<![CDATA[Maritime traffic management in major ports requires a comprehensive understanding of vessel movement patterns to ensure operational efficiency and safety. This study presents a spatio-temporal analysis of vessel traffic in Kaohsiung Port, Taiwan, utilizing a 10-month snapshot of AIS data (December 2024–October 2025). Employing quantitative methods including Kernel Density Estimation (KDE) for spatial intensity mapping, grid-based discretization for traffic density quantification, and temporal resolution analysis at multiple scales, the research identifies key operational hotspots and peak traffic periods. The analysis encompasses 1,247,890 AIS records from diverse vessel types, revealing distinct spatial clustering patterns in port entrance channels, anchorage zones, and terminal areas. Temporal analysis demonstrates pronounced diurnal and weekly cyclical patterns, with peak traffic intensities occurring during daytime operational hours and weekdays, reflecting commercial shipping schedules and port operational rhythms. The KDE-based hotspot identification reveals high-density zones concentrated within 0.5 nautical miles of major container terminals, indicating critical areas requiring enhanced traffic monitoring and collision avoidance measures. Grid-based traffic density quantification provides granular insights into vessel distribution across different port sectors, enabling zone-specific risk assessment and resource allocation strategies. The findings reveal complex spatio-temporal patterns that reflect the port's role as a major container hub in the Asia-Pacific region. Despite data quality limitations such as unspecified vessel types (59.9%) and incomplete destination fields, the results provide actionable insights for port authorities to enhance safety, optimize operations, and support strategic planning. This methodological framework demonstrates scalability and transferability to other port environments, contributing to the advancement of data-driven maritime traffic management systems]]>
Copyrights © 2026
