Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning

Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning
复制标题

通过深度学习寻找重离子碰撞中核对称能量的特征

DOI:
10.1016/j.physletb.2021.136669
复制
发表时间:
2021-07
期刊:
影响因子:
4.4
通讯作者:
Zhou Kai
Zhou Kai
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Wang Yongjia;Li Fupeng;Li Qingfeng;Lu Hongliang;Zhou Kai

文献摘要

参考文献

被引文献

相似文献

开发了一种深度卷积神经网络(CNN),通过学习重离子碰撞中质子和中子的二维(横动量和快度)分布与对称能(Esym(ρ))之间的映射,研究对称能效应.利用超相对论量子分子动力学(UrQMD)模型模拟的标记数据集进行监督训练。结果表明,以事件为基础的质子能谱作为输入,由于事件起伏较大,对软、硬Esym(ρ)的分类精度约为60%,而以事件总和质子能谱作为输入,分类精度提高到98%。用质子谱和中子谱进行5标记(5种不同的Esym(ρ))分类的准确率分别为58%和72%。对于回归任务,平均绝对误差(MAE),测量的平均幅度的绝对差异之间的预测和实际L(斜率参数Esym(ρ))的质子和中子谱,分别约为20.4和14.8 MeV。利用卷积神经网络算法可以识别密度相关核对称能对质子和中子横动量和快度分布的指纹。
A deep convolutional neural network (CNN) is developed to study symmetry energy (E sym (ρ)) effects by learning the mapping between the symmetry energy and the two-dimensional (transverse momentum and rapidity) distributions of protons and neutrons in heavy-ion collisions. Supervised training is performed with labeled data-set from the ultrarelativistic quantum molecular dynamics (UrQMD) model simulation. It is found that, by using proton spectra on event-by-event basis as input, the accuracy for classifying the soft and stiff E sym (ρ) is about 60% due to large event-by-event fluctuations, while by setting event-summed proton spectra as input, the classification accuracy increases to 98%. The accuracies for 5-label (5 different E sym (ρ)) classification task are about 58% and 72% by using proton and neutron spectra, respectively. For the regression task, the mean absolute errors (MAE) which measure the average magnitude of the absolute differences between the predicted and actual L (the slope parameter of E sym (ρ)) are about 20.4 and 14.8 MeV by using proton and neutron spectra, respectively. Fingerprints of the density-dependent nuclear symmetry energy on the transverse momentum and rapidity distributions of protons and neutrons can be identified by convolutional neural network algorithm.
在贝叶斯方法中用巨大共振约束等矢量核相互作用
DOI: 10.1016/j.physletb.2020.135820
发表时间: 2020-06
期刊: Physics Letters B
影响因子: 4.4
作者:
Xu Jun;Zhou Jia;Zhang Zhen;Xie Wen-Jie;Li Bao-An
通讯作者: Li Bao-An
DOI: 10.1016/0370-1573(91)90094-3
发表时间: 1991-04
期刊: Physics Reports
影响因子: --
作者:
J. Aichelin
通讯作者: J. Aichelin
DOI: 10.1016/j.physletb.2021.136084
发表时间: 2021-01
期刊: --
影响因子: --
作者:
Y. Song;R. Wang;Y. Ma;X. Deng;H. Liu
通讯作者: Y. Song;R. Wang;Y. Ma;X. Deng;H. Liu
DOI: 10.1016/j.ppnp.2020.103775
发表时间: 2020-03
期刊: arXiv: Nuclear Theory
影响因子: --
作者:
M. Colonna
通讯作者: M. Colonna
DOI: 10.1007/s41365-020-00766-x
发表时间: 2020-05
影响因子: 2.8
作者:
Hao Yu;D. Fang;Yugang Ma
通讯作者: Hao Yu;D. Fang;Yugang Ma