Discovering and Linking Spatio-Temporal Big Linked Data

The growing number of spatiotemporal datasets is an essential driver for bio-economy. Interoperability is needed to ensure efficient use of these data and had been addressed by standardization institutions, such as OGC and AIMS. Both of them promote the use of Semantic Web standards (e.g., GeoSPArql) as one pillar for interoperability [1]. A significant challenge to strengthen the utility of Semantic Web approaches is linking. Its central goal in the context of spatiotemporal datasets is the (semi-automatic) discovery of geospatial referents, such as events, areas, and places which are not yet linked or georeferenced. While the linking task is intrinsically challenging, it is especially resource- and time-consuming when processing and linking Semantic Big Data. This paper will demonstrate an approach which improves and automates linking Semantic Big Data and show its potential usage for bio-economy.