EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Extended Lead‐Time Geomagnetic Storm Forecasting With Solar Wind Ensembles and Machine Learning

M. Billcliff, A. W. Smith, M. Owens, W. L. Woo, L. Barnard, N. Edward‐Inatimi, I. J. Rae

Space Weather · 2026-03 · 24 (3)

DOI: 10.1029/2025sw004823 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Space Weather, online erschienen am 05.03.2026. Verfasst von M. Billcliff und 6 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Environment Research Council, Science and Technology Facilities Council, Northumbria University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Geomagnetic storms are large disruptions of the magnetosphere, which can impact satellites, communications systems, and power grids, causing significant technological and economic impacts. Current forecasting models utilize L1 satellite data, constraining lead time to a few hours, often insufficient for effective mitigation. We investigate how to extend the lead times of these forecasts with solar data. Associated spatial and propagation uncertainties of solar data are captured with a solar‐wind ensemble, of the computationally efficient one‐dimensional HUXt numerical model. The solar‐wind ensemble once propagated to Earth is processed through logistic regressions, weighting ensemble members by comparison with historical observed velocities, effectively filtering out high error ensemble members. Performance was evaluated across different storm intensities and lead times, demonstrating the models predictive capabilities in a variety of circumstances. Although not including transient phenomena such as Coronal Mass Ejections, our approach demonstrates strong predictive capability, achieving a Brier Skill Score relative to climatology of 0.595 and a Receiver Operating Characteristic Area Under the Curve (ROC AUC) of 0.751 at 6‐hr lead time for storms defined as within a 24‐hr forecast window. Overall, these results highlight the strong potential of the coupled numerical model and machine learning framework to extend the forecast lead time for geomagnetic storms.

Förderung

  • Natural Environment Research Council
  • Science and Technology Facilities Council
  • Northumbria University

Zitieren

APA

Billcliff, M., Smith, A. W., Owens, M., Woo, W. L., Barnard, L., Edward‐Inatimi, N., & Rae, I. J. (2026). Extended Lead‐Time Geomagnetic Storm Forecasting With Solar Wind Ensembles and Machine Learning. Space Weather, 24(3). https://doi.org/10.1029/2025sw004823

Vancouver

Billcliff M, Smith AW, Owens M, Woo WL, Barnard L, Edward‐Inatimi N, et al. Extended Lead‐Time Geomagnetic Storm Forecasting With Solar Wind Ensembles and Machine Learning. Space Weather. 2026;24(3). doi:10.1029/2025sw004823

BibTeX
@article{Billcliff2026,
  author = {Billcliff, M. and Smith, A. W. and Owens, M. and Woo, W. L. and Barnard, L. and Edward‐Inatimi, N. and Rae, I. J.},
  title = {Extended Lead‐Time Geomagnetic Storm Forecasting With Solar Wind Ensembles and Machine Learning},
  journal = {Space Weather},
  year = {2026},
  volume = {24},
  number = {3},
  doi = {10.1029/2025sw004823}
}
Kostenlos starten →