We are soliciting presentations on both theoretical and applied aspects of geospatial and spatiotemporal ontologies for the special sessions at the 2020 American Association of Geographers Annual Meeting. Next year the series in its 15th year will be a part of the 3rd GeoAI and Deep Learning Symposium. We welcome presentations on the following topics including, but not limited to:
* Spatial and spatiotemporal knowledge modeling, analysis, formalization, and validation (thesauri, vocabularies, and ontologies)
Emerging technologies and methods (GeoAI, deep learning, natural language processing) to support spatiotemporal reasoning, ontology matching, and alignment
* Information retrieval with knowledge graphs and deep learning models
* Management of geospatial semantic web data and linked data (e.g., GeoNames, LinkedGeoData)
* Data fusion and semantic interoperability across knowledge domains, cultures, ethnicities, languages, and time, spatiotemporal models
* Semantic annotation methods, provenance, and standards for spatial knowledge representation and processing (e.g.OWL, RDF, RDFS, JSON-LD, GeoJSON)
To present a paper or to participate in the session as a discussant, submit your abstract through AAG website and email your Participant Identification Number (PIN) to Alex Sorokine (SorokinA@ornl.gov). Please follow standard AAG abstract submission procedure and guidelines. If you have any questions please forward them to one of the organizers.
Capturing and representing geospatial and spatiotemporal dimensions of geographic knowledge is a great challenge from both theoretical and applied perspectives. Nowadays formalized geospatial knowledge representations and reasoning in the form of ontologies and knowledge graphs powers search engines, discovery of geodata, and understanding of the crowdsourced information. New technologies like deep learning and advanced natural language processing open new possibilities for practical applications and research in this area.
|Presenter||Kejin Cui*, George Mason University, A Vocabulary Recommendation Method for Spatiotemporal Data Discovery Based on Bayesian Network and Ontologies||15|
|Presenter||Chen-Chieh Feng*, Geography, National University of Singapore, Relation extraction from text||15|
|Presenter||Alexandre Sorokine*, Oak Ridge National Laboratory, Jason Kaufman, Oak Ridge National Laboratory, Robert Stewart, Oak Ridge National Laboratory, Jessie Piburn, Oak Ridge National Laboratory, Geographic data matching and conflation: challenges and an active learning solution||15|
|Presenter||Dalia Varanka*, United States Geological Survey, Geospatial Semantic Relation Properties for Social Space Data Graphs||15|
To access contact information login