{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:15:57Z","timestamp":1780413357339,"version":"3.54.1"},"reference-count":19,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T00:00:00Z","timestamp":1627948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Improvements in Radio-Isotope IDentification (RIID) algorithms have seen a resurgence in interest with the increased accessibility of machine learning models. Convolutional Neural Network (CNN)-based models have been developed to identify arbitrary mixtures of unstable nuclides from gamma spectra. In service of this, methods for the simulation and pre-processing of training data were also developed. The implementation of 1D multi-class, multi-label CNNs demonstrated good generalisation to real spectra with poor statistics and significant gain shifts. It is also shown that even basic CNN architectures prove reliable for RIID under the challenging conditions of heavy shielding and close source geometries, and may be extended to generalised solutions for pragmatic RIID.<\/jats:p>","DOI":"10.3390\/s21155238","type":"journal-article","created":{"date-parts":[[2021,8,4]],"date-time":"2021-08-04T02:16:07Z","timestamp":1628043367000},"page":"5238","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Convolutional Neural Networks for Challenges in Automated Nuclide Identification"],"prefix":"10.3390","volume":"21","author":[{"given":"Anthony","family":"Turner","sequence":"first","affiliation":[{"name":"School of Physics and Astronomy, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9137-6051","authenticated-orcid":false,"given":"Carl","family":"Wheldon","sequence":"additional","affiliation":[{"name":"School of Physics and Astronomy, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2035-3749","authenticated-orcid":false,"given":"Tzany","family":"Wheldon","sequence":"additional","affiliation":[{"name":"School of Physics and Astronomy, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Gilbert","sequence":"additional","affiliation":[{"name":"UKAEA, Culham Science Centre, Abingdon, Oxfordshire OX14 3DB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lee","family":"Packer","sequence":"additional","affiliation":[{"name":"UKAEA, Culham Science Centre, Abingdon, Oxfordshire OX14 3DB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Burns","sequence":"additional","affiliation":[{"name":"AWE PLC, Aldermaston, Reading RG7 4PR, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Freer","sequence":"additional","affiliation":[{"name":"School of Physics and Astronomy, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/23.83860","article-title":"A new approach to automatic radiation spectrum analysis","volume":"38","author":"Olmos","year":"1991","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1016\/S0168-9002(96)80068-4","article-title":"Statistical modelling of neural networks in \u03b3-spectrometry","volume":"369","author":"Vigneron","year":"1996","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/S0168-9002(98)01110-3","article-title":"Application of neural networks to quantitative spectrometry analysis","volume":"422","author":"Pilato","year":"1999","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1016\/j.nima.2008.09.035","article-title":"Nuclide identification algorithm based on K\u2013L transform and neural networks","volume":"598","author":"Chen","year":"2009","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/S0168-9002(01)01962-3","article-title":"Application of neural networks for the analysis of gamma-ray spectra measured with a Ge spectrometer","volume":"484","author":"Yoshida","year":"2002","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1109\/TNS.2017.2693152","article-title":"Automated Isotope Identification Algorithm Using Artificial Neural Networks","volume":"64","author":"Kamuda","year":"2017","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.jenvrad.2014.11.011","article-title":"Development of a neural network approach to characterise 226Ra contamination at legacy sites using gamma-ray spectra taken from boreholes","volume":"140","author":"Vargas","year":"2015","journal-title":"J. Environ. Radioact."},{"key":"ref_8","first-page":"1858","article-title":"A comparison of machine learning methods for automated gamma-ray spectroscopy","volume":"64","author":"Kamuda","year":"2018","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_9","first-page":"483","article-title":"Rapid nuclide identification algorithm based on convolutional neural network","volume":"133","author":"Liang","year":"2019","journal-title":"Semin. Nucl. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1109\/TNS.2020.2969703","article-title":"Automatic and Real-time Identification of Radionuclides in Gamma-ray Spectra: A new method based on Convolutional Neural Network trained with synthetic data set","volume":"67","author":"Daniel","year":"2020","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/S0168-9002(03)01368-8","article-title":"Geant4\u2014A simulation toolkit","volume":"506","author":"Agostinelli","year":"2003","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"012211","DOI":"10.1088\/1742-6596\/1643\/1\/012211","article-title":"Generalised gamma spectrometry simulator for problems in nuclide identification","volume":"1643","author":"Turner","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/S0168-9002(97)00048-X","article-title":"ROOT\u2014An object oriented data analysis framework","volume":"389","author":"Brun","year":"1997","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_14","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2015). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv."},{"key":"ref_15","unstructured":"Kingma, D., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_16","unstructured":"Bishop, C. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_17","unstructured":"Hinton, G., Srivastava, N., and Swersky, K. (2021, April 20). Lecture 6d\u2014A separate, adaptive learning rate for each connection. Slides of Lecture Neural Networks for Machine Learning, Available online: https:\/\/www.cs.toronto.edu\/~hinton\/coursera_lectures.html."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. arXiv.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.apradiso.2019.01.005","article-title":"Multi-radioisotope identification algorithm using an artificial neural network for plastic gamma spectra","volume":"147","author":"Kim","year":"2019","journal-title":"Appl. Radiat. Isot."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/15\/5238\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:39:32Z","timestamp":1760164772000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/15\/5238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,3]]},"references-count":19,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["s21155238"],"URL":"https:\/\/doi.org\/10.3390\/s21155238","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,3]]}}}