https://doi.org/10.1140/epjp/s13360-025-06813-z
Regular Article
Application of TENIS and artificial neural networks in neutron spectroscopy for BNCT beams in IRT-T and TRR: additional research
1
Department of Physics, Faculty of Science, Ferdowsi University of Mashhad, P.O. Box 91775-1436, Mashhad, Iran
2
Department of Physics, K. N. Toosi University of Technology, P.O. Box 16315-1618, Tehran, Iran
3
School of Nuclear Science and Engineering, Tomsk Polytechnic University, P.O. Box 634050, Tomsk, Russian Federation
4
Energy Engineering Department, Bilbao Engineering School, University of the Basque Country UPV/EHU, P.O. Box 48013, Bilbao, Spain
Received:
4
July
2025
Accepted:
29
August
2025
Published online:
16
September
2025
Following the successful results of the ThErmal Neutron Imaging System (TENIS) for mono- and poly-energetic neutron sources, in this research, real-time data obtained from the TENIS were utilized for neutron spectroscopy at the exits of the Beam Shaping Assemblies (BSAs) located at the beam ports of Tomsk Polytechnic University Research Reactor (IRT-T) and Tehran Research Reactor (TRR). To achieve this purpose, 70-pixel thermal neutron images were generated for 109 mono-energetic neutrons, referred to as the neutron fluence response matrix, using the MCNP6.1 code. These images were used as the input of the artificial neural network (ANN) tools in MATLAB. Results indicated that the sigmoid transfer function in both hidden and output layers gives the best correlation between the predicted and actual spectra of Boron Neutron Capture Therapy (BNCT) beam lines in IRT-T and TRR, with correlation coefficients (R2) of 0.74 and 0.86, and root-mean-square error of 0.020 and 0.014, respectively (i.e., a max–min problem). The results suggest that the ANN-unfolded TENIS results can also accurately predict the energy spectrum of neutrons suitable for the BNCT.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
