Taming nucleon density distributions with deep neural network | |
Yang, Zu-Xing1,2,3; Fan, Xiao-Hua4; Yin, Peng1,5; Zuo, Wei1,2 | |
刊名 | PHYSICS LETTERS B |
2021-12-10 | |
卷号 | 823页码:7 |
ISSN号 | 0370-2693 |
DOI | 10.1016/j.physletb.2021.136650 |
通讯作者 | Yang, Zu-Xing(yangzuxing16@impcas.ac.cn) ; Fan, Xiao-Hua(fanxiaohua@swu.edu.cn) ; Zuo, Wei(zuowei@impcas.ac.cn) |
英文摘要 | With the datasets of the density distributions calculated by Skyrme density functional theories, we elaborated deep neural networks to generate the density profile and provide a table of related hyperparameters set for similar applications of other structural models. In the process of machine learning with the objective/target functions that normalized mean square error and Kullback-Leibler divergence (cross entropy), there is a turning point showing the transition from the Fermi-like distribution to the realistic Skyrme distribution, while this property is transcended when Pearson chi(2) divergence is employed. A training program of about 35 minutes with only about 5% - 10% nuclei (200 - 300) is sufficient to describe the nucleon density distributions of all the nuclear chart within 2% relative error. We obtain similar results employing different datasets calculated by different Skyrme density functional theories. We further investigate the extrapolation properties, which show that an addition of 15 nucleons is acceptable. Based on the results, we propose a mixed dataset approach and a retraining approach in order to go beyond a single physical structure model. (C) 2021 The Authors. Published by Elsevier B.V. |
资助项目 | Key Research Program of the Chinese Academy of Sciences[XDPB15] ; National Natural Science Foundation of China[11975282] ; National Natural Science Foundation of China[11705240] ; National Natural Science Foundation of China[12005175] ; National Natural Science Foundation of China[11435014] ; 973 Program of China[2013CB834405] ; CUSTIPEN (China-U.S. Theory Institute for Physics with Exotic Nuclei) - U.S. Department of Energy, office of Science[DE-SC0009971] ; Fundamental Research Funds for the Central Universities[SWU119076] |
WOS关键词 | ELECTRON-SCATTERING ; MODEL |
WOS研究方向 | Astronomy & Astrophysics ; Physics |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000710220700008 |
资助机构 | Key Research Program of the Chinese Academy of Sciences ; National Natural Science Foundation of China ; 973 Program of China ; CUSTIPEN (China-U.S. Theory Institute for Physics with Exotic Nuclei) - U.S. Department of Energy, office of Science ; Fundamental Research Funds for the Central Universities |
内容类型 | 期刊论文 |
源URL | [http://119.78.100.186/handle/113462/136091] |
专题 | 中国科学院近代物理研究所 |
通讯作者 | Yang, Zu-Xing; Fan, Xiao-Hua; Zuo, Wei |
作者单位 | 1.Chinese Acad Sci, Inst Modern Phys, Lanzhou 730000, Peoples R China 2.Univ Chinese Acad Sci, Sch Nucl Sci & Technol, Beijing 100049, Peoples R China 3.RIKEN Nishina Ctr, Wako, Saitama 3510198, Japan 4.Southwest Univ, Sch Phys Sci & Technol, Chongqing 400715, Peoples R China 5.Iowa State Univ, Dept Phys & Astron, Ames, IA 50011 USA |
推荐引用方式 GB/T 7714 | Yang, Zu-Xing,Fan, Xiao-Hua,Yin, Peng,et al. Taming nucleon density distributions with deep neural network[J]. PHYSICS LETTERS B,2021,823:7. |
APA | Yang, Zu-Xing,Fan, Xiao-Hua,Yin, Peng,&Zuo, Wei.(2021).Taming nucleon density distributions with deep neural network.PHYSICS LETTERS B,823,7. |
MLA | Yang, Zu-Xing,et al."Taming nucleon density distributions with deep neural network".PHYSICS LETTERS B 823(2021):7. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论