Nuclear Binding Energy Prediction for Some Odd-Mass Number Nuclei by Artificial Neural Network (ANN)

Authors

Ruya H. Ibrahim, Department of Physics, College of Science, University of Anbar, Ramadi, IraqFollow
Akram Mohammed Ali, Department of Physics, College of Science, University of Anbar, Ramadi, IraqFollow

Abstract

Machine learning models called artificial neural networks (ANNs) are widely used in many fields and real-world applications. The parameter vector that forms the basis of these models needs to be evaluated computationally. We calculated the ground-level binding energy of 146 nuclei with an odd mass number using three different models:the integrated nuclear model,the liquid drop model and the experimental model. The results of these models were compared with our theoretical results calculated by the artificial intelligence network. The mean squared error of the target and output values and how close they are to zero were calculated, and the degree of correlation of the target and output values and the accuracy-error ratio were improved using the correlation coefficient(R) for each model. The output is optimized by the Particle Swarm Optimization (PSO) algorithm to give the results greater accuracy, a lower error ratio and clustering around the zero line with lower ratios.

Keywords

Artificial neural network, Binding energy, Mean square error, Odd nuclei, PSO optimization

Subject Area

Physics

Article Type

Article

First Page

4117

Last Page

4129

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite this Article

Ibrahim, Ruya H. and Ali, Akram Mohammed (2025) "Nuclear Binding Energy Prediction for Some Odd-Mass Number Nuclei by Artificial Neural Network (ANN)," Baghdad Science Journal: Vol. 22: Iss. 12, Article 17.
DOI: https://doi.org/10.21123/2411-7986.5168