Spatial and temporal super-resolution methods for high-fidelity solar imaging

Context. The Sun plays a significant role in space weather by emitting energy and electromagnetic radiation that influence the environment around the Earth. Missions such as SOHO, STEREO, and SDO captured solar observations at multiple wavelengths to monitor and predict solar events. However, the data transmission from these missions is often constrained, in particular, for those operating at greater distances from Earth. This limits the availability of continuous observations. Aims. We increase the spatial and temporal resolution of solar images to improve the quality and availability of solar data. By addressing telemetry constraints and providing more detailed solar image reconstructions, we seek to facilitate a more accurate analysis of solar dynamics and improve space weather prediction. Methods. We applied deep-learning techniques, specifically, a UNet-based architecture, to generate high-resolution solar images that enhance the intricate details of the solar structures. Additionally, we used a similar architecture to reconstruct solar image sequences with a reduced temporal resolution to predict missing frames and restore temporal continuity. Results. Our deep-learning approach successfully enhances the resolution of solar images and reveals finer details of solar structures. The model also predicts missing frames in solar image sequences, which allows more continuous observation despite telemetry constraints. These advancements contribute to a better analysis of solar dynamics and set the stage for an improved space weather forecasting and future solar physics research.