Neural network predictions of (α,n) reaction cross sections at 18.5±3 MeV using the Levenberg-Marquardt algorithm.

In recent developments, artificial neural networks (ANNs) have demonstrated their capability to predict reaction cross-sections based on experimental data. Specifically, for predicting (α,n) reaction cross-sections, we meticulously fine-tuned the neural network's performance by optimizing its parameters through the Levenberg-Marquardt algorithm. The effectiveness of this approach is corroborated by notable correlation coefficients; an R-value of 0.90928 for overall correlation, 0.98194 for validation, 0.99981 for testing, and 0.94116 for the comprehensive network prediction. We conducted a rigorous comparison between the results and theoretical computations derived from the TALYS 1.95 nuclear code to validate the predictive accuracy. The mean square error value for artificial neural network results is 7620.92, whereas for TALYS 1.95 calculations, it has been found to be 50,312.74. This comprehensive evaluation process validates the reliability of the ANN based on the Levenberg-Marquardt algorithm in approximating the reaction sections, thus demonstrating its potential for comprehensive investigations. These recent developments confirm the feasibility of using ANN models to gain insight into (α,n) reaction cross-sections.

Calculation of double differential neutron cross-sections of 56Fe and 90Zr isotopes.

This study is concerned with the calculations of double differential neutron cross-sections of the structural fusion materials of 56Fe and 90Zr isotopes that are bombarded with protons. Calculations were performed using the level density models of the TALYS 1.95 code and PHITS 3.22 Monte Carlo code. Constant Temperature Fermi Gas, Back Shifted Fermi Gas, and Generalized Super Fluid Models were employed for level density models. Calculations were performed at 22.2 MeV proton energies. Calculations were compared with the experimental data taken from Experimental Nuclear Reaction Data (EXFOR). In conclusion, the results showed that the level density model results of TALYS 1.95 codes for the double differential neutron cross-sections of 56Fe and 90Zr isotopes are consistent with experimental data. On the other hand, PHITS 3.22 results gave lower cross-section values than experimental data at 120 and 150°.

Estimations for (n,α) reaction cross sections at around 14.5MeV using Levenberg-Marquardt algorithm-based artificial neural network.

Prediction of neutron-induced reaction cross-sections at around the 14.5 MeV neutron energy is crucial to calculate nuclear transmutation rates, nuclear heating, and radiation damage from gas formation in fusion reactor technology In this research, the new approach of (n,α) reaction cross-section is presented. It has been assessed by utilizing the artificial neural network (ANN) when compared to more advanced algorithms, the Levenberg-Marquardt algorithm-based ANN can be exceedingly fast. The correlation coefficients for a training R-value of 0.99283, a validation R-value of 0.991190, a testing R-value of 0.97337, and an overall R-value of 0.98515 demonstrate that Levenberg-Marquardt algorithm-based ANN is well suited for this purpose. . The obtained results were compared to theoretical calculations of TALYS 1.95 nuclear code. As a consequence, it has been demonstrated that the ANN model can be used to determine the systemic study for (n, α) reaction cross-sections.

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

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.

Estimations of giant dipole resonance parameters using artificial neural network.

In this study; Giant Dipole Resonance (GDR) parameters of the spherical nucleus have been estimated by using artificial neural network (ANN) algorithms. The ANN training has been carried out with the Levenberg-Marquardt feed-forward algorithm in order to provide fast convergence and stability in ANN training and experimental data, taken from Reference Input Parameter Library (RIPL). R values of the system have been found as 0.99636, 0.94649, and 0.98318 for resonance energy, full width half maximum, and resonance cross-section, respectively. Obtained results have been compared with the GDR parameters which are taken from the literature. To validate our findings, newly acquired GDR parameters were then replaced with the existing GDR parameters in the TALYS 1.95 code and 142-146Nd(γ,n)141-145Nd reaction cross-sections have been calculated and compared with the experimental data taken from the literature. As a result of the study, it has been shown that ANN algorithms can be used to calculate the GDR parameters in the absence of the experimental data.