\u2019 adaptive utilization of the Compton regions. The generalization testing of four LLW samples as the external validation set proved its superior performance in low-count data with an average accuracy of 90% over 83% of the traditional method. Future work will focus on upgrading the HPGe-Compton Net for practical applications.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae0f38","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T22:49:37Z","timestamp":1759531777000},"page":"045010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HPGe-Compton Net: a physics-guided CNN for fast gamma spectra analysis via Compton region learning"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3541-9500","authenticated-orcid":true,"given":"Yanfeng","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9803-579X","authenticated-orcid":false,"given":"Yiming","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0029-5094","authenticated-orcid":true,"given":"Soo","family":"Hyun Byun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"article-title":"Low and intermediate-level radioactive waste","year":"2024","author":"Canadian Nuclear Safety Commission (CNSC)","key":"mlstae0f38bib1","type":"other"},{"article-title":"Genie 2000 customization tools manual: Genie\u2122 2000 spectroscopy software","year":"2013","author":"Canberra Industries, Inc.","key":"mlstae0f38bib2","type":"other"},{"key":"mlstae0f38bib3","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/0029-554X(61)90071-4","type":"journal-article","article-title":"Analysis of gamma-ray scintillation spectra by the method of least squares","volume":"14","author":"Salmon","year":"1961","journal-title":"Nucl. Instrum. Methods"},{"key":"mlstae0f38bib4","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1016\/S0969-8043(97)00127-9","type":"journal-article","article-title":"Single peak versus library least-squares analysis methods for the PGNAA analysis of vitrified waste","volume":"48","author":"Gardner","year":"1997","journal-title":"Appl. Radiat. Isot."},{"key":"mlstae0f38bib5","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.radphyschem.2018.08.015","type":"journal-article","article-title":"Uncertainty quantification for Gamma-ray spectroscopy using the Library-Least Squares technique","volume":"155","author":"Feinberg","year":"2019","journal-title":"Radiat. Phys. Chem."},{"key":"mlstae0f38bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apradiso.2019.108903","type":"journal-article","article-title":"Sparse spectral unmixing for activity estimation in \u03b3-ray spectrometry applied to environmental measurements","volume":"156","author":"Xu","year":"2020","journal-title":"Appl. Radiat. Isot."},{"key":"mlstae0f38bib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.apradiso.2021.110082","type":"journal-article","article-title":"Analysis of gamma-ray spectra with spectral unmixing, part II: recalibration for the quantitative analysis of HPGe measurements","volume":"182","author":"Xu","year":"2022","journal-title":"Appl. Radiat. Isot."},{"key":"mlstae0f38bib8","doi-asserted-by":"publisher","first-page":"eabq5089","DOI":"10.1126\/sciadv.abq5089","type":"journal-article","article-title":"Deep learning reveals predictive sequence concepts within immune repertoires to immunotherapy","volume":"8","author":"Sidhom","year":"2022","journal-title":"Sci. Adv."},{"key":"mlstae0f38bib9","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1126\/science.ads7373","type":"journal-article","article-title":"Predicting expression-altering promoter mutations with deep learning","volume":"389","author":"Jaganathan","year":"2025","journal-title":"Science"},{"key":"mlstae0f38bib10","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-48351-7","type":"journal-article","article-title":"Physics constrained unsupervised deep learning for rapid, high resolution scanning coherent diffraction reconstruction","volume":"13","author":"Hoidn","year":"2023","journal-title":"Sci. Rep."},{"key":"mlstae0f38bib11","doi-asserted-by":"publisher","first-page":"1846","DOI":"10.1038\/s41598-024-84995-9","type":"journal-article","article-title":"Physics-informed deep learning quantifies propagated uncertainty in seismic structure and hypocenter determination","volume":"15","author":"Agata","year":"2025","journal-title":"Sci. Rep."},{"key":"mlstae0f38bib12","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1038\/s41586-021-04223-6","type":"journal-article","article-title":"Deep physical neural networks trained with backpropagation","volume":"601","author":"Wright","year":"2022","journal-title":"Nature"},{"key":"mlstae0f38bib13","doi-asserted-by":"publisher","first-page":"article 151","DOI":"10.1038\/s44172-024-00303-3","type":"journal-article","article-title":"Multi-level physics informed deep learning for solving partial differential equations in computational structural mechanics","volume":"3","author":"He","year":"2024","journal-title":"Commun. Eng."},{"key":"mlstae0f38bib14","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1038\/s43588-022-00265-6","type":"journal-article","article-title":"Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation","volume":"2","author":"Li","year":"2022","journal-title":"Nat. Comput. Sci."},{"key":"mlstae0f38bib15","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1038\/s42005-025-02152-8","type":"journal-article","article-title":"Physics-guided deep learning strategy for 2D structure reconstruction from diffraction patterns","volume":"8","author":"Fu","year":"2025","journal-title":"Commun. Phys."},{"key":"mlstae0f38bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2022.166597","type":"journal-article","article-title":"Estimation of uranium concentration in ore samples with machine learning methods on HPGe gamma-ray spectra","volume":"1032","author":"Allinei","year":"2022","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstae0f38bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2023.168409","type":"journal-article","article-title":"Machine learning technique for isotopic determination of radionuclides using HPGe gamma-ray spectra","volume":"1054","author":"Khatiwada","year":"2023","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstae0f38bib18","doi-asserted-by":"publisher","first-page":"846","DOI":"10.3390\/digital4040042","type":"journal-article","article-title":"Physics guided neural networks with knowledge graph","volume":"4","author":"Gupta","year":"2024","journal-title":"Digital"},{"key":"mlstae0f38bib19","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1109\/TPWRS.2023.3266236","type":"journal-article","article-title":"Physics-guided neural network for load margin assessment of power systems","volume":"39","author":"Bento","year":"2024","journal-title":"IEEE Trans. Power Syst."},{"key":"mlstae0f38bib20","doi-asserted-by":"publisher","first-page":"p 20","DOI":"10.1201\/9781003143376-15","type":"book","article-title":"Physics-guided neural networks (PGNN): an application in lake temperature modeling","author":"Daw","year":"2022","edition":"1st edn"},{"article-title":"777 ultra low-background shield data sheet","year":"2022","author":"Mirion Technologies","key":"mlstae0f38bib21","type":"other"},{"article-title":"Broad energy germanium detectors data sheet","year":"2022","author":"Mirion Technologies","key":"mlstae0f38bib22","type":"other"},{"article-title":"Operating Manual for Broad-Energy Germanium (BEGe) Gamma Spectrometer","year":"2023","author":"Li","key":"mlstae0f38bib23","type":"book"},{"article-title":"Nuclear facility - McMaster nuclear reactor","year":"2024","author":"Canadian Nuclear Safety Commission (CNSC)","key":"mlstae0f38bib24","type":"other"},{"article-title":"TensorFlow: large-scale machine learning on heterogeneous systems","year":"2015","author":"Abadi","key":"mlstae0f38bib25","type":"preprint"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T06:30:58Z","timestamp":1760509858000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0f38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":25,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,10,15]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae0f38","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"assertion":[{"value":"HPGe-Compton Net: a physics-guided CNN for fast gamma spectra analysis via Compton region learning","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":"2025-07-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-03","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-15","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}