Currently, data-driven models of solar activity forecast are investigated extensively by using machine learning. For model training, it is highly demanded to establish a large database which may contain observations coming from different instruments with different spatio-temporal resolutions. In this paper, we employ deep learning models for super-resolution (SR) of magnetogram of Michelson Doppler Imager (MDI) in order to achieve the same spatial resolution of Helioseismic and Magnetic Imager (HMI). First, a generative adversarial network (GAN) is designed to transfer characteristics of MDI onto downscaled HMI, getting low-resolution HMI magnetogram in the same domain as MDI. Then, with the paired low-resolution and high-resolution HMI magnetograms, another GAN is trained in a supervised learning way, which consists of two streams, one is for generating high-fidelity image content, the other is explicitly optimized for generating elaborate image gradients. Thus, these two streams work together to guarantee both high-fidelity and photorealistic super-resolved images. Experimental results demonstrate that the proposed method can generate super-resolved magnetograms with perceptual-pleasant visual quality. Meanwhile, the best PSNR, LPIPS, RMSE, comparable SSIM and CC are obtained by the proposed method. The source code and data set can be accessed via .

Fengping Dou;Long Xu;Zhixiang Ren;Dong Zhao;Xinze Zhang

State Key Laboratory of Space Weather,National Space Science Center,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China;Peng Cheng National Laboratory,Shenzhen 518000,China;State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China

天文和天体物理学研究

[1]Fengping Dou;Long Xu;Zhixiang Ren;Dong Zhao;Xinze Zhang-.Super-resolution of Solar Magnetograms Using Deep Learning)[J].天文和天体物理学研究,2022(08):218-229

Magnetograms,magnetogram,magnetograms

Super,Solar,Using,Deep,Learning,Currently,driven,models,solar,activity,forecast,are,investigated,extensively,by,using,machine,learning,For,training,highly,demanded,establish,large,database,which,may,contain,observations,coming,from,different,instruments,spatio,temporal,resolutions,In,this,paper,we,employ,deep,SR,Michelson,Doppler,Imager,MDI,order,achieve,same,spatial,Helioseismic,Magnetic,HMI,First,generative,adversarial,network,GAN,designed,transfer,characteristics,onto,downscaled,getting,low,domain,Then,paired,another,trained,supervised,way,consists,streams,one,generating,fidelity,content,explicitly,optimized,elaborate,gradients,Thus,these,together,guarantee,both,photorealistic,resolved,images,Experimental,results,demonstrate,that,proposed,method,can,generate,perceptual,pleasant,visual,quality,Meanwhile,best,PSNR,LPIPS,RMSE,comparable,SSIM,CC,obtained,source,code,set,accessed,via

0.62759