Ship Trajectory Prediction Based on Ensemble Empirical Mode Decomposition and Optimized Long Short-Term Memory Network

Ship trajectory prediction is crucial for building an intelligent maritime safety system, reducing ship accidents, and improving maritime safety. Aiming at the present situation that a single prediction model cannot well extract features from ship trajectory data, and meet the current prediction accuracy requirements, a combined predicting model based on ensemble empirical mode decomposition (EEMD), sparrow search algorithm (SSA) and long short-term memory network (LSTM) is proposed. The model extracts trajectory information through EEMD and optimizes LSTM hyperparameters through SSA, thereby improving the accuracy of trajectory prediction. The Danish Automatic Identification System (AIS) data are used for experimental verification. The experimental results show that compared with LSTM, SSA-LSTM, and convolutional neural network models, the model proposed in this paper has the smallest root mean square error and higher prediction accuracy.