Imaging observations of solar X-ray bursts can reveal details of the energy release process and particle acceleration in flares.Most hard X-ray imagers make use of the modulation-based Fourier transform imaging method...Imaging observations of solar X-ray bursts can reveal details of the energy release process and particle acceleration in flares.Most hard X-ray imagers make use of the modulation-based Fourier transform imaging method,an indirect imaging technique that requires algorithms to reconstruct and optimize images.During the last decade,a variety of algorithms have been developed and improved.However,it is difficult to quantitatively evaluate the image quality of different solutions without a true,reference image of observation.How to choose the values of imaging parameters for these algorithms to get the best performance is also an open question.In this study,we present a detailed test of the characteristics of these algorithms,imaging dynamic range and a crucial parameter for the CLEAN method,clean beam width factor(CBWF).We first used SDO/AIA EUV images to compute DEM maps and calculate thermal X-ray maps.Then these realistic sources and several types of simulated sources are used as the ground truth in the imaging simulations for both RHESSI and ASO-S/HXI.The different solutions are evaluated quantitatively by a number of means.The overall results suggest that EM,PIXON,and CLEAN are exceptional methods for sidelobe elimination,producing images with clear source details.Although MEM_GE,MEM_NJIT,VIS_WV and VIS_CS possess fast imaging processes and generate good images,they too possess associated imperfections unique to each method.The two forward fit algorithms,VF and FF,perform differently,and VF appears to be more robust and useful.We also demonstrated the imaging capability of HXI and available HXI algorithms.Furthermore,the effect of CBWF on image quality was investigated,and the optimal settings for both RHESSI and HXI were proposed.展开更多
Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar dynamics.This paper introduces an innovative unsupervised deep learning optical flow model designed to calcu...Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar dynamics.This paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar images.The proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow labels.Additionally,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow outliers.We apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar Telescope.Comparative experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index Measure.Moreover,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity forecasting.The code is available at https://github.com/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.展开更多
The Atmospheric Imaging Assembly(AIA)onboard the Solar Dynamics Observatory(SDO)captures full-disk solar images in seven extreme ultraviolet wave bands.As a violent solar flare occurs,incoming photoflux may exceed the...The Atmospheric Imaging Assembly(AIA)onboard the Solar Dynamics Observatory(SDO)captures full-disk solar images in seven extreme ultraviolet wave bands.As a violent solar flare occurs,incoming photoflux may exceed the threshold of an optical imaging system,resulting in regional saturation/overexposure of images.Fortunately,the lost signal can be partially retrieved from non-local unsaturated regions of an image according to scattering and diffraction principle,which is well consistent with the attention mechanism in deep learning.Thus,an attention augmented convolutional neural network(AANet)is proposed to perform image desaturation of SDO/AIA in this paper.It is built on a U-Net backbone network with partial convolution and adversarial learning.In addition,a lightweight attention model,namely criss-cross attention,is embedded between each two convolution layers to enhance the backbone network.Experimental results validate the superiority of the proposed AANet beyond state-of-the-arts from both quantitative and qualitative comparisons.展开更多
Learning the mapping of magnetograms and EUV images is important for understanding the solar eruption mechanism and space weather forecasting.Previous works are mainly based on the pix2pix model for full-disk magnetog...Learning the mapping of magnetograms and EUV images is important for understanding the solar eruption mechanism and space weather forecasting.Previous works are mainly based on the pix2pix model for full-disk magnetograms generation and obtain good performance.However,in general,we are more concerned with the magnetic field distribution in the active regions where various solar storms such as the solar flare and coronal mass ejection happen.In this paper,we fuse the self-attention mechanism with the pix2pix model which allows more computation resource and greater weight for strong magnetic regions.In addition,the attention features are concatenated by the Residual Hadamard Production(RHP) with the abstracted features after the encoder.We named our model as RHP-attention pix2pix.From the experiments,we can find that the proposed model can generate magnetograms with finer strong magnetic structures,such as sunspots.In addition,the polarity distribution of generated magnetograms at strong magnetic regions is more consistent with observed ones.展开更多
基金supported by the National Key R&D Program of China 2022YFF0503002the National Natural Science Foundation of China(NSFC,Grant Nos.12333010 and 12233012)+2 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences(grant No.XDB0560000)supported by the Prominent Postdoctoral Project of Jiangsu Province(2023ZB304)supported by the Strategic Priority Research Program on Space Science,the Chinese Academy of Sciences,grant No.XDA15320000.
文摘Imaging observations of solar X-ray bursts can reveal details of the energy release process and particle acceleration in flares.Most hard X-ray imagers make use of the modulation-based Fourier transform imaging method,an indirect imaging technique that requires algorithms to reconstruct and optimize images.During the last decade,a variety of algorithms have been developed and improved.However,it is difficult to quantitatively evaluate the image quality of different solutions without a true,reference image of observation.How to choose the values of imaging parameters for these algorithms to get the best performance is also an open question.In this study,we present a detailed test of the characteristics of these algorithms,imaging dynamic range and a crucial parameter for the CLEAN method,clean beam width factor(CBWF).We first used SDO/AIA EUV images to compute DEM maps and calculate thermal X-ray maps.Then these realistic sources and several types of simulated sources are used as the ground truth in the imaging simulations for both RHESSI and ASO-S/HXI.The different solutions are evaluated quantitatively by a number of means.The overall results suggest that EM,PIXON,and CLEAN are exceptional methods for sidelobe elimination,producing images with clear source details.Although MEM_GE,MEM_NJIT,VIS_WV and VIS_CS possess fast imaging processes and generate good images,they too possess associated imperfections unique to each method.The two forward fit algorithms,VF and FF,perform differently,and VF appears to be more robust and useful.We also demonstrated the imaging capability of HXI and available HXI algorithms.Furthermore,the effect of CBWF on image quality was investigated,and the optimal settings for both RHESSI and HXI were proposed.
基金supported by the National Natural Science Foundation of China(NSFC,Grant Nos.12063002 and 12163004).
文摘Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar dynamics.This paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar images.The proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow labels.Additionally,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow outliers.We apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar Telescope.Comparative experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index Measure.Moreover,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity forecasting.The code is available at https://github.com/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.
基金supported by the National Key R&D Program of China(Nos.2021YFA1600504 and 2022YFE0133700)the National Natural Science Foundation of China(NSFC)(Nos.11790305,11873060 and 11963003)。
文摘The Atmospheric Imaging Assembly(AIA)onboard the Solar Dynamics Observatory(SDO)captures full-disk solar images in seven extreme ultraviolet wave bands.As a violent solar flare occurs,incoming photoflux may exceed the threshold of an optical imaging system,resulting in regional saturation/overexposure of images.Fortunately,the lost signal can be partially retrieved from non-local unsaturated regions of an image according to scattering and diffraction principle,which is well consistent with the attention mechanism in deep learning.Thus,an attention augmented convolutional neural network(AANet)is proposed to perform image desaturation of SDO/AIA in this paper.It is built on a U-Net backbone network with partial convolution and adversarial learning.In addition,a lightweight attention model,namely criss-cross attention,is embedded between each two convolution layers to enhance the backbone network.Experimental results validate the superiority of the proposed AANet beyond state-of-the-arts from both quantitative and qualitative comparisons.
基金funded by the National Key R&D Program of China(Nos.2021YFA1600504 and 2022YFE0133700)the National Natural Science Foundation of China(NSFC)(Nos.11790305,11963003,12273007 and 61902371)。
文摘Learning the mapping of magnetograms and EUV images is important for understanding the solar eruption mechanism and space weather forecasting.Previous works are mainly based on the pix2pix model for full-disk magnetograms generation and obtain good performance.However,in general,we are more concerned with the magnetic field distribution in the active regions where various solar storms such as the solar flare and coronal mass ejection happen.In this paper,we fuse the self-attention mechanism with the pix2pix model which allows more computation resource and greater weight for strong magnetic regions.In addition,the attention features are concatenated by the Residual Hadamard Production(RHP) with the abstracted features after the encoder.We named our model as RHP-attention pix2pix.From the experiments,we can find that the proposed model can generate magnetograms with finer strong magnetic structures,such as sunspots.In addition,the polarity distribution of generated magnetograms at strong magnetic regions is more consistent with observed ones.
