Study of (n,2n) reaction cross section of fission product based on neural network and decision tree models

¹ China Nuclear Data Center, China Institute of Atomic Energy, Beijing 102413, China
² Reactor Engineering Technology Research Institute, China Institute of Atomic Energy, Beijing 102413, China
³ Graduate Department of Nuclear Industry, Beijing 102413, China

^* e-mail: xuruirui@ciae.ac.cn

Published online: 17 April 2024

Abstract

The neutron induced nuclear reaction cross sections of fission products are related with the neutron fiux and the reactor burnup, which are important for the accurate of nuclear engineering design. To predict the (n,2n) reaction cross section, especially those lack of experimental measurements, we analyzed the relevant features and establish the experimental data set on the basis of sorting out the experimental data recorded in EXFOR library. The back propagation artificial neural network (ANN) and decision tree (DT) models are built to learn the experimental data set, respectively, adopting PyTorch and XGBOOST toolboxes. we report that machine learning models are applied to analysis and predicate (n,2n) reaction cross section.