Datasets for testing the Ensemble Outlier Detection Tool

The four datasets are used to test the workflow The JDS dataset is an extract from the Joint Danube Survey Data (https://www.danubesurvey.org/jds4/index.html). This includes species occurrences collected within the Danube River Basin. The EFI+ dataset: This was collated from the European River Catchment to aid in determining the species distribution in relation to changes in anthropogenic pressures from different river catchments. The biodiv data was retrieved from different open access datasets, including the Global Biodiversity Information Platform, iNaturalist, and VertNET. Danube GeoJSON provides the bounding box for the Danube River Basin that limits the extent of data downloaded from the online sources but also filters out the local data that is not within the area of interest.