Ship Behavior Pattern Analysis Based on Multiship Encounter Detection

Abstract

Maritime accidents have become a major threat to societal safety and environmental protection, especially in complex navigable waters with high traffic density and diverse ship behaviors. To achieve effective safety control and efficient traffic management, a comprehensive understanding of ship behavior is essential. This study proposed a framework for ship behavior pattern analysis based on multiship encounter detection. The overall methodology incorporates research steps of data preprocessing, multiship encounter detection, and ship behavior pattern analysis. Using automatic identification system (AIS) data, the multiship encounter situations were identified and extracted. Based on the extracted encounter scenarios, the ship behavior patterns were analyzed using characteristic parameter statistics, spatial-temporal distribution mining, and spatial correlation analysis models. A case study is conducted using the historical AIS data in Ningbo-Zhoushan Port. The experiment results show that ship behavior patterns differ among the extracted encounter categories, and significant hotspots in spatial-temporal distribution can be observed. The findings on ship behaviors and traffic characteristics in complex navigable waters provide theoretical references for maritime traffic management authorities to mitigate risks and improve maritime safety.