Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach
Deuteron separation energy is not only the basis for validating the nuclear mass models and nucleon-nucleon interaction potential, but also can determine the stability of a nuclide to certain extent. Bayesian neural network (BNN) approach, which has strong predictive power and can naturally give the...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Board of Atomic Energy Science and Technology
2023-04-01
|
| Series: | Yuanzineng kexue jishu |
| Subjects: | |
| Online Access: | https://www.aest.org.cn/CN/10.7538/yzk.2022.youxian.0858 |
| _version_ | 1827954282715938816 |
|---|---|
| author | XING Kang;LIANG Yan;SUN Xiaojun |
| author_facet | XING Kang;LIANG Yan;SUN Xiaojun |
| author_sort | XING Kang;LIANG Yan;SUN Xiaojun |
| collection | DOAJ |
| description | Deuteron separation energy is not only the basis for validating the nuclear mass models and nucleon-nucleon interaction potential, but also can determine the stability of a nuclide to certain extent. Bayesian neural network (BNN) approach, which has strong predictive power and can naturally give theoretical errors of predicted values, had been successfully applied to study the different kinds of separations except the deuteron separation. In this paper, several typical nuclear mass models, such as macroscopic model BW2, macroscopic-microscopic model WS4, and microscopic model HFB-31, are chosen to study the deuteron separation energy combining BNN approach. The root-mean-square deviations of these models are partly reduced. In addition, the inclusion of physical parameters related to the pair and shell effects in the input layer can further improve the theoretical accuracy for the deuteron separation energy. The results show that the theoretical predictions are more reliable as more physical features of BNN approach are included. |
| first_indexed | 2024-04-09T14:27:43Z |
| format | Article |
| id | doaj.art-ea3b1fe394924f65a818503af2171191 |
| institution | Directory Open Access Journal |
| issn | 1000-6931 |
| language | English |
| last_indexed | 2024-04-09T14:27:43Z |
| publishDate | 2023-04-01 |
| publisher | Editorial Board of Atomic Energy Science and Technology |
| record_format | Article |
| series | Yuanzineng kexue jishu |
| spelling | doaj.art-ea3b1fe394924f65a818503af21711912023-05-04T02:09:16ZengEditorial Board of Atomic Energy Science and TechnologyYuanzineng kexue jishu1000-69312023-04-0157471372010.7538/yzk.2022.youxian.0858Study of Deuteron Separation Energy Based on Bayesian Neural Network ApproachXING Kang;LIANG Yan;SUN Xiaojun 0College of Physics and Technology, Guangxi Normal University; Guangxi Key Laboratory of Nuclear Physics and Technology, Guangxi Normal UniversityDeuteron separation energy is not only the basis for validating the nuclear mass models and nucleon-nucleon interaction potential, but also can determine the stability of a nuclide to certain extent. Bayesian neural network (BNN) approach, which has strong predictive power and can naturally give theoretical errors of predicted values, had been successfully applied to study the different kinds of separations except the deuteron separation. In this paper, several typical nuclear mass models, such as macroscopic model BW2, macroscopic-microscopic model WS4, and microscopic model HFB-31, are chosen to study the deuteron separation energy combining BNN approach. The root-mean-square deviations of these models are partly reduced. In addition, the inclusion of physical parameters related to the pair and shell effects in the input layer can further improve the theoretical accuracy for the deuteron separation energy. The results show that the theoretical predictions are more reliable as more physical features of BNN approach are included.https://www.aest.org.cn/CN/10.7538/yzk.2022.youxian.0858bayesian neural networkdeuteron separation energy |
| spellingShingle | XING Kang;LIANG Yan;SUN Xiaojun Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach Yuanzineng kexue jishu bayesian neural network deuteron separation energy |
| title | Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach |
| title_full | Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach |
| title_fullStr | Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach |
| title_full_unstemmed | Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach |
| title_short | Study of Deuteron Separation Energy Based on Bayesian Neural Network Approach |
| title_sort | study of deuteron separation energy based on bayesian neural network approach |
| topic | bayesian neural network deuteron separation energy |
| url | https://www.aest.org.cn/CN/10.7538/yzk.2022.youxian.0858 |
| work_keys_str_mv | AT xingkangliangyansunxiaojun studyofdeuteronseparationenergybasedonbayesianneuralnetworkapproach |