AI framework boosts vessel trajectory accuracy 25% using ocean data

A team of researchers (Gnanavel, Fernando, Sridharan, Fookes) has developed a hierarchical two-stage framework for environment-aware long-horizon vessel trajectory prediction. The system addresses the challenge of forecasting ship movements under real ocean conditions by combining a coarse long-term predictor with a grid-aware short-term predictor via a hierarchical fusion mechanism. The short-term branch leverages a Spatio-Temporal Graph Transformer on discretized maritime cells to capture localized dynamics, while the long-term branch encodes overarching navigational intent. An integrated environmental module incorporates oceanographic parameters—surface currents, wind vectors, and significant wave height—using cross-modal attention and feature-wise modulation for adaptive response to varying sea conditions. Additionally, a learnable Savitzky-Golay smoothing layer enhances temporal coherence in fused trajectories.

The framework was evaluated on Australian Craft Tracking System (CTS) data from the North West region, aligned with Copernicus Marine Service products, using a 3-hour input and a 10-hour prediction horizon. Experimental results show that the framework outperforms the state-of-the-art by 25% in Average Displacement Error (ADE) and 17% in Final Displacement Error (FDE). Ablation studies further validated the contribution of each component—the environmental module alone improved ADE by 8%. This research has significant implications for collision avoidance, traffic management, and route planning in maritime operations, offering a robust method to handle long-range temporal dependencies and dynamic environmental factors that have historically made long-horizon prediction difficult.