Unsupervised Port Berth Identification from Automatic Identification System Data

2025-05-17

AI Summary

To address the challenges of incomplete and ambiguously bounded berth data in public port databases, this paper proposes an unsupervised berth identification method leveraging Automatic Identification System (AIS) trajectories. The method integrates spatiotemporal clustering with Bayesian hyperparameter optimization, introducing a novel Gaussian Mixture Model (GMM)-driven multi-scale berth modeling framework that automatically learns berth spatial distributions while jointly optimizing clustering granularity and model complexity. Evaluated across multiple real-world ports, the approach achieves an average Bhattacharyya distance of 0.85—representing a 94% improvement over the best baseline. Qualitative analysis confirms high localization accuracy, sharp boundary delineation, and significantly enhanced spatial resolution compared to existing methods. This work provides a scalable, annotation-free infrastructure for port operational monitoring and global supply chain digitization.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Clustering
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

Port berthing sites are regions of high interest for monitoring and optimizing port operations. Data sourced from the Automatic Identification System (AIS) can be superimposed on berths enabling their real-time monitoring and revealing long-term utilization patterns. Ultimately, insights from multiple berths can uncover bottlenecks, and lead to the optimization of the underlying supply chain of the port and beyond. However, publicly available documentation of port berths, even when available, is frequently incomplete - e.g. there may be missing berths or inaccuracies such as incorrect boundary boxes - necessitating a more robust, data-driven approach to port berth localization. In this context, we propose an unsupervised spatial modeling method that leverages AIS data clustering and hyperparameter optimization to identify berthing sites. Trained on one month of freely available AIS data and evaluated across ports of varying sizes, our models significantly outperform competing methods, achieving a mean Bhattacharyya distance of 0.85 when comparing Gaussian Mixture Models (GMMs) trained on separate data splits, compared to 13.56 for the best existing method. Qualitative comparison with satellite images and existing berth labels further supports the superiority of our method, revealing more precise berth boundaries and improved spatial resolution across diverse port environments.

Problem

• Identifies port berths using unsupervised AIS data clustering
• Addresses incomplete public berth documentation inaccuracies
• Optimizes port operations by revealing utilization patterns

Innovation

• Unsupervised spatial modeling with AIS data
• Clustering and hyperparameter optimization for berth identification
• Outperforms existing methods in precision and resolution