The second task (WP5.2) of the maritime use case work package aims to deliver a denition of the datasets to be used in the research and for the evaluation and validation purposes. Specifically, it describes multiple, heterogeneous datasets that may be used for maritime scenarios and use case validation.

This datAcron deliverable entitled Maritime Data Preparation and Curation is an interim report for the task WP5.2 dedicated to the identication of available sources. The objective of this report is to list and describe available data sources relevant to the maritime scenario and project objectives, as well as to provide the initial details about their nature and accessibility. It briefly introduces how they support the dierent scenarios, while the choice of their effective use is left to the datAcron partners.

After an introduction, the report summarises the maritime use case as described in Deliverable D5.1. Section 3 briefly describes data challenges regarding velocity, volume, veracity and variety aspects. Section 4 is dedicated to the description of identified datasets for the maritime use case. This section first describes AIS data sources, with a specic focus on data provided by the datAcron partners. In a second part, contextual data sources are described. Three main contextual data types have been identied in support to the maritime use case: data supporting navigation, data defining official registers and data about weather and ocean conditions. The section 4 then specifies the relationship between data and scenarios denfied in Deliverable D5.1. Finally the denfition of synthetic and pseudo-synthetic datasets in introduced.