Generation of solar EUV data from Ca II K Images by Deep Learning

We generate solar UV and EUV data from Ca II K data using a deep learning model. For this, we consider a deep learning method (pix2pixHD) based on conditional Generative Adversarial Networks (cGAN). We use Ca II K 393.3 nm images from the Precision Solar Photometric Telescope at the Rome Observatory and Solar Dynamics Observatory (SDO)/Atmospheric Imaging Assembly (AIA) nine-passband (9.4, 13.1, 17.1, 19.3, 21.1, 30.4, 33.5, 160.0, and 170.0 nm) UV/EUV data. We use data from 2011 January to 2015 June except for June and December for training and the remaining one for test. Our model successfully generates SDO/AIA-like solar UV/EUV images from Ca II K images. The mean correlation coefficient (CC) of intensities between AI-generated and real ones with 4 x 4 binning ranges from 0.79 to 0.95 except 17.1 nm one (0.68). We estimate differential emission measures (DEMs) of several structures (coronal loops in an active region, quiet region, and coronal hole) using two data sets: six-channel SDO/AIA images and the AI-generated EUV images from Ca II ones. The estimated DEMs from both methods are similar to each other, demonstrating that the AI-generated data from Ca II ones are feasible for scientific study.