Spatiotemporal Prediction of Ionospheric Total Electron Content Based on ED-ConvLSTM

Abstract

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.

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

“…This paper extends Li et al. 's work (2023) by adding an attention mechanism and proposes an Encoder Decoder ConvLSTM model with Attention (ED‐AttConvLSTM). ED‐AttConvLSTM accepts 7 consecutive days of TEC maps within the study area, extracts spatiotemporal features, weights them adaptively, and then converts the weighted spatiotemporal features into TEC maps for the next day.…”

“…To maximize the effective utilization of spatiotemporal features within TEC, this study builds upon the work of Li et al. (2023) by incorporating an attention mechanism. We introduce an Encoder‐Decoder ConvLSTM model with attention, abbreviated as ED‐AttConvLSTM.…”

“…Table 1 presents some researches of spatiotemporal models for ionospheric TEC prediction. Researches have shown that spatiotemporal prediction models outperform time series models in TEC prediction (Li et al, 2023;Luo et al, 2023).…”

“…The existing methods directly use spatiotemporal features for TEC prediction without considering this difference, therefore, spatiotemporal features are not fully utilized. To maximize the effective utilization of spatiotemporal features within TEC, this study builds upon the work of Li et al (2023) by incorporating an attention mechanism. We introduce an Encoder-Decoder ConvLSTM model with attention, abbreviated as ED-AttConvLSTM.…”

TEC Prediction Based on Att-CNN-BiLSTM

“…Influenced by many factors such as solar activity, geomagnetic activity and low-level atmospheric disturbance, ionospheric TEC has very complex spatiotemporal changes. At present, there is no accurate physical prediction model for TEC [6]. So far, there are three main types of short-term prediction methods for ionospheric TEC: ionospheric empirical models, statistical models, and artificial neural network models [7], [8], [9].…”