Ionospheric forecasts are critical for space-weather anomaly detection. Forecasting ionospheric total electron content (TEC) from the global navigation satellite system (GNSS) is of great significance to near-earth space environment monitoring. In this study, we propose a novel ionospheric TEC forecasting model based on deep learning, which consists of a convolutional neural network (CNN), long-short term memory (LSTM) neural network, and attention mechanism. The attention mechanism is added to the pooling layer and the fully connected layer to assign weights to improve the model. We use observation data from 24 GNSS stations from the Crustal Movement Observation Network of China (CMONOC) to model and forecast ionospheric TEC. We drive the model with six parameters of the TEC time series, Bz, Kp, Dst, and F10.7 indices and hour of day (HD). The new model is compared with the empirical model and the traditional neural network model. Experimental results show the CNN-LSTM-Attention neural network model performs well when compared to NeQuick, LSTM, and CNN-LSTM forecast models with a root mean square error (RMSE) and R² of 1.87 TECU and 0.90, respectively. The accuracy and correlation of the prediction results remained stable in different months and under different geomagnetic conditions.

Accurate corrections for ionospheric total electron content (TEC) and early warning information are crucial for global navigation satellite system (GNSS) applications under the influence of space weather. In this study, we propose to use a new machine learning model—the Prophet model, to predict the global ionospheric TEC by establishing a short-term ionospheric prediction model. We use 15th-order spherical harmonic coefficients provided by the Center for Orbit Determination in Europe (CODE) as the training data set. Historical spherical harmonic coefficient data from 7 days, 15 days, and 30 days are used as the training set to model and predict 256 spherical harmonic coefficients. We use the predicted coefficients to generate a global ionospheric TEC forecast map based on the spherical harmonic function model and select a year with low solar activity (63.4 < F10.7 < 81.8) and a year with the high solar activity (79.5 < F10.7 < 255.0) to carry out a sliding 2-day forecast experiment. Meanwhile, we verify the model performance by comparing the forecasting results with the CODE forecast product (COPG) and final product (CODG). The results show that we obtain the best predictions by using 15 days of historical data as the training set. Compared with the results of CODE’S 1-Day (C1PG) and CODE’S 2-Day (C2PG). The number of days with RMSE better than COPG on the first and second day of the low-solar-activity year is 151 and 158 days, respectively. This statistic for high-solar-activity year is 183 days and 135 days.

In this paper, we forecasted the ionospheric total electron content (TEC) over the region of China using the bidirectional convolutional gated recurrent unit (BiConvGRU) model. We first generated the China Regional Ionospheric Maps (CRIMs) using GNSS observations provide by the Crustal Movement Observation Network of China (CMONOC). We then used gridded TEC maps from 2015 to 2018 with a 1 h interval from the CRIMs as the dataset, including quiet periods and storm periods of ionospheric TEC. The BiConvGRU model was then utilized to forecast the ionospheric TEC across China for the year 2018. The forecasted TEC was compared with the TEC from the International Reference Ionosphere (IRI-2016), Convolutional Long Short-Term Memory (ConvLSTM), Convolutional Gated Recurrent Unit (ConvGRU), Bidirectional Convolutional Long Short-Term Memory (BiConvLSTM), and the 1-day Predicted Global Ionospheric Map (C1PG) provided by the Center for Orbit Determination in Europe (CODE). In addition, indices including Kp, ap, Dst and F10.7 were added to the training dataset to improve the forecasting accuracy of the model (-A indicates no indices, while -B indicates with indices). The results verified that the prediction accuracies of the models integrated with these indices were significantly improved, especially during geomagnetic storms. The BiConvGRU-B model presented a decrease of 41.5%, 22.3%, and 13.2% in the root mean square error (RMSE) compared to the IRI-2016, ConvGRU, and BiConvLSTM-B models during geomagnetic storm days. Furthermore, at a specific grid point, the BiConvGRU-B model showed a decrease of 42.6%, 49.1%, and 31.9% in RMSE during geomagnetic quiet days and 30.6%, 34.1%, and 15.1% during geomagnetic storm days compared to the IRI-2016, C1PG, and BiConvLSTM-B models, respectively. In the cumulative percentage analysis, the BiConvGRU-B model had a significantly higher percentage of mean absolute error (MAE) within the range of 0–1 TECU in all seasons compared to the BiConvLSTM-B model. Meanwhile, the BiConvGRU-B model outperformed the BiConvLSTM-B model with lower RMSE for each month of 2018.

In this article, we propose a convolutional gated recurrent unit (ConvGRU) deep learning method to forecast ionospheric total electron content (TEC) over China based on the regional ionospheric maps (RIMs) from 2015 to 2018. First, we use Global Navigation Satellite System observations from the Crustal Movement Observation Network of China to generate the RIMs of China (CRIMs). Second, we use the CRIMs of 2015–2017 as the training set to predict the ionospheric TEC over China in 2018. Finally, comparative experiments are carried out with ConvLSTM, International Reference Ionosphere (IRI), and Center for Orbit Determination in Europe's (CODE's) 1-day predicted Global Ionospheric Map (C1PG) released by CODE. In addition, we add geomagnetic indices (ap, Kp, and Dst) and solar activity index (F10.7) as the training set to analyze the prediction accuracy of the model (using -A if there are no indices, and -B if there are indices). The results illustrate that the prediction accuracy of ConvLSTM-B and ConvGRU-B models are improved on both geomagnetic storm and quiet days, and the improvement is more obvious on geomagnetic storm days. Furthermore, the root mean square error (RMSE) of the ConvGRU-B model decreases by 28%, 22.4%, and 5.9% compared to that of the ConvGRU-A, IRI-2016, and ConvLSTM-B models during geomagnetic storm days, respectively. For the prediction accuracy of a certain grid point, the RMSE of the ConvGRU-B model decreases by 23%, 32.6%, and 19.3% during geomagnetic quiet days and 24.4%, 30.6%, and 15.7% during geomagnetic storm days compared to that of the ConvGRU-A, IRI-2016, and ConvLSTM-B models, respectively. For the forecast accuracy of TEC in different seasons, the performance of the ConvGRU-B model is also better than that of the ConvLSTM-B model in 2018. These results show that the ConvGRU-B model has competitive performance in RIMs prediction over China during the geomagnetic quiet and storm days.

Total electron content (TEC) is an important parameter for studying ionospheric variations and space weather. Short-term prediction of the ionosphere plays a significant role in near-Earth space environment monitoring. This study proposes a model that combines a long short-term memory (LSTM) neural network with a localized attention mechanism (LAM), which weights the features using attention weights and connects them to a fully connected output layer. The model is constructed using TEC data from 16 Global Navigation Satellite System (GNSS) observation stations provided by the Crustal Movement Observation Network of China (CMONOC), along with six parameters: Bz, Kp, Dst, F10.7 indices, and hour of the day. The LAM-LSTM model is compared with the LSTM model and the BP model. Experimental results show that the LAM-LSTM model achieves a root mean square error (RMSE) of 1.35 TECU on average for the test dataset, while the LSTM model has an RMSE of 1.54 TECU, and the BP model has an RMSE of 1.74 TECU. The proposed model exhibits good stability in different geomagnetic conditions and different months.