• NUCLEAR TECHNIQUES
  • Vol. 46, Issue 8, 080009 (2023)
Zepeng GAO1、2 and Qingfeng LI1、3、*
Author Affiliations
  • 1School of Science, Huzhou University, Huzhou 313000, China
  • 2Sino-French Institute of Nuclear Engineering and Technology, Sun Yat-sen University, Zhuhai 519082, China
  • 3Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou 730000, China
  • show less
    DOI: 10.11889/j.0253-3219.2023.hjs.46.080009 Cite this Article
    Zepeng GAO, Qingfeng LI. Studies on several problems in nuclear physics by using machine learning[J]. NUCLEAR TECHNIQUES, 2023, 46(8): 080009 Copy Citation Text show less
    The nuclear symmetry energy (a) and its slope parameter (b) plotted as a function of density
    Fig. 1. The nuclear symmetry energy (a) and its slope parameter (b) plotted as a function of density
    The results of 66 newly measured nuclei appeared in the AME2020 mass evaluation
    Fig. 2. The results of 66 newly measured nuclei appeared in the AME2020 mass evaluation
    Δb dependence of the input grid dimension n
    Fig. 3. Δb dependence of the input grid dimension n
    Number in each cell denotes Δb for the testing data (generated with the vertical labeled mode) by using the training data (generated with the horizontal labeled mode). The left panels (right panels) present the results of the first (second) type of characteristic quantity.
    Fig. 4. Number in each cell denotes Δb for the testing data (generated with the vertical labeled mode) by using the training data (generated with the horizontal labeled mode). The left panels (right panels) present the results of the first (second) type of characteristic quantity.
    Confusion matrix for the five-class classification task
    Fig. 5. Confusion matrix for the five-class classification task
    Distributions of the predicted symmetry energy slope parameter L(ρ0)(a, b) The results obtained with 4 and 30 observables, respectively
    Fig. 6. Distributions of the predicted symmetry energy slope parameter L(ρ0)(a, b) The results obtained with 4 and 30 observables, respectively
    Zepeng GAO, Qingfeng LI. Studies on several problems in nuclear physics by using machine learning[J]. NUCLEAR TECHNIQUES, 2023, 46(8): 080009
    Download Citation