ED‐AttConvLSTM: An Ionospheric TEC Map Prediction Model Using Adaptive Weighted Spatiotemporal Features

In this paper, we propose a novel Total Electron Content (TEC) map prediction model, named ED‐AttConvLSTM, using a Convolutional Long Short‐Term Memory (ConvLSTM) network and attention mechanism based on encoder‐decoder structure. The inclusion of the attention mechanism enhances the efficient utili...

Full description

Saved in:
Bibliographic Details
Published in:Space Weather Vol. 22; no. 3
Main Authors: Li, Liangchao, Liu, Haijun, Le, Huijun, Yuan, Jing, Wang, Haoran, Chen, Yi, Shan, Weifeng, Ma, Li, Cui, Chunjie
Format: Journal Article
Language:English
Published: Washington John Wiley & Sons, Inc 01.03.2024
Wiley
Subjects:
Accuracy
Deep learning
Feature extraction
General circulation models
Geomagnetic storms
Geophysics
Ionosphere
Magnetic storms
Performance evaluation
Prediction models
Predictions
Solar activity
Time series
Total Electron Content
ISSN:1542-7390, 1539-4964, 1542-7390
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a novel Total Electron Content (TEC) map prediction model, named ED‐AttConvLSTM, using a Convolutional Long Short‐Term Memory (ConvLSTM) network and attention mechanism based on encoder‐decoder structure. The inclusion of the attention mechanism enhances the efficient utilization of spatiotemporal features extracted by the ConvLSTM, emphasizing the significance of crucial spatiotemporal features in the prediction process and, as a result, leading to an enhancement in predictive performance. We conducted experiments in East Asia (10°N–45°N, 90°E−130°E). The ED‐AttConvLSTM was trained and evaluated using the International GNSS Service TEC maps over a period of six years from 2013 to 2015 (high solar activity years) and 2017 to 2019 (low solar activity years). We compared our ED‐AttConvLSTM with IRI‐2016, COPG, LSTM, GRU, ED‐ConvLSTM and ED‐ConvGRU. The results indicate that our model surpasses the comparison models in forecasting both high and low solar activity years, across most months and UT moments in a day. Moreover, our model exhibits notably superior prediction performance during the most severe phases of a magnetic storm when compared to the comparison models. Subsequently, we then also discuss how the prediction performance of our model is affected by latitude. Finally, we discuss the diminishing performance of our model in multi‐day predictions, demonstrating that its reliability for forecasts ranging from one to 4 days in advance. Beyond the fifth day, there is a pronounced decline in the model's performance. Plain Language Summary High precision prediction of Total Electron Content (TEC) is of great significance for improving the accuracy of global satellite navigation systems. In this paper, we introduced the attention mechanism into the ionospheric TEC map prediction model to adaptively weight the ionospheric TEC spatiotemporal features, highlighting the contribution of important spatiotemporal features in TEC map prediction. Results showed that the prediction performance of our model is improved compared with the other six models. Key Points Introducing ED‐AttConvLSTM, a novel Total Electron Content (TEC) map prediction model utilizing Convolutional Long Short‐Term Memory and an attention mechanism in an encoder‐decoder framework The incorporation of attention mechanisms markedly decreased root mean square error in TEC map predictions for 2015 and 2019 Our model excels over 6 state‐of‐the‐art models, affirming its robustness and reliability for TEC map prediction
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1542-7390
1539-4964
1542-7390
DOI:10.1029/2023SW003740