WEG: Schätzung des Schiffsbestimmungsorts in weltweiten AIS-Trajektorien
WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
December 15, 2025
papers.authors: Jin Sob Kim, Hyun Joon Park, Wooseok Shin, Dongil Park, Sung Won Han
cs.AI
papers.abstract
Das Automatic Identification System (AIS) ermöglicht eine datengestützte maritime Überwachung, leidet jedoch unter Zuverlässigkeitsproblemen und unregelmäßigen Intervallen. Wir behandeln die Schiffszielschätzung unter Verwendung globaler AIS-Daten, indem wir einen differenzierten Ansatz vorschlagen, der lange Hafen-zu-Hafen-Trajektorien als eine geschachtelte Sequenzstruktur neu formuliert. Diese Methode mildert unter Verwendung räumlicher Raster räumlich-zeitliche Verzerrungen ab, während sie die detaillierte Auflösung beibehält. Wir stellen eine neuartige Deep-Learning-Architektur namens WAY vor, die dafür konzipiert ist, diese umformulierten Trajektorien zur langfristigen Ziels
English
The Automatic Identification System (AIS) enables data-driven maritime surveillance but suffers from reliability issues and irregular intervals. We address vessel destination estimation using global-scope AIS data by proposing a differentiated approach that recasts long port-to-port trajectories as a nested sequence structure. Using spatial grids, this method mitigates spatio-temporal bias while preserving detailed resolution. We introduce a novel deep learning architecture, WAY, designed to process these reformulated trajectories for long-term destination estimation days to weeks in advance. WAY comprises a trajectory representation layer and Channel-Aggregative Sequential Processing (CASP) blocks. The representation layer generates multi-channel vector sequences from kinematic and non-kinematic features. CASP blocks utilize multi-headed channel- and self-attention for aggregation and sequential information delivery. Additionally, we propose a task-specialized Gradient Dropout (GD) technique to enable many-to-many training on single labels, preventing biased feedback surges by stochastically blocking gradient flow based on sample length. Experiments on 5-year AIS data demonstrate WAY's superiority over conventional spatial grid-based approaches regardless of trajectory progression. Results further confirm that adopting GD leads to performance gains. Finally, we explore WAY's potential for real-world application through multitask learning for ETA estimation.