Issue |
A&A
Volume 695, March 2025
|
|
---|---|---|
Article Number | A105 | |
Number of page(s) | 11 | |
Section | The Sun and the Heliosphere | |
DOI | https://doi.org/10.1051/0004-6361/202452638 | |
Published online | 11 March 2025 |
Spatial and temporal super-resolution methods for high-fidelity solar imaging
1
Taras Shevchenko National University of Kyiv, Glushkova Ave., 4, 03127 Kyiv, Ukraine
2
Department of Physics, The Chinese University of Hong Kong, Hong Kong
3
Center for Computation Astrophysics, Flatiron Institute, New York, NY 10010, USA
4
Department of Astrophysical Sciences, Princeton University, 4 Ivy Lane, Princeton, NJ 08544, USA
5
Department of Physics & Center for Data Science, New York University, 726 Broadway, New York, NY 10003, USA
⋆ Corresponding author; alexgugnin21@gmail.com
Received:
16
October
2024
Accepted:
22
January
2025
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.
Key words: methods: data analysis / Sun: activity / Sun: atmosphere
© The Authors 2025
Open Access article, published by EDP Sciences, under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
This article is published in open access under the Subscribe to Open model. Subscribe to A&A to support open access publication.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.