Generation of Solar Coronal White-light Images from SDO/AIA EUV Images by Deep Learning

Abstract

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).

Near-real-time 3D Reconstruction of the Solar Coronal Parameters Based on the Magnetohydrodynamic Algorithm outside a Sphere Using Deep Learning

“…The Pix2Pix (Isola et al 2017) and the Pix2PixHD (Wang et al 2018) are supervised models based on a GAN. Those models have been applied in various areas of astronomy and space weather applications: (1) image translation among mutiwavelength images (Kim et al 2019;Park et al 2019;Jeong et al 2020;Shin et al 2020;Jeong et al 2022;Lawrance et al 2022), (2) denoising the solar magnetogram (Park et al 2020), (3) superresolution of the solar data (Jia et al 2019;Rahman et al 2020), and (4) the 3D reconstruction of coronal electron density (Jang et al 2021;Rahman et al 2023).…”

Application of Deep Learning to Solar and Space Weather Data

“…The off-limb coronal white light images with an altitude range between 1.11 -1.25 solar radii were generated from a single EUV channel image as well as multiple channel images by applying the DL model based on the cGANs (Lawrance et al 2022). It was found that the AI-generated white light image shows the best correlation with the original K-Cor (de Wijn et al 2012) image when multiple channels of the AIA 193 Å and 211 Å were used as input.…”

An Experimental Study on EUV‐To‐Magnetogram Image Translation Using Conditional Generative Adversarial Networks

“…cGANs have been further used in heliophysics in various context. We cite here the generation of white light (Lawrance et al., 2022) or He I 1083 nm images (Son et al., 2021) from EUV images; of solar magnetograms and EUV images from Galileo sunspot drawings (H. Lee et al., 2021); and of pseudo‐magnetograms from Ca II K images (Shin et al., 2020). They were also used to produce one‐day forecasting of global Total Electron Content (TEC) maps (S. Lee et al., 2021) from a training data set composed of TEC maps paired with one‐day ahead TEC maps; to denoise magnetograms (Park et al., 2020); to simulate solar radio bursts (Scully et al., 2023); to obtain super‐resolved (Deng et al., 2021; Dou et al., 2022) or deconvolved (Xu et al., 2020) images.…”