Total electron content (TEC) is a vital parameter for describing the state of the ionosphere, and precise prediction of TEC is of great significance for improving the accuracy of the Global Navigation Satellite System (GNSS). At present, most deep learning prediction models just consider TEC temporal variation, while ignoring the impact of spatial location. In this paper, we propose a TEC prediction model, ED-ConvLSTM, which combines convolutional neural networks with recurrent neural networks to simultaneously consider spatiotemporal features. Our ED-ConvLSTM model is built based on the encoder-decoder architecture, which includes two modules: encoder module and decoder module. Each module is composed of ConvLSTM cells. The encoder module is used to extract the spatiotemporal features from TEC maps, while the decoder module converts spatiotemporal features into predicted TEC maps. We compared the predictive performance of our model with two traditional time series models: LSTM, GRU, a spatiotemporal mode1 ConvGRU, and the TEC daily forecast product C1PG provided by CODE on a total of 135 grid points in East Asia (10°–45°N, 90°–130°E). The experimental results show that the prediction error indicators MAE, RMSE, MAPE, and prediction similarity index SSIM of our model are superior to those of the comparison models in high, normal, and low solar activity years. The paper also analyzed the predictive performance of each model monthly. The experimental results indicate that the predictive performance of each model is influenced by the monthly mean of TEC. The ED-ConvLSTM model proposed in this paper is the least affected and the most stable by the monthly mean of TEC. Additionally, the paper compared the predictive performance of each model during two magnetic storm periods when TEC changes sharply. The results indicate that our ED-ConvLSTM model is least affected during magnetic storms and its predictive performance is superior to those of the comparative models. This paper provides a more stable and high-performance TEC spatiotemporal prediction model.

Ionosphere disturbances are mainly caused by solar activities and earth surface activities. Different electromagnetic wave disturbances show different shapes on the spectrogram, such as artificial very low frequency transmitting stations, power systems, and satellite platform disturbances which all show a horizontal shape. Due to the electric field coupling or superposition by other electromagnetic disturbances, the horizontal electromagnetic wave clarity on the spectrogram is reduced, interrupted, or disappears. Aiming at this phenomenon, based on computer vision technology, this paper proposes an automatic detection and recognition algorithm for the space electric field abnormal interference. Firstly, the horizontal electromagnetic wave on the spectrogram is detected, and then the detected window density on the horizontal line is counted. We then record and save the density anomaly windows on multiple horizontal lines at the same time, so as to realize the electric field anomaly disturbance automatic detection. The accuracy of the algorithm for detecting continuous electromagnetic wave disturbance with a wide frequency and time interval is up to 98.2%. Through the space electromagnetic disturbances automatic identification from massive data, combined with space events and multi-dimensional information, such as time, space and orbit, it is helpful to further find out the global space-time transformation laws of space events.

The recognition algorithm of the lightning whistler wave, based on intelligent speech, is the key technology to break the bottleneck of massive data and study the temporal and spatial variation rules of the lightning whistler wave. However, its recognition effect depends on the hyperparameters determined by manual experiments repeatedly, which takes a great deal of time and cannot guarantee the best recognition effect of the model. Therefore, we proposed the lightning whistler wave recognition algorithm based on grey wolf optimization (GWO). In this paper, the GWO algorithm is used to automatically find the best value of hyperparameters of Long Short-Term Memory (LSTM) in their limited searching space. Here we consider the number of hidden units (hu) and learning rate (lr) as the hyperparameters to be optimized, and the spatial coordinate (hu, lr) as the grey wolf position. By the end of the GWO process, we obtain the position of the wolf king α with the optimal hu and lr searched by the GWO algorithm. Then we use the optimal hu and lr to configure LSTM and perform supervised learning on the train set to obtain the final lightning whistler wave speech recognition model. Through experimental verification, the recognition model based on the GWO not only overcomes the uncertainty of the traditional model relying on manual finetuning of parameters and realizes the mechanism of automatic search and acquisition of hyperparameters, but also its recognition effect improves by about 2% in accuracy, F1score, and other metrics compared with the model trained by manually setting hyperparameters.

Since the CSES (China Seismo-Electromagnetic Satellite) has been in orbit, it has detected a large number of constant-frequency electromagnetic disturbances (CFEDs), which are horizontal lines on the spectrum. In this paper, we present an algorithm for automatic recognition of CFEDs based on computer vision technology. The relevant results are of great significance for analysis of perturbation events and mining of the transformation laws of global space events. First, a grayscale spectrogram is obtained; then, a horizontal convolution kernel is used to enhance the horizontal edge features of the grayscale graph, and finally, black-and-white binarization is performed to complete data preprocessing. The preprocessed data are then fed into an unsupervised cluster model for training and recognition to realize automatic recognition of CFEDs. Experimental results show that the CFED recognition algorithm proposed in this paper is effective, with a recognition accuracy of more than 98%.

Pulse signals refer to electromagnetic waveforms with short duration and high peak energy in the time domain. Spatial electromagnetic pulse interference signals can be caused by various factors such as lightning, arc discharge, solar disturbances, and electromagnetic disturbances in space. Pulse disturbance signals appear as instantaneous, high-energy vertical-line pulse trains (VLPTs) on the spectrogram. This paper uses computer vision techniques and unsupervised clustering algorithms to process and analyze VLPT on very-low-frequency (VLF) waveform spectrograms collected by the China Seismo-Electromagnetic Satellite (CSES) electric field detector. First, the waveform data are transformed into time–frequency spectrograms with a duration of 8 s using the short-time Fourier transform. Then, the spectrograms are subjected to grayscale transformation, vertical line feature extraction, and binarization preprocessing. In the third step, the preprocessed data are dimensionally reduced and fed into an unsupervised K-means++ clustering model to achieve automatic recognition and labeling of VLPTs. By recognizing and studying VLPT, not only can interference be recognized, but the temporal and spatial locations of these interferences can also be determined. This lays the foundation for identifying VLPT sources and gaining deeper insights into the generation, propagation, and characteristics of electromagnetic radiation.

Ionospheric disturbances are mainly caused by solar and Earth surface activity. The electromagnetic data collected by the CSES (China Seismo-Electromagnetic Satellite, popularly known as the Zhangheng-1 satellite) can capture many space disturbances. Different spatial disturbances can exhibit distinctive shapes on spectrograms. Constant-frequency electromagnetic disturbances (CFEDs) such as artificially transmitted VLF radio waves, power line harmonics, and satellite platform disturbances can appear as horizontal lines on spectrograms. Therefore, we used computer vision and machine learning techniques to extract the frequency of global CFEDs and analyze their strong spatial signal characteristics. First, we obtained time-frequency spectrograms from CSES VLF electric-field waveform data using Fourier transform. Next, we employed an unsupervised clustering algorithm to automatically recognize CFED horizontal lines on spectrograms, merging horizontal lines from different spectrograms, to obtain the CFED horizontal-line frequency range. In the third stage, we verified the presence of CFEDs in power spectrograms, thus extracting their true frequency values. Finally, for strong CFED signals, we generated eight revisited periods, resulting in 10,230 power spectrograms for analyzing each CFED’s spatial characteristics using a combined periodic sequence and spatial region that included frequency offsets, frequency fluctuations, and signal non-observation areas. These findings contribute to enhancing the quality of CSES observational data and provides a theoretical basis for constructing global CFED spatial background fields and earthquake monitoring and early prediction systems.