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.

Empirical formula for (n, f) reaction cross sections of Uranium isotopes at 1-20 MeV neutrons

This article describes how to calculate neutron-induced fission reaction cross sections using a proposed empirical formula and the EMPIRE 3.2.3 and TALYS 1.95 computer codes for Uranium isotopes up to the third fission plateau. In this study, the excitation functions of 232U (n, f), 233U (n, f), 234U (n, f), 235U (n, f), 236U (n, f), 237U (n, f) and 238U (n, f) nuclear reactions were calculated at 1-20 MeV neutron energies. The results were contrasted to measured values from the Experimental Nuclear Reaction Data (EXFOR) as well as the evaluated data from Evaluated Nuclear Data File (ENDF) such as (EAF-2010, JEFF-3.3, ENDF/B-VIII.0 and TENDL-2019). Overall, the calculated, experimental, and evaluated fission cross-sections are in concordance.

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°.

A study on the cross-section data of 43,44m,46,47Sc isotopes via (d,x) reactions on natural abundance targets under the effects of deuteron optical models

Many studies have investigated the influence of theoretical models and factors involved in the acquisition of cross-section data of a nuclear reaction. The implications of different models of various variables such as level density, gamma strength function, and optical potentials on cross-section calculations whether used solo or jointly are investigated in a significant portion of the works conducted in this perspective. The aim of this particular study is to investigate the influence of different optical models on the cross-section calculations in production of several scandium isotopes, known for various medical uses, from several targets with natural abundances by (d,x) reactions. For this purpose, the cross-section calculations using five available deuteron optical models of TALYS code in ^natTi(d,x)⁴³Sc, ^natTi(d,x)^44mSc, ^natTi(d,x)⁴⁶Sc, ^natTi(d,x)⁴⁷Sc, ^natV(d,x)⁴⁷Sc and ^natCr(d,x)⁴⁷Sc reactions were performed and the obtained calculation results were compared with the experimental cross-section data gathered from the literature. To understand whether there is a significant and consistent relationship between the experimental data and the calculation results, both have been plotted together and analyzed with the naked-eye. In addition, the calculations of the mean standardized deviation, the mean relative deviation, the mean ratio and the mean square logarithmic deviation were performed in order to evaluate the results numerically.

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.

Investigation of (d, 3n) reaction cross section using theoretical nuclear codes calculations on some nuclear materials

It is important to examine the effects of the nuclear reaction, which is used as a building material in nuclear reactors. Nuclear reactions occur as a result of the interaction between incident particles with the target nuclei. The charged particle-induced reactions have prime importance in understanding the reaction mechanism which can be applicable to understand the particles resulting from the reaction. It is useful to develop shielding the particle accelerators and fusion reactors. The present study contributes to providing the theoretical prediction of excitation functions for ¹¹²Cd (d, 3n)¹¹¹In, ¹⁴¹Pr (d, 3n)¹⁴⁰Nd, ¹⁶⁷Er (d, 3n)¹⁶⁶Tm, ¹⁹⁷Au (d, 3n)¹⁹⁶Hg and ²⁰⁹Bi (d, 3n)²⁰⁸Po reactions using theoretical model codes such as TALYS-1.95, EMPIRE-3.2.3, and ALICE-2014 within the incident deuteron energy range of threshold energy to 50 MeV. Also, newly developed (d, 3n) cross-section formula (Kavun, 2020) calculations have been performed for these reactions at 20 MeV of deuteron energy. Lastly, all calculated results have been compared with one another and with the previously published experimental data of the EXFOR database.

Effects of combining some theoretical models in the cross-section calculations of some alpha-induced reactions for natSb

In cases where it is not possible to obtain the cross-section values experimentally due to various factors, the importance of obtaining them with theoretical models has been explained in many studies available in the literature. In this context, the comparison of the cross-section values obtained by using the theoretical models with the experimental data will also be very beneficial for updating and developing these models. Existing studies, which also serve this purpose, have given inspiration to this study and it is aimed to examine the effects of the simultaneous use of the alpha optical model potentials and the level density models on the cross-section calculations for some alpha-particle-induced reactions on natural antimony. The effects of theoretical models on the cross-section calculations were investigated by comparing the obtained calculation results with the experimental data taken from the literature. The TALYS code, which is frequently preferred in the literature, was used in all calculations within the scope of this study. For the comparison of the calculated results with the experimental data, not only a visual analysis by graphing the outcomes, but also a mean-weighted-deviation calculation was used, and the findings were interpreted by accounting for both of them.

Effects of deuteron optical models on the cross-section calculations of deuteron induced reactions on natural germanium

A common feature of scientific studies is that when experimental observation data are not available, theoretical calculations are used to obtain information about the subject under investigation. In this context, many parameters and theoretical models have been developed that can be used in nuclear physics studies just as it is in other branches of sciences. It is intended that by doing so, theoretical models can be improved using recent experimental data while also learning about outcomes where experimental data is unavailable or difficult to access. Among the many theoretical models available, there are also deuteron optical models whose effects are examined in this study. The objective of this study is to examine the effects of different deuteron optical models on the cross-section calculations of deuteron induced reactions on natural germanium. The cross-section values of ^natGe(d,x)⁷⁰As, ^natGe(d,x)⁷¹As, ^natGe(d,x)⁷²As, ^natGe(d,x)⁷³As, ^natGe(d,x)⁷⁴As and ^natGe(d,x)⁷⁶As reactions were calculated using five deuteron optical models in the TALYS code's v1.95 for this aim, and the results were compared to the experimental data available in the database known as Experimental Nuclear Reaction Data (EXFOR) library. Graphics and quantitative analyses were also used to present the findings and interpretations of the outcomes.

Estimation of (n,p) reaction cross sections at 14.5 ∓0.5 MeV neutron energy by using artificial neural network

The aim of this study is to develop an accurate artificial neural network algorithm for the cross-section of (n,p) reactions at 14.5 ∓0.5 MeV neutron energy which is important to developing materials for fusion reactor design. The experimental data used at artificial Neural network calculations have been taken from the Experimental Nuclear Reaction Data (EXFOR) database. Bayesian algorithm has been used at training section of artificial neural network. Regression (R) values of artificial neural network calculations have been found as 0.99363, 0.98574 and 0.99257 for training, testing and all process respectively. In addition to artificial neural network calculations, TALYS 1.95 nuclear reaction code has been used to reproduce (n,p) reactions at 14.5 ∓0.5 MeV. Two-component exciton model and Constant Temperature Fermi Gas Model have been used as pre-equilibrium and level density models respectively. Mean square errors of our calculations have been found 48.51 and 495.06 for artificial neural network and TALYS 1.95 respectively. Artificial Neural network estimations have been compared and analyzed with the TALYS 1.95 calculations and the experimental data taken from EXFOR database.

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.