A Dual-Domain Wavelet-Based Spatiotemporal Attention Network for 24-h Global Ionospheric TEC Prediction
Open Access
Abstract
To address the challenges associated with the complex spatiotemporal variations of global ionospheric total electron content (TEC), this study proposes a Dual-domain Filtered-label Wavelet-based Spatiotemporal Attention Network (DFL-WT-STANet) for global TEC forecasting. The proposed framework integrates wavelet-based multi-scale feature extraction, ConvLSTM-based spatiotemporal modeling, and decoupled temporal and spatial Transformer branches to capture local and global dependencies in TEC variations. A dual-domain optimization strategy is further introduced to jointly constrain prediction errors in the time and frequency domains, enhancing the representation of temporal variations and disturbance-related characteristics. Kp, Dst, F10.7, and SSN are incorporated as auxiliary solar and geomagnetic activity features. The global TEC data from 2003 to 2024 were used for experimental evaluation, with 2015, 2019, and 2024 selected as representative test years under different solar activity conditions. DFL-WT-STANet achieves RMSE values of 2.96 and 4.81 TECU in the high-solar-activity years of 2015 and 2024, respectively, while the RMSE decreases to 1.15 TECU in the low-solar-activity year of 2019. Compared with the CODE 1-day-ahead prediction product (C1PG), DFL-WT-STANet reduces the RMSE by 26.75%, 22.06%, and 25.29% in 2015, 2019, and 2024, respectively. During a severe geomagnetic storm with a minimum Dst of nT, the proposed model further reduces the storm-day RMSE and MAE by 8.93% and 11.32%, respectively, compared with WT-STANet. Monthly and latitude-dependent evaluations further show that the forecasting advantage is consistently maintained across different months and a broad range of latitude regions. These results demonstrate that DFL-WT-STANet provides accurate and robust global TEC forecasting under different solar and geomagnetic activity conditions, with particular advantages during pronounced ionospheric disturbances.
Keywords
Funding Information
- National Key Research and Development Program of China (2024YFC2816700)
- National Natural Science Foundation of China (42404026)
- National Natural Science Foundation of China (42304170)
- Research Initiation Fund (23QD112)
This publication has 30 references indexed in Scilit:
- FVMD-HTLD: Prediction of TEC based on Signal decomposition and integrated modelsAdvances In Space Research, 2025
- Ionospheric TEC prediction using the non-stationary inverted transformer fusion model and its performance in Chinese regionGPS Solutions, 2025
- A hybrid model for TEC prediction using BiLSTM and PSO-LSSVMAdvances In Space Research, 2024
- New encoder–decoder convolutional LSTM neural network architectures for next-day global ionosphere maps forecastGPS Solutions, 2023
- An Effective Ionospheric TEC Predicting Approach Using EEMD-PE-Kmeans and Self-Attention LSTMNeural Processing Letters, 2023
- A storm-time ionospheric TEC model with multichannel features by the spatiotemporal ConvLSTM networkJournal of Geodesy, 2023
- Ionospheric TEC prediction using hybrid method based on ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM) deep learning model over IndiaAdvances In Space Research, 2022
- Influence of the ionosphere on the accuracy of the satellite navigation systemActa Astronautica, 2022
- International Reference Ionosphere 2016: From ionospheric climate to real‐time weather predictionsSpace Weather, 2017
- An examination of the Galileo NeQuick model: comparison with GPS and JASON TECGPS Solutions, 2016