Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data

Accurate vessel track prediction is key for maritime traffic control and management. results can enable collision avoidance, in addition to being suitable planning routes advance, shortening the sailing distance, improving navigation efficiency. Vessel using automatic identification system (AIS) data has attracted extensive attention community. In this study, a combining density-based spatial clustering of applications with noise (DBSCAN)-based long short-term memory (LSTM) model (denoted as DLSTM) was developed prediction. DBSCAN used cluster tracks, LSTM then training The performance DLSTM compared that support vector regression, recurrent neural network, conventional models. revealed proposed outperformed these models by approximately 2–8%. able provide better which subsequently improve efficiency safety control.