Neural network predictions of (n,2n) reaction cross-sections at 14.6 MeV incident neutron energy.

Journal: Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine
Published Date:

Abstract

In this study, we have estimated the (n,2n) reaction cross-section for 14.6 MeV incident neutron energy by using the artificial neural network (ANN) method. We have also predicted the reaction cross-sections whose experimental data are not available in the literature. For the construction of the present ANN, available experimental data in the literature has been borrowed. The ANN estimations have been compared with the available experimental data and the results from a theoretical calculation and the two commonly used computer codes. According to the results that the ANN results are in good agreement with the experimental data than the codes and this shows that the method can be a powerful tool for the estimation of cross-section data for the neutron-induced reactions. Considering the predictions of the ANN of the cross-sections whose experimental data are not available in the literature, it is seen that they are in line with the trend of the experimental data, but far from the results given by the theoretical calculations and two computer codes.

Authors

  • Serkan Akkoyun
    Department of Physics, Faculty of Sciences, Sivas Cumhuriyet University, Sivas, Turkey; Artificial Intelligence Systems and Data Science Application and Research Center, Sivas Cumhuriyet University, Sivas, 58140, Turkey. Electronic address: sakkoyun@cumhuriyet.edu.tr.
  • Naima Amrani
    Physics Department, Faculty of Sciences, Ferhat ABBAS, Setif-1, University, Setif, Algeria; Dosing, Analysis and Characterization in High-Resolution Laboratory, Ferhat ABBAS, Setif-1 University, Setif, Algeria.
  • Tuncay Bayram
    Physics Department, Faculty of Sciences, Karadeniz Technical University, Trabzon, Turkey.