We have produced improved Artificial Intelligence-generated Solar Farside Magnetograms (AISFMs) using a continuously upgraded deep learning model, based on full-disk solar extreme-ultraviolet (EUV) observations obtained from STEREO-A, STEREO-B, and Solar Orbiter.  Using the AISFMs together with SDO/HMI magnetograms, we have continuously tracked the magnetic fields of solar active regions from the solar front side to the far side.

Jeong et al. (2024), "Artificial-intelligence-based Reconstruction of Solar Farside Vector Magnetograms from Multispacecraft Extreme-ultraviolet Data", The Astrophysical Journal Supplement Series, Volume 281, Issue 2, id.63, 14 pp. 

Jeong et al. (2022), "Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release", The Astrophysical Journal Supplement Series, Volume 262, Issue 2, id.50, 11 pp.