arXiv:2605.24748v1 Announce Type: cross Abstract: Understanding and forecasting the geoeffectiveness of a coronal mass ejection (CME) is crucial for protecting infrastructure in the near-Earth space environment and on Earth. In this study, we present a novel fusion model to forecast the geoeffectiveness of CME events. Our model combines convolutional neural networks for feature learning and a prediction network for feature fusion and event classification. The model is trained by observations from instruments including the Large Angle Spectroscopic Coronagraph (LASCO) on board the Solar and Hel
Advances in deep learning and the availability of extensive satellite observation data (SOHO, SDO) have converged to enable more sophisticated predictive models for space weather events.
Accurate forecasting of geoeffective CMEs is critical for protecting vital infrastructure from space weather impacts, affecting sectors from power grids to satellite communications.
The development of a novel fusion model combining CNNs for feature learning and a dedicated prediction network offers a more reliable and advanced method for anticipating CME geoeffectiveness.
- · Satellite operators
- · Power grid operators
- · Space agencies
- · AI/ML research institutions
- · Legacy space weather forecasting methods
Improved lead times for mitigating space weather risks to critical infrastructure.
Reduced economic losses from geomagnetic storms due to better preparedness and protective measures.
Potential for autonomous systems to implement protective actions based on AI-driven space weather predictions, further integrating AI into critical infrastructure management.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG