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
  • [1] Machine learning the nuclear mass
    Ze-Peng Gao
    Yong-Jia Wang
    Hong-Liang Lü
    Qing-Feng Li
    Cai-Wan Shen
    Ling Liu
    NuclearScienceandTechniques, 2021, 32 (10) : 73 - 85
  • [2] Machine learning the nuclear mass
    Ze-Peng Gao
    Yong-Jia Wang
    Hong-Liang Lü
    Qing-Feng Li
    Cai-Wan Shen
    Ling Liu
    Nuclear Science and Techniques, 2021, 32
  • [3] Correction to: Machine learning the nuclear mass
    Ze-Peng Gao
    Yong-Jia Wang
    Hong-Liang Lü
    Qing-Feng Li
    Cai-Wan Shen
    Ling Liu
    Nuclear Science and Techniques, 2021, 32 (11)
  • [4] Nuclear mass predictions using machine learning models
    Yuksel, Esra
    Soydaner, Derya
    Bahtiyar, Huseyin
    PHYSICAL REVIEW C, 2024, 109 (06)
  • [5] Machine learning the nuclear mass (vol 32, 109, 2021)
    Gao, Ze-Peng
    Wang, Yong-Jia
    Lu, Hong-Liang
    Li, Qing-Feng
    Shen, Cai-Wan
    Liu, Ling
    NUCLEAR SCIENCE AND TECHNIQUES, 2021, 32 (11)
  • [6] Machine learning in nuclear materials research
    Morgan, Dane
    Pilania, Ghanshyam
    Couet, Adrien
    Uberuaga, Blas P.
    Sun, Cheng
    Li, Ju
    CURRENT OPINION IN SOLID STATE & MATERIALS SCIENCE, 2022, 26 (02):
  • [7] Machine learning applications in nuclear physics
    He WanBing
    He JunJie
    Wang Rui
    Ma YuGang
    SCIENTIA SINICA-PHYSICA MECHANICA & ASTRONOMICA, 2022, 52 (05)
  • [8] Colloquium: Machine learning in nuclear physics
    Boehnlein, Amber
    Diefenthaler, Markus
    Sato, Nobuo
    Schram, Malachi
    Ziegler, Veronique
    Fanelli, Cristiano
    Hjorth-Jensen, Morten
    Horn, Tanja
    Kuchera, Michelle P.
    Lee, Dean
    Nazarewicz, Witold
    Ostroumov, Peter
    Orginos, Kostas
    Poon, Alan
    Wang, Xin-Nian
    Scheinker, Alexander
    Smith, Michael S.
    Pang, Long-Gang
    REVIEWS OF MODERN PHYSICS, 2022, 94 (03)
  • [9] MACHINE LEARNING NUCLEAR DETONATION FEATURES
    Schmitt, Daniel T.
    Peterson, Gilbert L.
    2014 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2014,
  • [10] Nuclear mass predictions with machine learning reaching the accuracy required by r-process studies
    Niu, Z. M.
    Liang, H. Z.
    PHYSICAL REVIEW C, 2022, 106 (02)