Ionospheric VTEC Prediction Based on Long Short-Term Memory Network

This article presents a short-term forecasting model for ionospheric VTEC based on Long Short-Term Memory (LSTM) neural networks, utilizing solar activity and geomagnetic activity parameters, along with VTEC data provided by the European Space Agency. The results show that the root mean square error of the VTEC predicted by the LSTM neural network model is 1.125 TECU (1TEC=1016[::el::]/m2), which ...