AIS-Based Hybrid Vessel Trajectory Prediction for Enhanced Maritime Navigation

The growing integration of non-terrestrial networks (NTNs), particularly low Earth orbit (LEO) satellite constellations, has significantly extended the reach of maritime connectivity, supporting critical applications such as vessel monitoring, navigation safety, and maritime surveillance in remote and oceanic regions. Automatic Identification System (AIS) data, increasingly collected through a combination of satellite and terrestrial infrastructures, provide a rich source of spatiotemporal vessel information. However, accurate trajectory prediction in maritime domains remains challenging due to irregular sampling rates, dynamic environmental conditions, and heterogeneous vessel behaviors. This study proposes a velocity-based trajectory prediction framework that leverages AIS data collected from integrated satellite–terrestrial networks. Rather than directly predicting absolute positions (latitude and longitude), our model predicts vessel motion in the form of latitude and longitude velocities. This formulation simplifies the learning task, enhances temporal continuity, and improves scalability, making it well-suited for resource-constrained NTN environments. The predictive architecture is built upon a Long Short-Term Memory network enhanced with attention mechanisms and residual connections (LSTM-RA), enabling it to capture complex temporal dependencies and adapt to noise in real-world AIS data. Extensive experiments on two maritime datasets validate the robustness and accuracy of our framework, demonstrating clear improvements over state-of-the-art baselines.