EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images

Daniel Collin, Yuri Shprits, Luca Chiarabini, Stefan J. Hofmeister, Nadja Klein, Guillermo Gallego

AGU Advances · 2026-11 · 7 (8)

DOI: 10.1029/2026av002524 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AGU Advances, online erschienen am 30.10.2026. Verfasst von Daniel Collin und 5 weiteren Autor:innen. Die Arbeit nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately predicting fast solar wind conditions is challenging, as uncertainties are large and unquantified by traditional single‐value prediction models. In particular, the risks of high‐speed solar wind streams (HSSs), which can cause damage to technological infrastructure, cannot be reliably assessed without probabilistic forecasts. We present PROSWIN, a probabilistic machine learning model that forecasts the hourly solar wind speed (SWS) at Earth with a 4‐day lead time. The approach combines solar images and magnetograms using a deep neural network coupled to a distributional regression algorithm. Because standard error metrics underweight the relevance of HSS peaks, we further introduce the prediction score (PS) , a model‐selection metric that jointly rewards timeline and HSS peak accuracy. On 14 years of data, our forecast achieves very well‐calibrated uncertainties (

Förderung

  • National Science Foundation

Zitieren

APA

Collin, D., Shprits, Y., Chiarabini, L., Hofmeister, S. J., Klein, N., & Gallego, G. (2026). PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images. AGU Advances, 7(8). https://doi.org/10.1029/2026av002524

Vancouver

Collin D, Shprits Y, Chiarabini L, Hofmeister SJ, Klein N, Gallego G. PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images. AGU Advances. 2026;7(8). doi:10.1029/2026av002524

BibTeX
@article{Collin2026,
  author = {Collin, Daniel and Shprits, Yuri and Chiarabini, Luca and Hofmeister, Stefan J. and Klein, Nadja and Gallego, Guillermo},
  title = {PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images},
  journal = {AGU Advances},
  year = {2026},
  volume = {7},
  number = {8},
  doi = {10.1029/2026av002524}
}
Kostenlos starten →