ED‐Autoformer: A New Model for Precise Global TEC Forecast

Abstract Total electron content (TEC) is a key parameter for characterizing ionospheric morphology and significantly impacts the Global Navigation Satellite System. The ionosphere responds dramatically to solar and geomagnetic activity, leading to substantial TEC fluctuations and disturbances. To im...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiawei Zhou, Hongtao Cai, Xu Yan, Hong‐wen Xu, Kun Hu, Chao Xiong
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Space Weather
Subjects:
Online Access:https://doi.org/10.1029/2025SW004356
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849415811651862528
author Jiawei Zhou
Hongtao Cai
Xu Yan
Hong‐wen Xu
Kun Hu
Chao Xiong
author_facet Jiawei Zhou
Hongtao Cai
Xu Yan
Hong‐wen Xu
Kun Hu
Chao Xiong
author_sort Jiawei Zhou
collection DOAJ
description Abstract Total electron content (TEC) is a key parameter for characterizing ionospheric morphology and significantly impacts the Global Navigation Satellite System. The ionosphere responds dramatically to solar and geomagnetic activity, leading to substantial TEC fluctuations and disturbances. To improve TEC prediction accuracy, we propose Encoder‐Decoder (ED)‐Autoformer, a novel model combining ED structure with the Autoformer model. The model integrates time series data with TEC to enable 24‐hr forecasts of both disturbance storm time index (Dst) and TEC. Evaluated on global ionospheric maps TEC, our model achieves a 12.0% improvement (0.51 TECu) in the root mean squared error (RMSE) during solar maximum and an 8.9% improvement (0.14 TECu) in RMSE during solar minimum compared to the Convolutional Long‐Short‐Term Memory (ConvLSTM) method. Furthermore, ED‐Autoformer shows superior computational efficiency with 45.4% faster inference speed compared to ED‐ConvLSTM. We further analyzed TEC disturbances during geomagnetic storm periods. For the geomagnetic storm on 20 September 2015, the RMSE remained below 3.50 TECu for most periods, peaking at 5.50 TECu during the main phase. These results demonstrate the robustness of the model in accurately predicting TEC disturbances during geomagnetic storm periods.
format Article
id doaj-art-744ebff09a1c4a79ba33d134b3e7077e
institution Kabale University
issn 1542-7390
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Space Weather
spelling doaj-art-744ebff09a1c4a79ba33d134b3e7077e2025-08-20T03:33:25ZengWileySpace Weather1542-73902025-06-01236n/an/a10.1029/2025SW004356ED‐Autoformer: A New Model for Precise Global TEC ForecastJiawei Zhou0Hongtao Cai1Xu Yan2Hong‐wen Xu3Kun Hu4Chao Xiong5School of Earth and Space Science and Technology Wuhan University Wuhan ChinaSchool of Earth and Space Science and Technology Wuhan University Wuhan ChinaSchool of Earth and Space Science and Technology Wuhan University Wuhan ChinaSchool of Earth and Space Science and Technology Wuhan University Wuhan ChinaSchool of Earth and Space Science and Technology Wuhan University Wuhan ChinaSchool of Earth and Space Science and Technology Wuhan University Wuhan ChinaAbstract Total electron content (TEC) is a key parameter for characterizing ionospheric morphology and significantly impacts the Global Navigation Satellite System. The ionosphere responds dramatically to solar and geomagnetic activity, leading to substantial TEC fluctuations and disturbances. To improve TEC prediction accuracy, we propose Encoder‐Decoder (ED)‐Autoformer, a novel model combining ED structure with the Autoformer model. The model integrates time series data with TEC to enable 24‐hr forecasts of both disturbance storm time index (Dst) and TEC. Evaluated on global ionospheric maps TEC, our model achieves a 12.0% improvement (0.51 TECu) in the root mean squared error (RMSE) during solar maximum and an 8.9% improvement (0.14 TECu) in RMSE during solar minimum compared to the Convolutional Long‐Short‐Term Memory (ConvLSTM) method. Furthermore, ED‐Autoformer shows superior computational efficiency with 45.4% faster inference speed compared to ED‐ConvLSTM. We further analyzed TEC disturbances during geomagnetic storm periods. For the geomagnetic storm on 20 September 2015, the RMSE remained below 3.50 TECu for most periods, peaking at 5.50 TECu during the main phase. These results demonstrate the robustness of the model in accurately predicting TEC disturbances during geomagnetic storm periods.https://doi.org/10.1029/2025SW004356ionospheric stormTEC predictionmachine learning
spellingShingle Jiawei Zhou
Hongtao Cai
Xu Yan
Hong‐wen Xu
Kun Hu
Chao Xiong
ED‐Autoformer: A New Model for Precise Global TEC Forecast
Space Weather
ionospheric storm
TEC prediction
machine learning
title ED‐Autoformer: A New Model for Precise Global TEC Forecast
title_full ED‐Autoformer: A New Model for Precise Global TEC Forecast
title_fullStr ED‐Autoformer: A New Model for Precise Global TEC Forecast
title_full_unstemmed ED‐Autoformer: A New Model for Precise Global TEC Forecast
title_short ED‐Autoformer: A New Model for Precise Global TEC Forecast
title_sort ed autoformer a new model for precise global tec forecast
topic ionospheric storm
TEC prediction
machine learning
url https://doi.org/10.1029/2025SW004356
work_keys_str_mv AT jiaweizhou edautoformeranewmodelforpreciseglobaltecforecast
AT hongtaocai edautoformeranewmodelforpreciseglobaltecforecast
AT xuyan edautoformeranewmodelforpreciseglobaltecforecast
AT hongwenxu edautoformeranewmodelforpreciseglobaltecforecast
AT kunhu edautoformeranewmodelforpreciseglobaltecforecast
AT chaoxiong edautoformeranewmodelforpreciseglobaltecforecast