High-Precision Prediction of Isotopic Binding Energy per Nucleon Using Machine Learning and Nuclear Feature Engineering Methods

Authors

  • Zarnigor Xudoyorova Ixtiyor qizi Teacher at School No. 34, Samarkand City Author

Keywords:

Keywords: AME2020, EXFOR, XGBoost, SHAP analysis, Liquid Drop Model, binding energy, Random Forest, machine learning.

Abstract

In this study, based on the international nuclear databases AME2020 and EXFOR, machine learning algorithms such as XGBoost and Random Forest, alongside physics-informed feature engineering approaches, were applied to predict fundamental properties of atomic nuclei—specifically the binding energy per nucleon (B/A)—with high accuracy. During the research, preliminary data analysis including correlation matrices, residual analysis based on the XGBoost model, and SHAP analysis evaluating factors influencing predictions were carried out. The obtained results proved that the synthesis of physical parameters and artificial intelligence yields high efficiency in modeling nuclear properties.

References

1.Wang M. et al. “The AME 2020 atomic mass evaluation (I). Evaluation of input data, adjustment procedures” Chinese Physics C. – 2021. – Vol. 45, № 3. – P. 030002.

2.Kondev F. G. et al. “The NUBASE2020 evaluation of nuclear physics properties” Chinese Physics C. – 2021. – Vol. 45, № 3. – P. 030001.

3.Yüksel E., Soydaner D., Bahtiyar H. “Nuclear mass predictions using machine learning models” Physical Review C. – 2024. – Vol. 109, № 6. – P. 064322.

4.Niu Z. M., Liang H. Z. “Machine learning in nuclear physics” Progress in Particle and Nuclear Physics. – 2024. – Vol. 136. – P. 104107.

5.Niu Z. M. et al. “Machine learning the nuclear mass” Physical Review C. – 2021. – Vol. 104, № 2. – P. 024312.

6.Chen T., Guestrin C. “XGBoost: A scalable tree boosting system” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2016. – P. 785-794.

7.Lundberg S. M., Lee S. I. “An unified approach to interpreting model predictions” Advances in Neural Information Processing Systems (NeurIPS). – 2017. – Vol. 30.

8.Ring P., Schuck P. “The Nuclear Many-Body Problem” – Springer Science & Business Media, 2004.

9.Bohr A., Mottelson B. R. “Nuclear Structure.” Vol. 1: Single-Particle Motion. – World Scientific, 1998.

10.Krappe H. J., Pomorski K. “Theory of Nuclear Fission” A Textbook. – Springer Science & Business Media, 2012.

11.Bishop C. M. “Pattern Recognition and Machine Learning” – Springer, 2006

Downloads

Published

2026-10-17