A Data-Driven Iterative Multi-Attribute Clustering Algorithm and Its Application in Port Congestion Estimation

Container port congestion threatens the effectiveness and sustainability of the global supply chain because it stagnates cargo flows and triggers ripple effects across connected, multimodal freight transport networks. This study aims to develop a novel and tangible method to measure port congestion by investigating ship behaviors between different zones in port waters. Different port zones have varying ship densities because ships moor in the anchorage area randomly but dock at berths in an orderly and close fashion. This observation leads us to apply the density-based clustering method for port zone identification and differentiation. In order to ensure the method is globally applicable and accurate, we develop a new clustering algorithm, an iterative, multi-attribute DBSCAN (IMA-DBSCAN), which incorporates an iterative process, together with both spatial information and domain knowledge. The necessary input data for the algorithm is extracted from the Automatic Identification System (AIS), a satellite-based tracking system with real-time ship positioning and sailing data. An illustrative case suggests that our algorithm can rapidly and precisely identify anchorage areas and individual berths (even in a port with complicated geographic features), while other methods cannot. The algorithm is applied to measure congestion at 20 major container ports in the world. The results show a significant increase in congestion at the Port of Los Angeles from August to December 2020, which matches the realistic statistics and proves the efficiency and practical applicability of the proposed algorithm.