Leveraging the Empirical Wavelet Transform in Combination with Convolutional LSTM Neural Networks to Enhance the Accuracy of Polar Motion Prediction

Abstract High-precision polar motion prediction is of great significance for deep space exploration and satellite navigation. Polar motion is affected by a variety of excitation factors, and nonlinear prediction methods are more suitable for polar motion prediction. In order to explore the effect of deep learning in polar motion prediction. This paper proposes a combined model based on empirical wavelet transform (EWT), Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM). By training and forecasting EOP 20C04 data, the effectiveness of the algorithm is verified, and the performance of two forecasting strategies in deep learning for polar motion prediction is explored. The results indicate that recursive multi-step prediction performs better than direct multi-step prediction for short-term forecasts within 15 days, while direct multi-step prediction is more suitable for medium and long-term forecasts. In the 365 days forecast, the mean absolute error of EWT-CNN-LSTM in the X direction and Y direction is 18.25 mas and 15.78 mas, respectively, which is 23.5% and 16.2% higher than the accuracy of Bulletin A. The results show that the algorithm has a good effect in medium and long term polar motion prediction.