Maritime Tracking Data Analysis and Integration with AISdb

TL;DR

This work tackles the challenge of processing vast, noisy AIS data for maritime safety and environmental analysis by introducing AISdb, an open-source Python library that loads, cleans, interpolates, filters, visualizes, and integrates AIS data with environmental datasets on SQLite or PostgreSQL backends. The authors detail a modular software architecture with ten core functionalities, including decoding, noise removal, trajectory interpolation, GIS-based analysis, data integration, and export, plus live-stream support and a WebAssembly-based visualization interface. They illustrate AISdb's scientific impact through diverse case studies—ranging from gravity-model traffic forecasting to ecosystem and conservation applications—and outline future directions for dataset expansion and broader stakeholder collaboration. Collectively, AISdb provides a reproducible, scalable platform that enhances maritime safety, security, and environmental decision-making by unlocking rich, integrated spatiotemporal insights from AIS data.

Abstract

Efficiently handling Automatic Identification System (AIS) data is vital for enhancing maritime safety and navigation, yet is hindered by the system's high volume and error-prone datasets. This paper introduces the Automatic Identification System Database (AISdb), a novel tool designed to address the challenges of processing and analyzing AIS data. AISdb is a comprehensive, open-source platform that enables the integration of AIS data with environmental datasets, thus enriching analyses of vessel movements and their environmental impacts. By facilitating AIS data collection, cleaning, and spatio-temporal querying, AISdb significantly advances AIS data research. Utilizing AIS data from various sources, AISdb demonstrates improved handling and analysis of vessel information, contributing to enhancing maritime safety, security, and environmental sustainability efforts.

Figures (4)

• Figure 1: The technical architecture of AISdb workflow.
• Figure 2: The image demonstrates the stages of applying the noise removal technique on vessel trajectory data from the North Atlantic Ocean: (1) Initial Data shows raw trajectories with inherent noise and variability; (2) Noise Dominated emphasizes the proliferation of noisy data points, creating a highly cluttered visual on top of Step (1); (3) Post-Processing reveals the cleaned trajectories after noise reduction, significantly improving the clarity and interpretability of vessel movements.
• Figure 3: AIS data query, trajectory interpolation, and visualization Python script example using AISdb. The first step sets up a connection to an SQLite database and queries the last 20 hours of data contained in the database. The second step returns trajectories from the database that are split if time gaps are larger than 24 hours. The third step uses a great circle distance filter with a 200 km distance and 50 knots speed threshold to segment the trajectories further. In a fourth step, each trajectory is now interpolated with a time step of 5 minutes. Finally, the trajectories are plotted in a web interface.
• Figure 4: The web interface visualization showcases the diverse trajectories of vessels near our AIS Station antennas in Halifax at Dalhousie University and the National Research Council (NRC) Sandy Cove site, captured through AISdb’s tracking module and station. Vessel types are represented by different colors, and each line represents the ship's trajectory. The visualization illustrates how users can track vessels and query data using the web interface by selecting a region, range of dates, and vessel type.