神经网络在原子核质量中的应用
The Application of Neural Networks in Nuclear Masses
DOI: 10.12677/app.2025.154028, PDF,   
作者: 曲 爽：上海理工大学理学院，上海
关键词: 原子核质量；神经网络；贝叶斯方法；Nuclear Mass； Neural Network； Bayesian Method
摘要: 本文采用贝叶斯神经网络方法对多个核质量模型进行了优化，包括宏观模型LDM、宏观–微观模型FRDM12，微观模型RMF等。基于AME2020核质量数据表，BNN方法有效降低了实验值与理论预测值之间的均方根误差，尤其在LDM模型和RMF模型中，均方根误差都降低了80%。通过对轻、中和重核的单中子分离能进行测试，结果显示BNN优化后的核质量模型的单中子分离能与实验数据能够较好地趋近，并且再现了奇偶交错现象。
Abstract: This paper employs the Bayesian neural network method to optimize multiple nuclear mass models, including the macroscopic model LDM, the macroscopic-microscopic model FRDM12, and the microscopic model RMF, etc. Based on the AME2020 nuclear mass data table, the BNN method effectively reduces the root mean square error between experimental values and theoretical predictions, especially in the LDM and RMF models, where the root mean square error is reduced by 80%. By testing the single-neutron separation energies of light, medium, and heavy nuclei, the results show that the single-neutron separation energies of the BNN-optimized nuclear mass models can better approach the experimental data and reproduce the odd-even staggering phenomenon.
文章引用：曲爽. 神经网络在原子核质量中的应用[J]. 应用物理, 2025, 15(4): 256-261. https://doi.org/10.12677/app.2025.154028

参考文献

[1] Ramirez, E.M., Ackermann, D., Blaum, K., Block, M., Droese, C., Düllmann, C.E., et al. (2012) Direct Mapping of Nuclear Shell Effects in the Heaviest Elements. Science, 337, 1207-1210. [Google Scholar] [CrossRef] [PubMed]
[2] Wienholtz, F., Beck, D., Blaum, K., Borgmann, C., Breitenfeldt, M., Cakirli, R.B., et al. (2013) Masses of Exotic Calcium Isotopes Pin down Nuclear Forces. Nature, 498, 346-349. [Google Scholar] [CrossRef] [PubMed]
[3] Hager, U., Eronen, T., Hakala, J., Jokinen, A., Kolhinen, V.S., Kopecky, S., et al. (2006) First Precision Mass Measurements of Refractory Fission Fragments. Physical Review Letters, 96, Article ID: 042504. [Google Scholar] [CrossRef] [PubMed]
[4] de Roubin, A., Atanasov, D., Blaum, K., George, S., Herfurth, F., Kisler, D., et al. (2017) Nuclear Deformation in the a ≈ 100 Region: Comparison between New Masses and Mean-Field Predictions. Physical Review C, 96, Article ID: 014310. [Google Scholar] [CrossRef] 
[5] Wang, M., Huang, W.J., Kondev, F.G., Audi, G. and Naimi, S. (2021) The AME 2020 Atomic Mass Evaluation (II). Tables, Graphs and References. Chinese Physics C, 45, Article ID: 030003. [Google Scholar] [CrossRef] 
[6] Gamow, G. (1930) Mass Defect Curve and Nuclear Constitution. Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character, 126, 632-644.
[7] Duflo, J. and Zuker, A.P. (1995) Microscopic Mass Formulas. Physical Review C, 52, R23-R27. [Google Scholar] [CrossRef] [PubMed]
[8] Zuker, A.P. (2008) Shell Formation and Nuclear Masses. Revista Mexicana de Física, 54, 129.
[9] Möller, P., Sierk, A.J., Ichikawa, T. and Sagawa, H. (2016) Nuclear Ground-State Masses and Deformations: FRDM (2012). Atomic Data and Nuclear Data Tables, 109, 1-204. [Google Scholar] [CrossRef] 
[10] Wang, N., Liu, M. and Wu, X. (2010) Modification of Nuclear Mass Formula by Considering Isospin Effects. Physical Review C, 81, Article ID: 044322. [Google Scholar] [CrossRef] 
[11] Wang, N., Liang, Z., Liu, M. and Wu, X. (2010) Mirror Nuclei Constraint in Nuclear Mass Formula. Physical Review C, 82, Article ID: 044304. [Google Scholar] [CrossRef] 
[12] Liu, M., Wang, N., Deng, Y. and Wu, X. (2011) Further Improvements on a Global Nuclear Mass Model. Physical Review C, 84, Article ID: 014333. [Google Scholar] [CrossRef] 
[13] Wang, N., Liu, M., Wu, X. and Meng, J. (2014) Surface Diffuseness Correction in Global Mass Formula. Physics Letters B, 734, 215-219. [Google Scholar] [CrossRef] 
[14] Goriely, S., Chamel, N. and Pearson, J.M. (2013) Further Explorations of Skyrme-Hartree-Fock-Bogoliubov Mass Formulas. XIII. the 2012 Atomic Mass Evaluation and the Symmetry Coefficient. Physical Review C, 88, Article ID: 024308. [Google Scholar] [CrossRef] 
[15] Goriely, S., Chamel, N. and Pearson, J.M. (2013) Hartree-Fock-Bogoliubov Nuclear Mass Model with 0.50 Mev Accuracy Based on Standard Forms of Skyrme and Pairing Functionals. Physical Review C, 88, Article ID: 061302. [Google Scholar] [CrossRef] 
[16] Goriely, S., Chamel, N. and Pearson, J.M. (2016) Further Explorations of Skyrme-Hartree-Fock-Bogoliubov Mass Formulas. XVI. Inclusion of Self-Energy Effects in Pairing. Physical Review C, 93, Article ID: 034337. [Google Scholar] [CrossRef] 
[17] Geng, L., Toki, H. and Meng, J. (2005) Masses, Deformations and Charge Radii-Nuclear Ground-State Properties in the Relativistic Mean Field Model. Progress of Theoretical Physics, 113, 785-800. [Google Scholar] [CrossRef] 
[18] Niu, Z.M., Zhu, Z.L., Niu, Y.F., Sun, B.H., Heng, T.H. and Guo, J.Y. (2013) Radial Basis Function Approach in Nuclear Mass Predictions. Physical Review C, 88, Article ID: 024325. [Google Scholar] [CrossRef] 
[19] Utama, R., Piekarewicz, J. and Prosper, H.B. (2016) Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach. Physical Review C, 93, Article ID: 014311. [Google Scholar] [CrossRef] 
[20] Huang, W.J., Wang, M., Kondev, F.G., Audi, G. and Naimi, S. (2021) The AME 2020 Atomic Mass Evaluation (I). Evaluation of Input Data, and Adjustment Procedures. Chinese Physics C, 45, Article ID: 030002. [Google Scholar] [CrossRef] 
[21] Bhagwat, A. (2014) Simple Nuclear Mass Formula. Physical Review C, 90, Article ID: 064306. [Google Scholar] [CrossRef] 

为你推荐