OTERO, A.G.L.POTIENS JUNIOR, A.J.MARUMO, J.T.2021-08-022021-08-022021OTERO, A.G.L.; POTIENS JUNIOR, A.J.; MARUMO, J.T. Comparing deep learning architectures on gamma-spectroscopy analysis for nuclear waste characterization. <b>Brazilian Journal of Radiation Sciences</b>, v. 9, n. 1A, p. 1-8, 2021. DOI: <a href="https://dx.doi.org/10.15392/bjrs.v9i1A.1257">10.15392/bjrs.v9i1A.1257</a>. Disponível em: http://repositorio.ipen.br/handle/123456789/32082.2319-0612http://repositorio.ipen.br/handle/123456789/32082Neural networks, particularly deep neural networks, are used nowadays with great success in several tasks, such as image classification, image segmentation, translation, text to speech, speech to text, achieving super-human performance. In this study, the capabilities of deep learning are explored on a new field: gamma-spectroscopy analysis, comparing the classification performance of different deep neural network architectures. The following architectures where tested: VGG-16, VGG-19, Xception, ResNet, InceptionV3, and MobileNet, which are available through the Keras Deep Learning framework to identify several different radionuclides (Am-241, Ba133, Cd-109, Co-60, Cs-137, Eu-152, Mn-54, Na-24, and Pb-210). Using an HPGe detector to acquire several gamma spectra from different sealed sources to create a dataset used for the training and validation of the neural network's comparison. This study demonstrates the strengths and weaknesses of applying deep learning on gamma-spectroscopy analysis for nuclear waste characterization.1-8openAccessartificial intelligencecomputer architecturegamma spectroscopyhigh-purity ge detectorsneural networksradioactive waste managementradioactive wastesradioisotopessealed sourcesArtigo de periódico1A910.15392/bjrs.v9i1A.12570000-0003-3010-96910000-0002-4098-0272https://orcid.org/0000-0003-3010-9691Sem Percentil