AISHIP: an ontology for extended vessel representation and multimodal data integration

The maritime sector generates vast amounts of heterogeneous data due to dense global vessel traffic. This data offers significant potential for improving operational efficiency and ensuring safety at sea. However, its effective use is hindered by a lack of semantic alignment between diverse information sources. To address this challenge, we present AISHIP, an ontology designed to unify and semantically enrich maritime data. AISHIP extends the existing VesselAI ontology by incorporating enhanced vessel characteristics, additional trajectory information, multimodal vessel representations, and a detailed conceptualization of propulsion systems. The primary objective of AISHIP is to serve as a semantic interface that facilitates the integration of heterogeneous maritime datasets, enabling consistent annotation, querying, and reasoning across systems. By providing a shared semantic foundation, AISHIP supports a range of maritime applications, including vessel behavior analysis, fleet management, and search and rescue operations. These tasks benefit from harmonized data representations, which improve analytical precision and operational decision-making. We discuss relevant use cases to illustrate the ontology’s practical value and evaluate its design to demonstrate its quality. AISHIP represents an extensible and reusable resource, aligning with FAIR principles, and offers strong potential for adoption in future maritime analytics and digital twin frameworks.