Transfer learning and neural networks in predicting quadrupole deformation  

作　　者：原林 李佳星 张鸿飞 Yuan Lin;Jia-Xing Li;Hong-Fei Zhang(School of Science,Xi'an Polytechnic University,Xi'an 710048,China;Engineering Research Center of Flexible Radiation Protection Technology,Universities of Shaanxi Province,Xi'an 710048,China;Xi'an Key Laboratory of Nuclear Protection Textile Equipment Technology,Xi'an 710048,China;School of Physics,Xi'an Jiaotong University,Xi'an 710049,China;School of Nuclear Science and Technology,Lanzhou University,Lanzhou 730000,China)

机构地区：[1]School of Science,Xi'an Polytechnic University,Xi'an 710048,China [2]Engineering Research Center of Flexible Radiation Protection Technology,Universities of Shaanxi Province,Xi'an 710048,China [3]Xi'an Key Laboratory of Nuclear Protection Textile Equipment Technology,Xi'an 710048,China [4]School of Physics,Xi'an Jiaotong University,Xi'an 710049,China [5]School of Nuclear Science and Technology,Lanzhou University,Lanzhou 730000,China

出　　处：《Chinese Physics C》2024年第6期162-168,共7页中国物理C（英文版）

基　　金：Supported by the National Natural Science Foundation of China(12175170,11675066)。

摘　　要：Accurately determining the quadrupole deformation parameters of atomic nuclei is crucial for understanding their structural and dynamic properties.This study introduces an innovative approach that combines transfer learning techniques with neural networks to predict the quadrupole deformation parameters of even-even nuclei.With the application of this innovative technique,the quadrupole deformation parameters of 2331 even-even nuclei are successfully predicted within the nuclear region defined by proton numbers 8≤Z≤134 and neutron numbers N≥8.Additionally,we discuss the impact of nuclear quadrupole deformation parameters on the capture cross-sections in heavy-ion fusion reactions,reconstructing the capture cross-sections for the reactions ^(48)Ca+^(244)Pu and ^(48)Ca+^(248)Cm.This research offers new insights into the application of neural networks in nuclear physics and highlights the potential of merging advanced machine learning techniques with both theoretical and experimental data,particularly in fields where experimental data are limited.

关 键 词：nuclear deformation neural networks transfer learning heavy-ion fusion reactions 

分 类 号：O571[理学—粒子物理与原子核物理] TP183[理学—物理]