Big (Geo-) Data promises to lead science into a new age in which complex scientific and social questions can be approached in a holistic way by combining multi-thematic and multi-perspective data across different media formats. This makes the integrating of massive amounts of highly heterogeneous data a core challenge for Geographic Information Science. In this talk, I argue that Big (Geo-)Data should not be approached by equally big ontologies. I propose an observation-driven ontology engineering framework to assist domain experts in becoming knowledge engineers. I present our ongoing work on semantic signatures as methodology to mine ontological primitives out of observation data and propose how geo-ontology design patterns may assist domain experts in creating small, data-driven application ontologies.
Krzysztof Janowicz is an Assistant Professor for Geographic Information Science at the Geography Department of the University of California, Santa Barbara and Faculty Research Affiliate of the Center for Information Technology and Society as well as the Cognitive Science Program. Before, he was an Assistant Professor in the GeoVISTA Center, Department of Geography at the Pennsylvania State University. He is the community leader of the 52° North semantics community and one of the two Editors-in-Chief of the Semantic Web journal. Before moving to the US, he was working as postdoctoral researcher at the Institute for Geoinformatics (ifgi), University of Münster in Germany. His work is available online at: http://geog.ucsb.edu/~jano/
March 2, 2012
Click here for video presentation
Co-sponsored by the Information Sciences and Spatial Sciences Institute