ShanghaiTech University Knowledge Management System
Enhancing reliability in photonuclear cross-section fitting with Bayesian neural networks | |
2025-03 | |
发表期刊 | NUCLEAR SCIENCE AND TECHNIQUES (IF:3.6[JCR-2023],2.4[5-Year]) |
ISSN | 1001-8042 |
EISSN | 2210-3147 |
卷号 | 36期号:3 |
发表状态 | 已发表 |
DOI | 10.1007/s41365-024-01611-1 |
摘要 | This study investigates photonuclear reaction (gamma,n)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\gamma ,\text {n})$$\end{document} cross-sections using Bayesian neural network (BNN) analysis. After determining the optimal network architecture, which features two hidden layers, each with 50 hidden nodes, training was conducted for 30,000 iterations to ensure comprehensive data capture. By analyzing the distribution of absolute errors positively correlated with the cross-section for the isotope 159\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{159}$$\end{document}Tb, as well as the relative errors unrelated to the cross-section, we confirmed that the network effectively captured the data features without overfitting. Comparison with the TENDL-2021 Database demonstrated the BNN's reliability in fitting photonuclear cross-sections with lower average errors. The predictions for nuclei with single and double giant dipole resonance peak cross-sections, the accurate determination of the photoneutron reaction threshold in the low-energy region, and the precise description of trends in the high-energy cross-sections further demonstrate the network's generalization ability on the validation set. This can be attributed to the consistency of the training data. By using consistent training sets from different laboratories, Bayesian neural networks can predict nearby unknown cross-sections based on existing laboratory data, thereby estimating the potential differences between other laboratories' existing data and their own measurement results. Experimental measurements of photonuclear reactions on the newly constructed SLEGS beamline will contribute to clarifying the differences in cross-sections within the existing data. |
关键词 | Photoneutron reaction Bayesian neural network Machine learning Gamma source SLEGS |
URL | 查看原文 |
收录类别 | SCI ; EI |
语种 | 英语 |
资助项目 | National key research and development program[2022YFA1602404] ; National Natural Science Foundation of China[ |
WOS研究方向 | Nuclear Science & Technology ; Physics |
WOS类目 | Nuclear Science & Technology ; Physics, Nuclear |
WOS记录号 | WOS:001421771800003 |
出版者 | SPRINGER SINGAPORE PTE LTD |
EI入藏号 | 20250817931061 |
EI主题词 | Multilayer neural networks |
EI分类号 | 1101 Artificial Intelligence - 1301.1.3 Atomic and Molecular Physics - 1301.2.1 High Energy Physics - 1301.2.1.1.1 Hadron Colliders - 1301.2.2 Nuclear Physics |
原始文献类型 | Journal article (JA) |
文献类型 | 期刊论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/493522 |
专题 | 物质科学与技术学院 物质科学与技术学院_博士生 |
通讯作者 | Sun, Qian-Kun; Zhang, Yue; Wang, Hong-Wei |
作者单位 | 1.Chinese Acad Sci, Shanghai Inst Appl Phys, Shanghai 201800, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Shanghai Adv Res Inst, Shanghai 201210, Peoples R China 4.ZhengZhou Univ, Sch Phys & Microelect, Zhengzhou 450001, Peoples R China 5.ShanghaiTech Univ, Sch Phys Sci & Technol, Shanghai 201210, Peoples R China |
推荐引用方式 GB/T 7714 | Sun, Qian-Kun,Zhang, Yue,Hao, Zi-Rui,et al. Enhancing reliability in photonuclear cross-section fitting with Bayesian neural networks[J]. NUCLEAR SCIENCE AND TECHNIQUES,2025,36(3). |
APA | Sun, Qian-Kun.,Zhang, Yue.,Hao, Zi-Rui.,Wang, Hong-Wei.,Fan, Gong-Tao.,...&Wang, Zhen-Wei.(2025).Enhancing reliability in photonuclear cross-section fitting with Bayesian neural networks.NUCLEAR SCIENCE AND TECHNIQUES,36(3). |
MLA | Sun, Qian-Kun,et al."Enhancing reliability in photonuclear cross-section fitting with Bayesian neural networks".NUCLEAR SCIENCE AND TECHNIQUES 36.3(2025). |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
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。