The 2nd edition of the Big Data from Space conference (co-organised by the European Space Agency, the EC Joint Research Centre and the EU Satellite Centre) was held at the Auditorio de Tenerife from the 15th to the 17th of March 2016 with the goal to bring together researchers, engineers, developers and users in the area of Big Data from Space addressing the whole life-cycle of Big Data (from university education to on board processing, down to image and data analysis, until downstream exploitation). The conference was a huge success with nearly 300 participants coming from almost 40 countries and more than 90 papers selected for oral or poster presentations.
Big Data from Space refers to Earth and Space observation data collected by space-borne and ground-based sensors. Whether for Earth or Space observation, they qualify being called ’big data’ given the sheer volume of sensed data (archived data reaching the exabyte scale), their high velocity (new data is acquired almost on a continuous basis and with an increasing rate), their variety (data is delivered by sensors acting over various frequencies of the electromagnetic spectrum in passive and active modes), their veracity (sensed data is associated with uncertainty and accuracy measurements) and value (the capacity to extract information and meaning from them). Regarding the volume of the data, the first three Sentinel satellites (operated by ESA in the framework of the Copernicus programme, funded and managed by the European Commission) acquired in 2015 around 3 TB per day, which will become more than 6 TB per day by the end of 2016 (other three Sentinel satellites will be launched in the upcoming months); in addition, there are several other commercial and national satellites which are constantly increasing the volume of data.
BigDataEurope was represented at the BiDS’16 conference with the presentation of Sergio Albani (SatCen) entitled “A pilot for Big Data exploitation in the Space and Security domain”. The presentation initially illustrated the activities related to Big Data at SatCen (under the Research, Technology Development and Innovation area). Then the BigDataEurope project was introduced with focus on the pilot of the Societal Challenge “Secure Societies” led by SatCen (domain leader), UoA (technical leader) and “NCSR” Demokritos.
The pilot for Secure Societies is validating the BigDataEurope platform dealing with the integration and fusion of data coming from remote and social sensing in order to add value to the current data exploitation practices; this is key in the Space and Security domain, where useful information can be derived not only from satellite data but also from data coming from social media and other sources. Thus the BigDataEurope pilot for Secure Societies has been developed in the Space and Security domain following the so-called Big Data Vs, i.e. Volume (large satellite images), Variety (heterogeneous data such as satellite images and textual content), Velocity (fast-paced social data and news stream), Veracity (cross-verification of the sources) and Value (adding useful information).
The pilot is based on two workflows, currently under development by SatCen, UoA and Demokritos. The first workflow, called the change detection workflow, ingests satellite images to detect areas with changes on land cover or land use by using change detection techniques; the identified Areas of Interest are then associated with social media and news items and presented to the end-user for cross-validation. The reverse procedure is applied to the second workflow, called the event detection workflow. Event detection is triggered by news and social media information, where trending topics (i.e. document clusters) with geospatial connotation constitute a time- and space- localized event; provided such event, the corresponding satellite images are acquired and processed in order to check for changes in land cover or land use.
While the pilot architecture has been already defined, the next steps of the deployment will be focused on the parallelization of the data management chain (pre-processing and change detection), the ingestion of other remote sensing data (e.g. Sentinel 2), the scalability of the News Crawler tool and the improvement of the user interface with keywords functionality.
For more details see:
S. Albani, M. Lazzarini, M. Koubarakis, E. K. Taniskidou, G. Papadakis, V. Karkaletsis, G. Giannakopoulos, “A pilot for Big Data exploitation in the Space and Security domain”, proceedings of 2nd Big Data from Space Conference, 15-17 March, Santa Cruz de Tenerife (2016).