中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 云南天文台
  3. 中国科学院云南天文台
  4. 天文技术实验室
NNHMC: An Efficient Stokes Inversion Method Using a Neural Network (NN) Model Combined with the Hamiltonian Monte Carlo (HMC) Algorithm

文献类型：期刊论文

作者Xu C(徐冲)4,5; Wang JL(王锦良)4,5; Li, Hao1; Hu, ZiYao2,5; Bai, XianYong2,5; Lin, JiaBen2,5; Liu H(刘辉)4,5; Jin ZY(金振宇)3,4,5; Ji KF(季凯帆)4,5
刊名ASTROPHYSICAL JOURNAL
出版日期2024-12-01
卷号977期号:1
ISSN号0004-637X
DOI10.3847/1538-4357/ad8b2b
产权排序第1完成单位
文献子类Article
英文摘要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.
学科主题天文学 ; 太阳与太阳系 ; 计算机科学技术 ; 人工智能
URL标识查看原文
出版地TEMPLE CIRCUS, TEMPLE WAY, BRISTOL BS1 6BE, ENGLAND
WOS关键词VECTOR MAGNETIC-FIELDS ; SOLAR OPTICAL TELESCOPE ; PROFILES ; HINODE
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)
WOS研究方向Astronomy & Astrophysics
语种英语
WOS记录号WOS:001370888700001
出版者IOP Publishing Ltd
资助机构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)
版本出版稿
源URL[http://ir.ynao.ac.cn/handle/114a53/27841]  
专题天文技术实验室
作者单位1.Key Laboratory of Solar Activity and Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, 100190, People's Republic of China;
2.National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, People's Republic of China;
3.Yunnan Key Laboratory of Solar Physics and Space Science, Kunming 650216, People's Republic of China
4.Yunnan Observatories, Chinese Academy of Sciences, Kunming 650011, People's Republic of China; wangjinliang@ynao.ac.cn, jkf@ynao.ac.cn;
5.University of Chinese Academy of Sciences, Beijing 100049, People's Republic of China;
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).

入库方式： OAI收割

来源：云南天文台

浏览0
下载0
收藏0
其他版本

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。