Ship Track Prediction Model based on Automatic Identification System Data and Bidirectional Cyclic Neural Network

In order to further improve the accuracy of ship navigation dynamic prediction, a ship navigation trajectory prediction method combining automatic identification system (AIS) and deep learning is proposed. The AIS data is transformed into navigation dynamic time series, and the navigation trajectory features are extracted for the training and testing of long short term memory (LSTM) based on attention mechanism. The prediction results can provide reference for the supervision of vessel traffic services(VTS),and have high practical application value in early warning of ship collision, stranding and other accidents.