Communication Dans Un Congrès Année : 2021

Deep learning based approach to forecasting Kp index up to a few days ahead using SDO/AIA data

Résumé

In the last few years, methods for forecasting geomagnetic indices from near-Earth solar wind parameters have become popular in the space weather community. These methods often prove to be more accurate than many empirical models. However, these approaches have the notable drawback of being effective in an operational context only for limited time horizons (often up to 6 hours ahead at best). In order to address this challenge, we present a novel deep-learning based model using images delivered by the Atmospheric Imaging Assembly (AIA) instrument onboard the Solar Dynamics Observatory (SDO) spacecraft to directly provide probabilistic forecasts of the planetary geomagnetic index Kp up to a few days ahead.

Fichier non déposé

Dates et versions

hal-04848973 , version 1 (19-12-2024)

Identifiants

  • HAL Id : hal-04848973 , version 1

Citer

Guillerme Bernoux, Antoine Brunet, Eric Buchlin, Miho Janvier, Angelica Sicard. Deep learning based approach to forecasting Kp index up to a few days ahead using SDO/AIA data. 17th European Space Weather Week, Oct 2021, Glasgow, United Kingdom. pp.2021. ⟨hal-04848973⟩
61 Consultations
0 Téléchargements

Partager

  • More