Estimations of level density parameters by using artificial neural network for phenomenological level density models

Abstract

The main aim of this study is to develop accurate artificial neural network (ANN) algorithms to estimate level density parameters. An efficient Bayesian-based algorithm is presented for classification algorithms. Unknown model parameters are estimated using the observed data, from which the Bayesian-based algorithm is predicted. This paper focuses on the Bayesian method for parameter estimations of Gilbert Cameron Model (GCM), Back Shifted Fermi Gas Model (BSFGM) and Generalised Super Fluid Model (GSM), which are known as the phonemological level density models. Obtained level density parameters have been compared with the Reference Input Parameter Library for Calculation of Nuclear Reactions and Nuclear Data Evaluations (RIPL) data. R values of the Bayesian method have been found as 0.9946, 0.9981 and 0.9824 for BSFGM, GCM and GSM, respectively. In order to validate our results, default level density parameters of TALYS 1.95 code have been changed with our newly obtained results and photo-neutron cross-section calculations of the 117Sn(γ,n)116Sn, 118Sn(γ,n)117Sn, 119Sn(γ,n)118Sn and 120Sn(γ,n)119Sn reactions have been calculated by using these newly obtained level density parameters.