This study proposes high-frequency container port congestion measures based on Automatic Identification System (AIS) data. Vessel movement information of 3,957 container ships from March 2017 to April 2017 is included. The world top 20 container ports’ berth and anchorage areas are identified through Density Based Spatial Clustering of Applications with Noise (DBSCAN) and convex hull methods, and their hourly port congestion statuses are depicted in terms of the traffic volume and turnaround time. The constructed congestion measures overcome the disadvantages of the traditionally used port or industry data, which is heterogenous, behind the time and not easy to obtain publicly. The higher frequency (hourly) of the proposed measures can effectively monitor any slight change in port performance. A Long Short-Term Memory (LSTM) neural network model is then proposed for congestion prediction using constructed congestion measures. Point prediction and sequence prediction are both performed. We innovatively introduce congestion propagation effects into the prediction model as input features. Using Shanghai, Singapore and Ningbo ports as case studies, results show that the inclusion of congestion propagation effect can improve the prediction performance especially for sequence prediction. This study provides significant implications and decision support for container shipping market participants.

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.