Keynote abstract: Extracting and fusing information from large and heterogeneous datasets

The rapidly increasing amount and variety of data coming from satellites and other sources is raising new issues such as the management and exploitation of extremely large and complex datasets (Big Data); the main challenge in the Space and Security domain is to improve the capacity to extract in a timely manner operational (i.e. useful and clear) information from a huge amount of heterogeneous data. The talk will describe the work performed in the context of the Big Data Europe project (http://www.big-data-europe.eu/), where in one of its pilots, we investigate the fusion of information extracted from satellite images and user-generated content on social media. In our pilot, we deploy change detection from satellite images and event detection in social media text on the Big Data Europe distributed processing infrastructure and relate changes in land cover with events extracted from geo-located social media and news text. From the software engineering point of view, this pilot allows us to experiment with the integration of diverse analysis tools into modern big data infrastructures; from the security domain's point of view, it allows us to demonstrate how heterogeneous data fused via geo-temporal indexing. The talk will also present the Big Data Europe modular platform that integrates systems from Apache and European projects into a Big Data swiss army knife. Development within Big Data Europe aims to provide a layer for semantically describing and discovering what data and processing is available at a deployment, to maintain data provenance and lineage including rights and obligations regarding derivative data, and to provide a data integration layer.