Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Global TEC forecasting based on deep learning techniques: a comparative study and perspectives for a Space Weather operational service
  • +3
  • Maria Graciela Molina,
  • Jorge Habib Namour,
  • Claudio Cesaroni,
  • Luca Spogli,
  • Noelia Beatriz Argüelles,
  • Eric Nana Asamoah
Maria Graciela Molina
Universidad Nacional de Tucumán
Author Profile
Jorge Habib Namour
Universidad Nacional de Tucuman
Author Profile
Claudio Cesaroni
Istituto Nazionale di Geofisica e Vulcanologia

Corresponding Author:[email protected]

Author Profile
Luca Spogli
Istituto Nazionale di Geofisica e Vulcanologia
Author Profile
Noelia Beatriz Argüelles
Universidad Nacional de Tucumán
Author Profile
Eric Nana Asamoah
Istituto Nazionale di Geofisica e Vulcanologia
Author Profile

Abstract

The aim of this work is to present a global ionospheric prediction model based on deep learning (DL) to forecast Total Electron Content 24 hours in advance under different space weather conditions. Three different DL techniques have been compared to select the most suitable for the purpose of an operational service: Long Short Term Memory (LSTM), Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN). The modeling approach inherits and extends what has been proposed by Cesaroni and co-authors (2020). We use TEC on 18 selected grid points of Global Ionospheric Maps (GIMs) as the target parameter and Kp index as the external input. We use a dataset from 2005-2016 for training and testing, we also analyze case studies from 2017 under different geomagnetic conditions. Results show that CNN models have better predictive capabilities than the other two DL models, even under geomagnetically disturbed conditions. Considering the first 24 hours of forecasting, CNN exhibits errors between 0.5 and 2 TECu, while LSTM and GRU errors can reach 3 TECu. We also show how all the proposed models outperform the two naive models: the so-called “frozen ionosphere” and a 27 days averaged model.
Moreover, we implemented the models using incremental training to update them as new data arrives and thus the trained model is able to adapt to rapid changes within the previous 24 hs to the forecasting. Thus, the proposed model can be implemented in an operative manner for Space Weather applications and services.
05 May 2023Submitted to ESS Open Archive
05 May 2023Published in ESS Open Archive