摘要: Recent reactor antineutrino experiments have observed that the neutrino spectrum changes with the reactor core evolution and that the individual fissile isotope antineutrino spectra can be decomposed from the evolving data, providing valuable information for the reactor model and data inconsistent problems. We propose a machine learning method by building a convolutional neural network based on a virtual experiment with a typical short-baseline reactor antineutrino experiment configuration: by utilizing the reactor evolution information, the major fissile isotope spectra are correctly extracted, and the uncertainties are evaluated using the Monte Carlo method. Validation tests show that the method is unbiased and introduces tiny extra uncertainties.
-
来自:
Yuda Zeng
-
链接:
https://link.springer.com/article/10.1007/s41365-023-01229-9
-
期刊:
Nuclar Scinece and Techniques
-
分类:
核科学技术
>>
裂变堆工程技术
-
说明:
该版本为论文定稿,已被 Nuclar Scinece and Techniques 期刊所接收,并在 Springer 出版。
-
投稿状态:
已在期刊出版
-
引用:
ChinaXiv:202306.00011
(或此版本
ChinaXiv:202306.00011V1)
DOI:10.12074/202306.00011V1
CSTR:32003.36.ChinaXiv.202306.00011.V1
- 推荐引用方式:
Zeng, Yuda,Wang, Jun,Zhao, Rong,An, Fengpeng,Xiao, Xiang,Hor, Yuenkeung,Wang, Wei.(2023).Decomposition of fissile isotope antineutrino spectra using convolutional neural network.Nuclar Scinece and Techniques.doi:10.12074/202306.00011V1
(点此复制)