Institutional Repository System Of Yunnan Observatories, CAS
| NNHMC: An Efficient Stokes Inversion Method Using a Neural Network (NN) Model Combined with the Hamiltonian Monte Carlo (HMC) Algorithm | |
Xu C(徐冲)1,2 ; Wang JL(王锦良)1,2; Li, Hao3; Hu, ZiYao2,4; Bai, XianYong2,4; Lin, JiaBen2,4; Liu H(刘辉)1,2; Jin ZY(金振宇)1,2,5; Ji KF(季凯帆)1,2
| |
| 发表期刊 | ASTROPHYSICAL JOURNAL
 |
| 2024-12-01 | |
| 卷号 | 977期号:1 |
| DOI | 10.3847/1538-4357/ad8b2b |
| 产权排序 | 第1完成单位 |
| 收录类别 | SCI |
| 摘要 | The Milne-Eddington (M-E) atmosphere model is commonly adopted in the inversion of the magnetic fields in the solar photosphere. By applying the Levenberg-Marquardt algorithm or training a neural network (NN) model, the magnetic field vector can be quickly inferred from the Stokes profile but lacks reliable and statistically well-defined confidence intervals for parameters. To address this, we present an efficient Bayesian inference method called NNHMC, combining the NN model with the Hamiltonian Monte Carlo (HMC) algorithm. The NN model is used to speedily synthesize batches of synthetic Stokes profiles, accelerating the inference process. The HMC algorithm significantly improves sampling efficiency in high-dimensional parameter spaces and can handle large-scale data sets in batches. The spectropolarimetric observation of an active region obtained by the Hinode/spectropolarimeter (SP) is used to demonstrate the capability of the NNHMC method. The strength, inclination, and azimuth of the magnetic field and the line-of-sight velocity inferred with the NNHMC method are very similar to those derived with the MERLIN code. Furthermore, this study provided posterior distributions and uncertainties for these parameters. A test on the same hardware and software platform shows a speed increase of up to 2.5 orders of magnitude with respect to the traditional Markov Chain Monte Carlo method (without the NN, using the M-E atmosphere model), establishing the NNHMC method as a highly effective tool for Stokes inversion based on Bayesian inference. |
| 资助项目 | the Natural Science Foundation of China[12073077]; the Natural Science Foundation of China[12373115]; Natural Science Foundation of China[202205AG070009]; Yunnan Key Laboratory of Solar Physics and Space Science[202305AS350029]; Yunnan Key Laboratory of Solar Physics and Space Science[202305AT350005]; Yunnan Revitalization Talent Support Program[E4PD3001]; Climbing Program of NSSC[2021YFA1600500]; Climbing Program of NSSC[2021YFA1600503]; National Key R&D Program of China; STFC (UK) |
| 项目资助者 | the Natural Science Foundation of China[12073077, 12373115] ; Natural Science Foundation of China[202205AG070009] ; Yunnan Key Laboratory of Solar Physics and Space Science[202305AS350029, 202305AT350005] ; Yunnan Revitalization Talent Support Program[E4PD3001] ; Climbing Program of NSSC[2021YFA1600500, 2021YFA1600503] ; National Key R&D Program of China ; STFC (UK) |
| 语种 | 英语 |
| 学科领域 | 天文学 ; 太阳与太阳系 ; 计算机科学技术 ; 人工智能 |
| 文章类型 | Article |
| 出版者 | IOP Publishing Ltd |
| 出版地 | TEMPLE CIRCUS, TEMPLE WAY, BRISTOL BS1 6BE, ENGLAND |
| ISSN | 0004-637X |
| URL | 查看原文 |
| WOS记录号 | WOS:001370888700001 |
| WOS研究方向 | Astronomy & Astrophysics |
| WOS类目 | Astronomy & Astrophysics |
| 关键词[WOS] | VECTOR MAGNETIC-FIELDS ; SOLAR OPTICAL TELESCOPE ; PROFILES ; HINODE |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 版本 | 出版稿 |
| 条目标识符 | http://ir.ynao.ac.cn/handle/114a53/27841 |
| 专题 | 天文技术实验室 |
| 作者单位 | 1.Yunnan Observatories, Chinese Academy of Sciences, Kunming 650011, People's Republic of China; [email protected], [email protected]; 2.University of Chinese Academy of Sciences, Beijing 100049, People's Republic of China; 3.Key Laboratory of Solar Activity and Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, 100190, People's Republic of China; 4.National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, People's Republic of China; 5.Yunnan Key Laboratory of Solar Physics and Space Science, Kunming 650216, People's Republic of China |
| 第一作者单位 | 中国科学院云南天文台 |
| 推荐引用方式 GB/T 7714 | Xu C,Wang JL,Li, Hao,et al. NNHMC: An Efficient Stokes Inversion Method Using a Neural Network (NN) Model Combined with the Hamiltonian Monte Carlo (HMC) Algorithm[J]. ASTROPHYSICAL JOURNAL,2024,977(1). |
| APA | 徐冲.,王锦良.,Li, Hao.,Hu, ZiYao.,Bai, XianYong.,...&季凯帆.(2024).NNHMC: An Efficient Stokes Inversion Method Using a Neural Network (NN) Model Combined with the Hamiltonian Monte Carlo (HMC) Algorithm.ASTROPHYSICAL JOURNAL,977(1). |
| MLA | 徐冲,et al."NNHMC: An Efficient Stokes Inversion Method Using a Neural Network (NN) Model Combined with the Hamiltonian Monte Carlo (HMC) Algorithm".ASTROPHYSICAL JOURNAL 977.1(2024). |
| 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 | ||
| NNHMC_ An Efficient （1760KB） | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 请求全文 | |
| 个性服务 |
| 推荐该条目 |
| 保存到收藏夹 |
| 查看访问统计 |
| 导出为Endnote文件 |
| 谷歌学术 |
| 谷歌学术中相似的文章 |
| [徐冲]的文章 |
| [王锦良]的文章 |
| [Li, Hao]的文章 |
| 百度学术 |
| 百度学术中相似的文章 |
| [徐冲]的文章 |
| [王锦良]的文章 |
| [Li, Hao]的文章 |
| 必应学术 |
| 必应学术中相似的文章 |
| [徐冲]的文章 |
| [王锦良]的文章 |
| [Li, Hao]的文章 |
| 相关权益政策 |
| 暂无数据 |
| 收藏/分享 |
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。
修改评论