A forecasting model of ionospheric foF2 using the CNN-BiLSTM network

To further boost the performance of short-term predictions for the ionospheric F2 layer's critical frequency (foF2), a series model based on convolutional neural network (CNN) and bidirectional long-term memory neural network (BiLSTM) is constructed. The hourly foF2 values from Qingdao to Wuhan, Xinxiang to Wuhan and Suzhou to Wuhan were used for training and verification. To evaluate the predictive performance of the CNN-BiLSTM model. A comparative analysis was performed with the deep learning BiLSTM model. Through statistical analysis of foF2 parameter observation values and model prediction results. The experiment results show that the CNN-BiLSTM model with deep learning has a higher robustness and usability, and can further boost the performance of short term prediction of foF2. And the proposed method can be used to predict foF2 accurately.