摘要
机器学习已经在生物、医学、生产等多个领域广泛应用并展现了其优势.最近,机器学习在物理领域也开始逐渐兴起并展现出其独特的优点.该文旨在探索机器学习在强子物理中的应用潜力.作者以隐粲五夸克态Pc(4312)、Pc(4440)和Pc(4457)为例,在强子分子态图像下研究它们的性质.研究表明,神经网络方法和基于χ2的拟合方法都能够阐明基于领头阶接触势的基本物理性质.然而,χ2拟合方法无法区分Pc(4440)和Pc(4457)的量子数,神经网络方法则可以.由此,作者进一步分析了每个实验数据点对于神经网络预测的影响,以及在拟合方法中每个数据点对于关键物理参数的重要性.通过对比研究,作者发现神经网络方法可以多维度地利用实验数据信息,在强子物理中具有巨大的应用前景.
作者
张振宇
刘家豪
胡继峰
王倩
Ulf-G.Meißner
Zhenyu Zhang;Jiahao Liu;Jifeng Hu;Qian Wang;Ulf-G.Meißner(Guangdong Provincial Key Laboratory of Nuclear Science,Institute of Quantum Matter,South China Normal University,Guangzhou 510006,China;Guangdong-Hong Kong Joint Laboratory of Quantum Matter,Southern Nuclear Science Computing Center,South China Normal University,Guangzhou 510006,China;Helmholtz-Institut für Strahlen-und Kernphysik and Bethe Center for Theoretical Physics,Universität Bonn,Bonn D-53115,Germany;Institute for Advanced Simulation,Institut für Kernphysik and Jülich Center for Hadron Physics,Forschungszentrum Jülich,Jïlich D-52425,Germany;Tbilisi State University,Tbilisi 0186,Georgia)
基金
partly supported by the National Natural Science Foundation of China(NSFC,12035007)
Guangdong Provincial funding(2019QN01X172)
Guangdong Major Project of Basic and Applied Basic Research(2020B0301030008)
supported by the NSFC(12070131001)
the Deutsche Forschungsgemeinschaft(DFG,German Research Foundation,Project-ID 196253076-TRR110)through the funds provided to the Sino-German Collaborative Research Center TRR110"Symmetries and the Emergence of Structure in QCD"
supported by the Chinese Academy of Sciences(CAS)President’s International Fellowship Initiative(PIFI)(2018DM0034)
Volkswagen Stiftung(93562)。
