AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks
For maritime safety and efficiency, this work shows that memory-augmented models can improve vessel trajectory prediction, though it is an incremental application of existing methods to a new domain.
This paper investigates memory-augmented neural networks for vessel trajectory prediction using AIS data, achieving consistent and substantial performance gains over deep learning baselines without external memory on datasets from the Gulf of Mexico and the New York Bight.
Accurate vessel trajectory prediction is essential for safe and efficient maritime operations, enabling collision avoidance and supporting route optimization. Although memory-augmented neural networks have recently shown strong performance in pedestrian and road-vehicle trajectory prediction by selectively retrieving relevant information from an external memory, their potential for vessel trajectory prediction remains underexplored. This paper presents an empirical investigation of memory-based trajectory prediction using Automatic Identification System (AIS) data. Experiments on data from the Gulf of Mexico and the New York Bight demonstrate consistent and substantial performance gains over a range of deep learning baselines that do not incorporate an external memory.