Exploring the Potential of DEM Analysis Using Solar Orbiter/EUI and AI-Generated Data

In this study, we determine the differential emission measures (DEMs) using Solar Orbiter/Extreme Ultraviolet Imager (EUI)/Full Sun Imager (FSI) and AI-generated EUV data. The FSI observes only two full-disk extreme UV (EUV) channels (174 and 304 Å), which poses a limitation for accurately determining DEMs. We address this problem using deep learning models based on Pix2PixCC, trained using the Solar Dynamics Observatory (SDO)/Atmospheric Imaging Assembly (AIA) dataset. These models successfully generate five-channel (94, 131, 193, 211, and 335 Å) EUV data from 171 and 304 Å EUV observations with high correlation coefficients. We then apply the trained models to the Solar Orbiter/EUI/FSI dataset and generate the five-channel data that the FSI cannot observe. Here we use the regularized inversion method to compare the DEMs from the SDO/AIA dataset with those from the Solar Orbiter/EUI/FSI ones with AI-generated data. First, we demonstrate that, when SDO and Solar Orbiter are at inferior conjunction, the main peaks and widths of both DEMs are well consistent with each other at the same coronal structures. These results reveal that deep learning can make it possible to properly determine the DEMs using Solar Orbiter/EUI/FSI and AI-generated EUV data. Additionally, we determine the DEM when the two instruments are at various angular separations, such as when 60 degrees (L4 and L5) and 180 degrees apart. Our results suggest that the stereoscopic DEM analysis of coronal features using our methodology should be possible.