AIS Data Analytics for Intelligent Maritime Surveillance Systems

Abstract

The huge volumes of spatial-temporal maritime traffic data that is currently being accumulated from the Automatic Identification System (AIS) can open the path for smart decision-making and facilitate a number of intelligent applications including ship movements tracking, route patterns extraction, operations and next event prediction, trade and cargo flow, etc. However, it is very challenging to store, transfer, and load such large volumes of spatial-temporal data. Pre-analysis is essential before extracting spatial and temporal relationships in maritime traffic data, in which data variability, inconsistent data quality, and computational complexity demanded by various applications can pose additional constraints. In this chapter, we first briefly review maritime traffic surveillance systems for spatial-temporal data collection. Then we present a computational framework to efficiently compress, transfer, and acquire necessary information for the further analysis of large-scale AIS data to empower relevant applications in the maritime sector. The framework is composed of two parts: the first is a lossless compression algorithm that compresses the AIS data into binary form for efficient storage, speedy access, and easy transfer across networks and systems within the organization; the second is an aggregation algorithm which derives movement and activity information of vessels grouped by grid and/or time window from the compressed binary files. The aggregation algorithm compresses and organizes data by vessel identity (ID), thereby improving accessibility and reducing storage demand. Finally, a use case of maritime big data intelligent surveillance is briefly described.