Image super-resolution is a technique of enhancing the resolution of an image where a high-resolution (HR) image is reconstructed from a low-resolution (LR) image. In this Letter, we apply two novel deep learning models (residual attention model and progressive GAN model) for enhancing Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI) magnetograms. For this, we consider line-of-sight (LOS) magnetograms taken by SDO/HMI as output and their degraded ones with 4 × 4 binning as input. Deep learning networks try to find internal relationships between LR and HR images from the given input and the corresponding output image. We consider SDO/HMI magnetograms from 2014 May to August for training, from 2014 October to December for validation, and 2015 January to March for test. We find that the deep learning models generate higher-quality results than the bicubic interpolation in terms of visual aspects and metrics. We apply this model to a full-resolution SDO/HMI magnetogram and then compare the generated magnetogram with the corresponding Hinode/The Solar Optical Telescope Narrowband Filtergrams (NFI) magnetogram. This comparison shows that the generated magnetogram is consistent with the Hinode one with a high correlation (CC: 0.94) and a high similarity (SSIM: 0.93), which are better than the bicubic method.
This study is the first attempt to generate a three-dimensional (3D) coronal electron density distribution based on the pix2pixHD model, whose computing time is much shorter than that of the magnetohydrodynamic (MHD) simulation. For this, we consider photospheric solar magnetic fields as input, and electron density distribution simulated with the MHD Algorithm outside a Sphere (MAS) at a given solar radius is taken as output. We consider 155 pairs of Carrington rotations as inputs and outputs from 2010 June to 2022 April for training and testing. We train 152 deep-learning models for 152 solar radii, which are taken up to 30 solar radii. The artificial intelligence (AI) generated 3D electron densities from this study are quite consistent with the simulated ones from lower radii to higher radii, with an average correlation coefficient 0.97. The computing time of testing data sets up to 30 solar radii of 152 deep-learning models is about 45.2 s using the NVIDIA TITAN XP graphics-processing unit, which is much less than the typical simulation time of MAS. We find that the synthetic coronagraphic images estimated from the deep-learning models are similar to the Solar Heliospheric Observatory (SOHO)/Large Angle and Spectroscopic Coronagraph C3 coronagraph data, especially during the solar minimum period. The AI-generated coronal density distribution from this study can be used for space weather models on a near-real-time basis.
Low coronal white-light observations are very important to understand low coronal features of the Sun, but they are rarely made. We generate Mauna Loa Solar Observatory (MLSO) K-coronagraph like white-light images from the Solar Dynamics Observatory/Atmospheric Imaging Assembly (SDO/AIA) EUV images using a deep learning model based on conditional generative adversarial networks. In this study, we used pairs of SDO/AIA EUV (171, 193, and 211 Å) images and their corresponding MLSO K-coronagraph images between 1.11 and 1.25 solar radii from 2014 to 2019 (January to September) to train the model. For this we made seven (three using single channels and four using multiple channels) deep learning models for image translation. We evaluate the models by comparing the pairs of target white-light images and those of corresponding artificial intelligence (AI)–generated ones in October and November. Our results from the study are summarized as follows. First, the multiple channel AIA 193 and 211 Å model is the best among the seven models in view of the correlation coefficient (CC = 0.938). Second, the major low coronal features like helmet streamers, pseudostreamers, and polar coronal holes are well identified in the AI-generated ones by this model. The positions and sizes of the polar coronal holes of the AI-generated images are very consistent with those of the target ones. Third, from AI-generated images we successfully identified a few interesting solar eruptions such as major coronal mass ejections and jets. We hope that our model provides us with complementary data to study the low coronal features in white light, especially for nonobservable cases (during nighttime, poor atmospheric conditions, and instrumental maintenance).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.