This thesis includes a quality assessment investigation of Automatic Identification System (AIS) data retrieved through the ARPA project data platform from Digitraffic. Automatic Identification System (AIS) data is essential in improving the global shipping industry's safety, efficiency, environmental performance, and operations. The dataset includes location, navigational, and static data from thousands of ships from the Baltic Sea geographical region.

The research examines the literature on AIS data quality through which an assessment concept was constructed. This mixed-method approach combines qualitative and quantitative data analysis techniques to identify the elements that influence the data's quality and develop strategies for measuring it. The investigation focuses on four critical aspects of data quality: accuracy, completeness, consistency, and timeliness.

The findings show that AIS technology, communication protocols, ambient conditions, and human variables all impact the quality of marine AIS data. Therefore, to address these issues, the dissertation provides a set of quality indicators and data validation procedures. The effectiveness of the quality assessment procedures in identifying AIS data quality concerns was demonstrated.

According to the study, ongoing monitoring and improvement of AIS data quality are still required to improve marine safety and decision-making, ultimately making it ideal for autonomous shipping where the data is needed with a high degree of integrity.