1,2,1,1,1,2,3,4,1,7,1- 1Austrian Space Weather Office, GeoSphere Austria, Graz, Austria
- 2Institute of Physics, University of Graz, Graz, Austria
- 3Goddard Planetary Heliophysics Institute, University of Maryland, Baltimore County, Baltimore, MD 21250, USA
- 4Heliophysics Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
- 5Community Coordinated Modeling Center, NASA Goddard Space Flight Center, 8800 Greenbelt Rd., Greenbelt, MD 20771, USA
- 6Universities Space Research Association, Washington, DC, USA
- 7DPHY, ONERA, Université de Toulouse, F-31000, Toulouse, France
We present a fully automated end-to-end pipeline for operational short-term forecasting of the in situ magnetic structure of coronal mass ejections (CMEs) at Earth. Triggered by new events in the NASA/CCMC DONKI catalog, the system couples ensemble arrival time predictions using ELEvo with deep-learning-based in situ detection of magnetic obstacles (ARCANE), and iterative flux rope reconstruction using the semi-empirical 3DCORE model. As more real-time L1 solar wind data becomes available, the pipeline continuously updates forecasts of the remaining CME magnetic field profile. Using archived real-time data, we evaluate the pipeline under operational constraints and analyze how reconstruction quality evolves as a function of available data, providing insight into capabilities and limitations of fully automated real-time CME magnetic field reconstruction for space weather forecasting.
How to cite: Rüdisser, H. T., Davies, E. E., Amerstorfer, U. V., Weiler, E., Weiss, A. J., Reiss, M. A., Le Louëdec, J., Nguyen, G., and Möstl, C.: Towards a fully automated end-to-end pipeline for short-term CME magnetic field forecasting, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-11539, https://doi.org/10.5194/egusphere-egu26-11539, 2026.
