利用机器学习方法对几个核物理问题的深入研究  

Studies on several problems in nuclear physics by using machine learning

作　　者：高泽鹏 李庆峰[1,3] GAO Zepeng;LI Qingfeng(School of Science,Huzhou University,Huzhou 313000,China;Sino-French Institute of Nuclear Engineering and Technology,Sun Yat-sen University,Zhuhai 519082,China;Institute of Modern Physics,Chinese Academy of Sciences,Lanzhou 730000,China)

机构地区：[1]湖州师范学院理学院,湖州313000 [2]中山大学中法核工程与技术学院,珠海519082 [3]中国科学院近代物理研究所,兰州730000

出　　处：《核技术》2023年第8期88-95,共8页Nuclear Techniques

基　　金：国家自然科学基金(No.11875125,No.12147219);国家重点研发计划(No.2020YFE0202002)资助。

摘　　要：机器学习能够从大量复杂的数据中挖掘其内在的关联,近些年被广泛应用在科学研究中。本文分别评估了两类机器学习算法在修正核质量、重构重离子反应碰撞参数以及提取对称能斜率系数等热点问题上的表现,并讨论了机器学习模型的外推能力和泛化能力。结果表明:机器学习方法在三个核物理问题的研究中均体现出强大的能力。将机器学习方法应用于核物理问题的研究中可以进一步探索新物理,从而更好地推动理论和实验的发展。[Background]Machine learning,which has been widely applied to scientific research in recent years,can be used to investigate the inherent correlations within a large number of complex data.[Purpose]We evaluate the performances of two types of machine-learning algorithms for correcting nuclear mass models,reconstructing the impact parameter in heavy-ion collisions,and extracting the symmetry energy slope parameter.We also discuss the extrapolation and generalization ability of the machine-learning models.[Method]For correcting the nuclear mass models,10 characteristic quantities are fed into the LightGBM to mimic the residual between the experimental and the theoretical binding energies.For impact parameter or symmetry energy,two types of observables constructed based on the particle information simulated by using the UrQMD transport model for setting up the different impact parameters or symmetry energy slope parameters are used as inputs to a conventional neural network and the LightGBM to extract the original information.[Result]Analysis of these nuclear physics problems reveals the potential applicability of machine-learning methods.[Conclusions]Machine-learning methods can be used to investigate new physical problems,thereby promoting the development of both theory and experiment.

关 键 词：机器学习 原子核质量 碰撞参数 对称能 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] O571.6[自动化与计算机技术—控制科学与工程]