https://doi.org/10.1140/epja/s10050-023-01189-z
Regular Article - Theoretical Physics
Evaluation of pre-neutron-emission mass distributions in induced fission of typical actinides based on Monte Carlo dropout neural network
1
School of Nuclear Science and Technology, Lanzhou University, 730000, Lanzhou, China
2
Engineering Research Center for Neutron Application Technology, Ministry of Education, Lanzhou University, 730000, Lanzhou, China
3
MOE Frontiers Science Center for Rare Isotopes, Lanzhou University, 730000, Lanzhou, China
Received:
14
September
2023
Accepted:
1
November
2023
Published online:
13
November
2023
The pre-neutron-emission mass distribution is a critical physical constant in neutron-induced fission reaction. In this work, the Monte Carlo dropout neural network (MC-Dropout NN) method is applied to evaluate the pre-neutron-emission mass distributions of neutron-induced typical actinides (232Th, 235U, 238U, 237Np, 239Pu) fission. This method can reproduce precise mass distributions and give the uncertainty of predictions. Moreover, based on the MC-dropout NN learning of the existing experimental fission yields, the unknown yields and their uncertainty can be given. Finally, we predict pre-neutron-emission mass distributions of neutron-induced fission of 232Th and 238U at incident neutron energy below 45 MeV and study the influence of pre-fission neutrons on fission yields. Given the good agreements with experimental data, the neural network approach is a very useful tool in the field of nuclear data evaluation.
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 2023. 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.
