Techniques for interactive visual examination of vessel performance

• Scalable Visual Analytics for Maritime Data: Proposed approaches to scaling visual analytics techniques from small experimental datasets to large AIS data for maritime vessel movement analysis. • Insights into Vessel Behavior: Revealed valuable insights into both normal and abnormal vessel behaviors through interactive visualization. • Anomaly Detection and Contextualization: Proposed methods for detecting and contextualizing anomalies in vessel movements using clustering, spatial filtering, and spatio-temporal visualization. • Integration with Domain Knowledge : Demonstrated how combining domain knowledge with visual analytics enhances context-aware interpretation and decision-making. • General Workflow and Guidelines: Developed a reusable analysis workflow and a set of practical guidelines for applying visual analytics to large-scale maritime movement data. • Foundation for Real-World Applications: Positioned the techniques as a foundation for human-in-the-loop decision support in future monitoring systems for autonomous maritime operations. The development and evaluation of autonomous maritime vessels rely heavily on data-driven insights from iterative testing and analysis. While initial analyses are often conducted on small experimental datasets to explore key system characteristics, scaling these analyses to large datasets presents significant challenges. In this study, we extend our prior work on visual exploration of small-scale test bed data by proposing approaches to scaling the visual analytics techniques to large datasets. Using AIS data from ferry boats as a proxy for extensive maritime drone operations, we address the challenges of large-scale data exploration over eight days of repetitive ferry movements across a busy strait, simulating conditions suitable for autonomous vessels. Our approach investigates movement patterns, operational stability during repeated trips, and potential collision scenarios. To support such analyses, we propose a general, reusable workflow and a set of practical guidelines for applying visual analytics techniques to large maritime movement datasets. The findings highlight the scalability and adaptability of visual analytics methods, providing valuable tools for analyzing complex maritime datasets and advancing autonomous vessel technologies.