Nuclear mass predictions with multi-hidden-layer feedforward neural network

IF 1.7 4区 物理与天体物理 Q2 PHYSICS, NUCLEAR
Xian-Kai Le, Nan Wang, Xiang Jiang
{"title":"Nuclear mass predictions with multi-hidden-layer feedforward neural network","authors":"Xian-Kai Le,&nbsp;Nan Wang,&nbsp;Xiang Jiang","doi":"10.1016/j.nuclphysa.2023.122707","DOIUrl":null,"url":null,"abstract":"<div><p><span>Based on Keras deep learning<span> framework, the feedforward neural network (FNN) model is employed to improve the predictions of the liquid drop model (LDM). It is shown that the prediction ability of FNN can be significantly improved if multiple hidden layers are used with only four input parameters. The root-mean-square deviation (RMSD) of nuclear mass predicted by LDM can be reduced from 2.38 MeV to 196 keV with the multi-hidden-layer FNN model, which is only one third of the single-hidden-layer FNN model. The predictions of two-neutron separation energies (</span></span><em>S</em><sub>2n</sub>) and single-neutron separation energies (<span><math><msub><mrow><mi>S</mi></mrow><mrow><mi>n</mi></mrow></msub></math></span>) indicate that the multi-hidden-layer FNN model gives a better description of the shell structure. In addition, the extrapolation capability of the model in the super-heavy nuclear region is studied, the results show that better extrapolation capability can be achieved if multiple hidden layers are employed.</p></div>","PeriodicalId":19246,"journal":{"name":"Nuclear Physics A","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Physics A","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0375947423001100","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, NUCLEAR","Score":null,"Total":0}
引用次数: 1

Abstract

Based on Keras deep learning framework, the feedforward neural network (FNN) model is employed to improve the predictions of the liquid drop model (LDM). It is shown that the prediction ability of FNN can be significantly improved if multiple hidden layers are used with only four input parameters. The root-mean-square deviation (RMSD) of nuclear mass predicted by LDM can be reduced from 2.38 MeV to 196 keV with the multi-hidden-layer FNN model, which is only one third of the single-hidden-layer FNN model. The predictions of two-neutron separation energies (S2n) and single-neutron separation energies (Sn) indicate that the multi-hidden-layer FNN model gives a better description of the shell structure. In addition, the extrapolation capability of the model in the super-heavy nuclear region is studied, the results show that better extrapolation capability can be achieved if multiple hidden layers are employed.

基于多隐层前馈神经网络的核质量预测
基于Keras深度学习框架,采用前馈神经网络(FNN)模型来改进液滴模型(LDM)的预测。结果表明,如果只使用四个输入参数使用多个隐藏层,则可以显著提高FNN的预测能力。利用多隐层FNN模型,LDM预测的核质量均方根偏差(RMSD)可以从2.38MeV降低到196keV,仅为单层FNN模型的三分之一。对两个中子分离能(S2n)和单个中子分离能的预测表明,多隐层FNN模型能更好地描述壳层结构。此外,还研究了模型在超重核区的外推能力,结果表明,如果采用多个隐层,可以获得更好的外推能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Nuclear Physics A
Nuclear Physics A 物理-物理:核物理
CiteScore
3.60
自引率
7.10%
发文量
113
审稿时长
61 days
期刊介绍: Nuclear Physics A focuses on the domain of nuclear and hadronic physics and includes the following subsections: Nuclear Structure and Dynamics; Intermediate and High Energy Heavy Ion Physics; Hadronic Physics; Electromagnetic and Weak Interactions; Nuclear Astrophysics. The emphasis is on original research papers. A number of carefully selected and reviewed conference proceedings are published as an integral part of the journal.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信