Aircraft Trajectory Prediction Model Based on Improved GRU Structure

Abstract

In view of the actual need to predict aircraft trajectory, traditional prediction models often have problems such as insufficient precision and slow training efficiency. By analyzing the target trajectory with temporal characteristics, the Elastic-BiGRU trajectory prediction model is proposed, which combines the Smooth filtering method, the Elastic Network fitting method and the GRU structure, the prediction accuracy of aircraft trajectory is further improved. The experimental results show that the Elastic-BiGRU model compared with Bi-LSTM model and Bi-GRU model, its MSE error is relatively reduced by more than 8% and 11%The Elastic-BiGRU also solves the problem of slow training speed of Bi-LSTM model, and saves about 20% of the time.