通过机器学习的高斯过程可靠计算核结合能

IF 3.6 1区 物理与天体物理 Q1 NUCLEAR SCIENCE & TECHNOLOGY Nuclear Science and Techniques Pub Date : 2024-06-18 DOI:10.1007/s41365-024-01463-9
Zi-Yi Yuan, Dong Bai, Zhen Wang, Zhong-Zhou Ren
{"title":"通过机器学习的高斯过程可靠计算核结合能","authors":"Zi-Yi Yuan, Dong Bai, Zhen Wang, Zhong-Zhou Ren","doi":"10.1007/s41365-024-01463-9","DOIUrl":null,"url":null,"abstract":"<p>Reliable calculations of nuclear binding energies are crucial for advancing the research of nuclear physics. Machine learning provides an innovative approach to exploring complex physical problems. In this study, the nuclear binding energies are modeled directly using a machine-learning method called the Gaussian process. First, the binding energies for 2238 nuclei with <span>\\(Z &gt; 20\\)</span> and <span>\\(N &gt; 20\\)</span> are calculated using the Gaussian process in a physically motivated feature space, yielding an average deviation of 0.046 MeV and a standard deviation of 0.066 MeV. The results show the good learning ability of the Gaussian process in the studies of binding energies. Then, the predictive power of the Gaussian process is studied by calculating the binding energies for 108 nuclei newly included in AME2020. The theoretical results are in good agreement with the experimental data, reflecting the good predictive power of the Gaussian process. Moreover, the <span>\\(\\alpha\\)</span>-decay energies for 1169 nuclei with <span>\\(50 \\le Z \\le 110\\)</span> are derived from the theoretical binding energies calculated using the Gaussian process. The average deviation and the standard deviation are, respectively, 0.047 MeV and 0.070 MeV. Noticeably, the calculated <span>\\(\\alpha\\)</span>-decay energies for the two new isotopes <span>\\(^{204}\\)</span>Ac (Huang et al. Phys Lett B <b>834</b>, 137484 (2022)) and <span>\\(^{207}\\)</span>Th (Yang et al. Phys Rev C <b>105</b>, L051302 (2022)) agree well with the latest experimental data. These results demonstrate that the Gaussian process is reliable for the calculations of nuclear binding energies. Finally, the <span>\\(\\alpha\\)</span>-decay properties of some unknown actinide nuclei are predicted using the Gaussian process. The predicted results can be useful guides for future research on binding energies and <span>\\(\\alpha\\)</span>-decay properties.</p>","PeriodicalId":19177,"journal":{"name":"Nuclear Science and Techniques","volume":"102 1","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Reliable calculations of nuclear binding energies by the Gaussian process of machine learning\",\"authors\":\"Zi-Yi Yuan, Dong Bai, Zhen Wang, Zhong-Zhou Ren\",\"doi\":\"10.1007/s41365-024-01463-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Reliable calculations of nuclear binding energies are crucial for advancing the research of nuclear physics. Machine learning provides an innovative approach to exploring complex physical problems. In this study, the nuclear binding energies are modeled directly using a machine-learning method called the Gaussian process. First, the binding energies for 2238 nuclei with <span>\\\\(Z &gt; 20\\\\)</span> and <span>\\\\(N &gt; 20\\\\)</span> are calculated using the Gaussian process in a physically motivated feature space, yielding an average deviation of 0.046 MeV and a standard deviation of 0.066 MeV. The results show the good learning ability of the Gaussian process in the studies of binding energies. Then, the predictive power of the Gaussian process is studied by calculating the binding energies for 108 nuclei newly included in AME2020. The theoretical results are in good agreement with the experimental data, reflecting the good predictive power of the Gaussian process. Moreover, the <span>\\\\(\\\\alpha\\\\)</span>-decay energies for 1169 nuclei with <span>\\\\(50 \\\\le Z \\\\le 110\\\\)</span> are derived from the theoretical binding energies calculated using the Gaussian process. The average deviation and the standard deviation are, respectively, 0.047 MeV and 0.070 MeV. Noticeably, the calculated <span>\\\\(\\\\alpha\\\\)</span>-decay energies for the two new isotopes <span>\\\\(^{204}\\\\)</span>Ac (Huang et al. Phys Lett B <b>834</b>, 137484 (2022)) and <span>\\\\(^{207}\\\\)</span>Th (Yang et al. Phys Rev C <b>105</b>, L051302 (2022)) agree well with the latest experimental data. These results demonstrate that the Gaussian process is reliable for the calculations of nuclear binding energies. Finally, the <span>\\\\(\\\\alpha\\\\)</span>-decay properties of some unknown actinide nuclei are predicted using the Gaussian process. The predicted results can be useful guides for future research on binding energies and <span>\\\\(\\\\alpha\\\\)</span>-decay properties.</p>\",\"PeriodicalId\":19177,\"journal\":{\"name\":\"Nuclear Science and Techniques\",\"volume\":\"102 1\",\"pages\":\"\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2024-06-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nuclear Science and Techniques\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1007/s41365-024-01463-9\",\"RegionNum\":1,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"NUCLEAR SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Science and Techniques","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1007/s41365-024-01463-9","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NUCLEAR SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

可靠的核结合能计算对于推动核物理研究至关重要。机器学习为探索复杂的物理问题提供了一种创新方法。在这项研究中,使用一种名为高斯过程的机器学习方法直接对核结合能进行建模。首先,利用高斯过程在物理激励的特征空间中计算了2238个具有\(Z >20\)和\(N >20\)的原子核的结合能,得出平均偏差为0.046 MeV,标准偏差为0.066 MeV。结果表明,高斯过程在结合能研究中具有良好的学习能力。然后,通过计算新纳入 AME2020 的 108 个原子核的结合能,研究了高斯过程的预测能力。理论结果与实验数据十分吻合,反映了高斯过程良好的预测能力。此外,利用高斯过程计算的理论结合能还得出了1169个原子核的α衰变能。平均偏差和标准偏差分别为 0.047 MeV 和 0.070 MeV。值得注意的是,两种新同位素 \(^{204}\)Ac (Huang et al. Phys Lett B 834, 137484 (2022))和 \(^{207}\)Th (Yang et al. Phys Rev C 105, L051302 (2022))的\(α\)-衰变能与最新的实验数据吻合得很好。这些结果表明高斯过程对于核结合能的计算是可靠的。最后,利用高斯过程预测了一些未知锕系元素核的(α)衰变特性。这些预测结果可以为今后研究结合能和(\α)衰变特性提供有用的指导。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Reliable calculations of nuclear binding energies by the Gaussian process of machine learning

Reliable calculations of nuclear binding energies are crucial for advancing the research of nuclear physics. Machine learning provides an innovative approach to exploring complex physical problems. In this study, the nuclear binding energies are modeled directly using a machine-learning method called the Gaussian process. First, the binding energies for 2238 nuclei with \(Z > 20\) and \(N > 20\) are calculated using the Gaussian process in a physically motivated feature space, yielding an average deviation of 0.046 MeV and a standard deviation of 0.066 MeV. The results show the good learning ability of the Gaussian process in the studies of binding energies. Then, the predictive power of the Gaussian process is studied by calculating the binding energies for 108 nuclei newly included in AME2020. The theoretical results are in good agreement with the experimental data, reflecting the good predictive power of the Gaussian process. Moreover, the \(\alpha\)-decay energies for 1169 nuclei with \(50 \le Z \le 110\) are derived from the theoretical binding energies calculated using the Gaussian process. The average deviation and the standard deviation are, respectively, 0.047 MeV and 0.070 MeV. Noticeably, the calculated \(\alpha\)-decay energies for the two new isotopes \(^{204}\)Ac (Huang et al. Phys Lett B 834, 137484 (2022)) and \(^{207}\)Th (Yang et al. Phys Rev C 105, L051302 (2022)) agree well with the latest experimental data. These results demonstrate that the Gaussian process is reliable for the calculations of nuclear binding energies. Finally, the \(\alpha\)-decay properties of some unknown actinide nuclei are predicted using the Gaussian process. The predicted results can be useful guides for future research on binding energies and \(\alpha\)-decay properties.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Nuclear Science and Techniques
Nuclear Science and Techniques 物理-核科学技术
CiteScore
5.10
自引率
39.30%
发文量
141
审稿时长
5 months
期刊介绍: Nuclear Science and Techniques (NST) reports scientific findings, technical advances and important results in the fields of nuclear science and techniques. The aim of this periodical is to stimulate cross-fertilization of knowledge among scientists and engineers working in the fields of nuclear research. Scope covers the following subjects: • Synchrotron radiation applications, beamline technology; • Accelerator, ray technology and applications; • Nuclear chemistry, radiochemistry, radiopharmaceuticals, nuclear medicine; • Nuclear electronics and instrumentation; • Nuclear physics and interdisciplinary research; • Nuclear energy science and engineering.
期刊最新文献
Properties of the phase diagram from the Nambu-Jona-Lasino model with a scalar-vector interaction In-beam gamma rays of CSNS Back-n characterized by black resonance filter Analysis of level structure and monopole effects in Ca isotopes Highly coupled off-resonance lattice design in diffraction-limited light sources Possibility of reaching the predicted center of the “island of stability” via the radioactive beam-induced fusion reactions
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1