Machine learning the nuclear mass

被引:68
|
作者
Gao, Ze-Peng [1 ,2 ]
Wang, Yong-Jia [2 ]
Lu, Hong-Liang [3 ]
Li, Qing-Feng [2 ,4 ]
Shen, Cai-Wan [2 ]
Liu, Ling [1 ]
机构
[1] Shenyang Normal Univ, Coll Phys Sci & Technol, Shenyang 110034, Peoples R China
[2] Huzhou Univ, Sch Sci, Huzhou 313000, Peoples R China
[3] Huawei Technol Co Ltd, HiSilicon Res Dept, Shenzhen 518000, Peoples R China
[4] Chinese Acad Sci, Inst Modern Phys, Lanzhou 730000, Peoples R China
基金
美国国家科学基金会;
关键词
Nuclear mass; Machine learning; Binding energy; Separation energy; GROUND-STATE MASSES; DEFORMATIONS; ENERGY;
D O I
10.1007/s41365-021-00956-1
中图分类号
TL [原子能技术]; O571 [原子核物理学];
学科分类号
0827 ; 082701 ;
摘要
Background: The masses of similar to 2500 nuclei have been measured experimentally; however, >7000 isotopes are predicted to exist in the nuclear landscape from H (Z = 1) to Og (Z = 118) based on various theoretical calculations. Exploring the mass of the remaining isotopes is a popular topic in nuclear physics. Machine learning has served as a powerful tool for learning complex representations of big data in many fields. Purpose: We use Light Gradient Boosting Machine (LightGBM), which is a highly efficient machine learning algorithm, to predict the masses of unknown nuclei and to explore the nuclear landscape on the neutron-rich side from learning the measured nuclear masses. Methods: Several characteristic quantities (e.g., mass number and proton number) are fed into the LightGBM algorithm to mimic the patterns of the residual delta(Z,A) between the experimental binding energy and the theoretical one given by the liquid-drop model (LDM), Duflo-Zucker (DZ, also dubbed DZ28) mass model, finite-range droplet model (FRDM, also dubbed FRDM2012), as well as the Weizsacker-Skyrme (WS4) model to refine these mass models. Results: By using the experimental data of 80% of known nuclei as the training dataset, the root mean square deviations (RMSDs) between the predicted and the experimental binding energy of the remaining 20% are approximately 0.234 +/- 0.022, 0.213 +/- 0.018, 0.170 +/- 0.011, and 0.222 +/- 0.016 MeV for the LightGBM-refined LDM, DZ model, WS4 model, and FRDM, respectively. These values are approximately 90%, 65%, 40%, and 60% smaller than those of the corresponding origin mass models. The RMSD for 66 newly measured nuclei that appeared in AME2020 was also significantly improved. The one-neutron and two-neutron separation energies predicted by these refined models are consistent with several theoretical predictions based on various physical models. In addition, the two-neutron separation energies of several newly measured nuclei (e.g., some isotopes of Ca, Ti, Pm, and Sm) predicted with LightGBM-refined mass models are also in good agreement with the latest experimental data. Conclusions: LightGBM can be used to refine theoretical nuclear mass models and predict the binding energy of unknown nuclei. Moreover, the correlation between the input characteristic quantities and the output can be interpreted by SHapley additive exPlanations (a popular explainable artificial intelligence tool), which may provide new insights for developing theoretical nuclear mass models.
引用
收藏
页数:13
相关论文
共 50 条
  • [11] Simulation and Analysis of the Properties of Linear Structures in the Mass Distribution of Nuclear Reaction Products by Machine Learning Methods
    G. A. Ososkov
    Yu. V. Pyatkov
    M. O. Rudenko
    Physics of Particles and Nuclei Letters, 2021, 18 : 559 - 569
  • [12] Simulation and Analysis of the Properties of Linear Structures in the Mass Distribution of Nuclear Reaction Products by Machine Learning Methods
    Ososkov, G. A.
    Pyatkov, Yu, V
    Rudenko, M. O.
    PHYSICS OF PARTICLES AND NUCLEI LETTERS, 2021, 18 (05) : 559 - 569
  • [13] Machine learning for nuclear cardiology: The way forward
    Sirish Shrestha
    Partho P. Sengupta
    Journal of Nuclear Cardiology, 2019, 26 : 1755 - 1758
  • [14] Machine learning for nuclear cardiology: The way forward
    Shrestha, Sirish
    Sengupta, Partho P.
    JOURNAL OF NUCLEAR CARDIOLOGY, 2019, 26 (05) : 1755 - 1758
  • [15] Physically interpretable machine learning for nuclear masses
    Mohan, A. T.
    Mumpower, M. R.
    Sprouse, T. M.
    Lovell, A. E.
    PHYSICAL REVIEW C, 2022, 106 (02)
  • [16] Nuclear data evaluation augmented by machine learning
    Vicente-Valdez, Pedro
    Bernstein, Lee
    Fratoni, Massimiliano
    ANNALS OF NUCLEAR ENERGY, 2021, 163 (163)
  • [17] Recent Developments in Machine Learning for Mass Spectrometry
    Beck, Armen G.
    Muhoberac, Matthew
    Randolph, Caitlin E.
    Beveridge, Connor H.
    Wijewardhane, Prageeth R.
    Kentta''maa, Hilkka I.
    Chopra, Gaurav
    ACS MEASUREMENT SCIENCE AU, 2024, 4 (03): : 233 - 246
  • [18] Multiwavelength cluster mass estimates and machine learning
    Cohn, J. D.
    Battaglia, Nicholas
    MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2020, 491 (02) : 1575 - 1584
  • [19] Machine learning in analytical spectroscopy for nuclear diagnostics [Invited]
    Rao, Ashwin P.
    Jenkins, Phillip R.
    Pinson, Ryan E.
    Auxier II, John D.
    Shattan, Michael B.
    Patnaik, Anil K.
    APPLIED OPTICS, 2023, 62 (06) : A83 - A109
  • [20] Machine Learning Method in Study of Nuclear Charge Radius
    Dong X.
    Geng L.
    Yuanzineng Kexue Jishu/Atomic Energy Science and Technology, 2023, 57 (04): : 679 - 695