Prediction of the Diurnal Variation of VLF Waves in Earth-Ionosphere Waveguide Based on BPNN-TL Method
Yurong Pu, Yuanyuan Chen, Yi Dong, Kai Zhang, Fengjuan Wang, Xiaoli Xi · IEEE Antennas and Wireless Propagation Letters · 2024
Accurate prediction of the diurnal variations of very low frequency (VLF) waves in the Earth-ionosphere waveguide is still a challenging task. In this letter, a novel method, which consists of a back-propagation neural network (BPNN) and transfer learning (TL) approach known as BPNN-TL, is introduced to predict the diurnal variations of VLF waves. The BPNN is used to pre-train a network model based on a theoretical dataset generated by the waveguide mode theory. The parameters of the pre-trained model are later fine-tuned by the TL technique with measured data. By taking the advantage of BPNN and TL, the reality gap caused by inevitable theoretical modeling approximation errors is mitigated.