Unsupervised Port Berth Identification from Automatic Identification System Data

TL;DR

This paper introduces an unsupervised, data-driven method using AIS data clustering and hyperparameter tuning to accurately identify port berths, outperforming existing approaches and enhancing port operation insights.

Contribution

It presents a novel unsupervised spatial modeling approach for port berth detection using AIS data, improving accuracy and robustness over prior methods.

Findings

Achieved a mean Bhattacharyya distance of 0.85 with GMMs, outperforming previous methods.

Successfully applied the approach across diverse port sizes and environments.

Provided qualitative evidence of more precise berth boundaries and better spatial resolution.

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.