Optimizing vessel trajectories: Advanced denoising and interpolation techniques for AIS data

Abstract

The quality of vessel trajectory data is essential for effective maritime traffic control, enhanced situational awareness, and the advancement of maritime algorithms. However, various factors—such as human error, signal interference, and environmental conditions—frequently introduce anomalies and result in missing data within vessel trajectories, thereby compromising the usability of such data. This study introduces a comprehensive framework for AIS trajectory denoising and interpolation, aimed at restoring incomplete and noisy vessel trajectories. Our approach integrates a “Segmentation-Integration-Selection" process to detect and remove outliers, followed by tailored interpolation techniques that handle both short-range and long-range trajectory gaps. For short gaps, kinematic-based interpolation is employed, while long gaps are addressed through data transfer from similar historical trajectories. Experimental results demonstrate that our method significantly improves upon traditional approaches, achieving higher accuracy in reconstructing reliable vessel trajectories. This work provides a robust solution for enhancing the completeness and precision of AIS data, with implications for maritime safety, traffic control, and the future of intelligent shipping systems.