Space weather is a term used to describe hazardous events in the near-Earth space environment, such as solar wind and geomagnetic storms. These events can have adverse effects on vulnerable infrastructure, such as power grids and satellites. Space and ground operations depend significantly on the accurate knowledge and forecasts of the conditions on the space environment. Currently, prediction of the solar wind parameters at the Earth such as solar wind speed, density, and the magnetic field, is done using massive and computationally expensive physics-based models that are slow to run in real-time.
In this project funded by the Helmholtz Imaging Platform, we use vast numbers of high resolution multi-spectral images of the Sun to improve the prediction of the solar wind close to the Earth, we plan to exploit the capabilities of classical computer vision tools and modern deep learning algorithms to identify relevant structures on the Sun. Our aim is to understand how the disturbances on the Sun affect the space close to the Earth, what conditions on the Sun lead to the strongest geomagnetic storms and how the geomagnetic activity depends on the history of the solar activity, allowing us to make the most accurate empirical predictions of the solar wind and its impact on the near-Earth space and ground infrastructure. Through an initial predictive model, we aim to completely change the field of space weather forecasting, and therefore address the high risk high-gain challenges of predicting space weather conditions.
Jan 2021 – Dez 2022
Helmholtz Imaging Platform
- Prof. Yuri Shprits (GFZ)
- Dr. Jenia Jitsev (JSC Jülich)
- Dr. Marcus Paradies (DLR Jena)
- Prof. Yuri Shprits
- Dr. Ruggero Vasile
- Dr. Irina Zhelavskaya
- Deutsches Zentrum für Luft- und Raumfahrt, Institute of Data Science (DLR Jena)
- Forschungszentrum Jülich, Institute for Advanced Simulation and Super Computing Centre (JSC Jülich)