Shipping map: An innovative method in grid generation of global maritime network for automatic vessel route planning using AIS data

Journal article, 2025

Considering the challenges faced by current global grid-based route planning methods, including vessel navigability underestimation and high computational demands for fine grid configuration, this study introduces an innovative approach to the grid generation of a global maritime network for automatic vessel route planning. By leveraging global Automatic Identification System (AIS) data, the methodology focuses on advanced trajectory segmentation, waypoint detection, clustering algorithms, and route searching. A novel spatiotemporal approach is proposed to facilitate effective trajectory segmentation despite data discontinuities. The Pruned Exact Linear Time (PELT) algorithm is employed to identify waypoints, managing their quantity during heading instability. To recognize crucial berthing areas in ports and strategic waypoint zones at sea, a customized KNN-block adaptive Density-Based Spatial Clustering of Applications with Noise (CKBA-DBSCAN) is developed to address the challenges of varying density clustering parameters and high computational costs. Lastly, the double-layer network matching technique, which starts with grid-based route planning and refines to the final navigable and smoothed route, uniquely integrates data-driven and model-based strategies. Rigorous testing with a year's worth of global AIS data demonstrates high efficiency in planning navigable routes for various vessel types on worldwide voyages. The results underscore the practicality of the proposed approach in real-world route planning and maritime shipping network development. Remarkably, the methodology achieves a minimum 17.08 % reduction in time for global route generation. This hybrid approach, which integrates the strengths of both data-driven and model-based methods, significantly enhances vessel scheduling and routing efficiencies, showcasing its superior performance in comparative studies and its potential for widespread adoption in the maritime industry.