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

doi:10.1016/j.physletb.2021.136669

	Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning
	Wang, Yongjia 3; Li, Fupeng 2,3; Li, Qingfeng 1,3; Lu, Hongliang 5; Zhou, Kai 4
刊名	PHYSICS LETTERS B
	2021-11-10
卷号	822 页码:5
ISSN号	0370-2693
DOI	10.1016/j.physletb.2021.136669
通讯作者	Wang, Yongjia(wangyongjia@zjhu.edu.cn) ; Li, Qingfeng(liqf@zjhu.edu.cn)
英文摘要	A deep convolutional neural network (CNN) is developed to study symmetry energy (E-sym(rho)) 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(rho) 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(rho)) 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(rho)) 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. (C) 2021 The Author(s). Published by Elsevier B.V.
资助项目	National Natural Science Foundation of China[U2032145] ; National Natural Science Foundation of China[11875125] ; National Natural Science Foundation of China[12047568] ; National Key Research and Development Program of China[2020YFE0202002] ; BMBF under the ErUM-Data project ; Ten Thousand Talents Program of Zhejiang province[2018R52017] ; AI grant at FIAS of SAMSON AG, Frankfurt
WOS关键词	IMPACT PARAMETER DETERMINATION ; QUANTUM MOLECULAR-DYNAMICS ; NEURAL-NETWORKS ; EQUATION ; STATE ; PROGRESS ; PHYSICS
WOS研究方向	Astronomy & Astrophysics ; Physics
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000703669100018
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program of China ; BMBF under the ErUM-Data project ; Ten Thousand Talents Program of Zhejiang province ; AI grant at FIAS of SAMSON AG, Frankfurt
内容类型	期刊论文
源URL	[http://119.78.100.186/handle/113462/136294]
专题	中国科学院近代物理研究所
通讯作者	Wang, Yongjia; Li, Qingfeng
作者单位	1.Chinese Acad Sci, Inst Modern Phys, Lanzhou 730000, Peoples R China 2.Zhejiang Univ Technol, Sch Sci, Hangzhou 310014, Peoples R China 3.Huzhou Univ, Sch Sci, Huzhou 313000, Peoples R China 4.Frankfurt Inst Adv Studies, Ruth Moufang Str 1, D-60438 Frankfurt, Germany 5.Huawei Technol Co Ltd, HiSilicon Res Dept, Shenzhen 518000, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yongjia,Li, Fupeng,Li, Qingfeng,et al. Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning[J]. PHYSICS LETTERS B,2021,822:5.
APA	Wang, Yongjia,Li, Fupeng,Li, Qingfeng,Lu, Hongliang,&Zhou, Kai.(2021).Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning.PHYSICS LETTERS B,822,5.
MLA	Wang, Yongjia,et al."Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning".PHYSICS LETTERS B 822(2021):5.