Prediction of Global Ionospheric Total Electron Content (TEC) Based on SAM-ConvLSTM Model

This paper first applies a prediction model based on self-attention memory ConvLSTM (SAM-ConvLSTM) to predict the global ionospheric total electron content (TEC) maps with up to 1 day of lead time. We choose the global ionospheric TEC maps released by the Center for Orbit Determination in Europe (CODE) as the training data set covering the period from 1999 to 2022. Besides that, we put several space environment data as additional multivariate-features into the framework of the prediction model to enhance its forecasting ability. In order to confirm the efficiency of the proposed model, the other two prediction models based on convolutional long short-term memory (LSTM) are used for comparison. The three models are trained and evaluated on the same data set. Results show that the proposed SAM-ConvLSTM prediction model performs more accurately than the other two models, and more stably under space weather events. In order to assess the generalization capabilities of the proposed model amidst severe space weather occurrences, we selected the period of 22-25 April 2023, characterized by a potent geomagnetic storm, for experimental validation. Subsequently, we employed the 1-day predicted global TEC products from the Center for Operational Products and Services (COPG) and the SAM-ConvLSTM model to evaluate their respective forecasting prowess. The results show that the SAM-ConvLSTM prediction model achieves lower prediction error. In one word, the ionospheric TEC prediction model proposed in this paper can establish the ionosphere TEC of spatio-temporal data association for a long time, and realize high precision of prediction performance. The ionosphere is a major area of space activities, which has a direct impact and indirect effects on radio communication, navigation, and positioning. The total electron content (TEC) is an important parameter to describe the morphology and structure of the ionosphere. Therefore, it's particularly necessary to predict the ionospheric TEC. To handle this problem, we first apply a prediction model based on self-attention memory ConvLSTM (SAM-ConvLSTM) to predict the global ionospheric TEC maps with up to 1 day of lead time. Moreover, the other two prediction models based on convolutional long short-term memory (LSTM) are also investigated for comparison, and the results show that the SAM-ConvLSTM prediction model performs best. Besides that, we test the prediction accuracy and robustness during the period of a severe space weather event by using the CODE's 1-day predicted global TEC products (COPG) and SAM-ConvLSTM model respectively, and we find the proposed prediction model performs stably. SAM-ConvLSTM prediction model achieves an excellent predictive performance of global ionospheric total electron content mapsSAM-ConvLSTM prediction model shows the significantly best performance among the other prediction models based on convolutional LSTMSAM-ConvLSTM prediction model performs more accurately and robustly compared to the COPG model under the severe space weather events