Improving Spatial Resolution of Sunspot HMI Images Using Conditional Generative Adversarial Networks

Solar Dynamics Observatory (SDO) spacecraft as a spacebased project is able to conduct continuous monitoring of the Sun. The Helioseismic and Magnetic Imager (HMI) instrument on SDO, in particular, provides continuum images and magnetograms with a cadence of under 1 minute. SDO/HMI's spatial resolution is only about 1”, which makes it impossible to perform a good analysis on the subarcsecond scale. On the other hand, larger aperture groundbased telescopes such as the Goode Solar Telescope (GST) at the Big Bear Solar Observatory are able to achieve a better resolution (16 times better than SDO/HMI). However, groundbased telescopes like GST have limitations in terms of observation time, which can only make observations during the day in clear sky condition. The purpose of this study is to make attempts in improving the spatial resolution of images captured by HMI beyond the diffraction limit of the telescope by employing the Conditional Generative Adversarial Networks algorithm (cGAN). The cGAN model was trained using 1800 pairs of HMI and GST sunspot images. This method successfully reconstruct HMI images with a spatial resolution close to GST images, this is supported by ∼62% increase in the peak signaltonoise ratio (PSNR) value and ∼90% decrease in the mean squared error (MSE) value. The higher resolution sunspot images produced by this model can be useful for further Solar Physics studies.