Calculations of GDR parameters for deformed nuclei using LogitBoost classifier and artificial neural network
Üncü, Yiğit Ali
Üst veriTüm öğe kaydını göster
Photo-nuclear interactions are important for investigating fundamental nuclear physics phenomena. The photo-absorption cross-section energy curve displays a wide resonance called giant dipole resonance (GDR) until 30 MeV. First, spherical and deformed nuclei have been determined by using LogitBoost classifier, and then GDR param- eters for deformed nuclei have been estimated by using an artificial neural network (ANN) via Levenberg–Marquardt algorithm which has been selected for the training sec- tion. In the last step, 233U(γ,n)232U, 234U(γ,n)233U, 235U(γ,n)234U, 236U(γ,n)235U, 238U(γ,n)237U reaction cross-sections have been computed by using GDR parameters obtained ANN estimations. The mean square error, root mean square error, and R are evaluated as the best performance of ANN estimates. Photo-neutron cross-section re- sults have been compared with experimental data from the literature. Consequently, it has been found that ANN algorithms can be used to determine the GDR parameters for deformed nuclei in the lack of experimental data of photo-absorption reaction.