Presentation on theme: "A CyberGIS Environment for Near-Real-Time Spatial Analysis of Social Media Data Shaowen Wang CyberInfrastructure and Geospatial Information Laboratory."— Presentation transcript:
1 A CyberGIS Environment for Near-Real-Time Spatial Analysis of Social Media Data Shaowen WangCyberInfrastructure and Geospatial Information Laboratory (CIGI)Department of Geography and Geographic Information ScienceDepartment of Computer ScienceDepartment of Urban and Regional PlanningNational Center for Supercomputing Applications (NCSA)University of Illinois at Urbana-ChampaignNSF-CDI Specialist MeetingKnowledge Discovery in Cyberspace and Big DataSan Diego, CAAugust 7, 2013
2 Cyberinfrastructure – A Simplified View Data / InformationPeopleIntegrationCollaborationComputingCommunication
7 Hypothesis: Is such detection feasible based on social media data? CyberGIS FluMapperPurpose: Early and fine- spatiotemporal-scale detection of flu outbreakHypothesis: Is such detection feasible based on social media data?
9 Questions – Scientific Problem Solving How to detect, represent, and communicate spatiotemporal patterns of flu risk?How to reveal spatial diffusion trajectories across various spatiotemporal scales?
10 Wang, S. , Cao, G. , Zhang, Z. , Zhao, Y. , and Padmanabhan, A. 2012 Wang, S., Cao, G., Zhang, Z., Zhao, Y., and Padmanabhan, A “A CyberGIS Environment for Analysis of Location-Based Social Media Data.” In: Location-Based Computing and Services, 2nd Edition, ed. A. K. Hassan and H. Amin, CRC Press, pages:
11 FluMapper Components Data collection and processing Collects, processes and stores streaming data from Twitter in near real timeScalable services to query raw and derived dataSpatiotemporal data modelProvides aggregated data and statistics at multiple scales for efficient information retrievalAt the finest scale, the conterminous United States is represented as a field of 30-arc second resolutionExploratory data analysisKernel density estimation (KDE)Monte-Carlo simulationsFlow mappingSingle-source flow mapping is applied to depict movement patterns
12 Spatiotemporal Data Cube (May 23 ~ June 5, 2013)
14 Questions – CyberGISHow to model and analyze big data that are not collected for the purpose of intended spatiotemporal analysis?How to integrate hybrid spatiotemporal analyses?How to replicate and validate such analyses?What are the key CyberGIS characteristics?What are the basic building blocks of CyberGIS?
15 NSF CyberGIS Project $4.43 million, Year: 2010-1015 Principal InvestigatorShaowen WangProject StaffASU: Wenwen Li and Rob PahleORNL: Ranga Raju VatsavaiSDSC: Choonhan YounUIUC: Yan Liu and Anand PadmanabhanGraduate and undergraduate studentsCo-Principal InvestigatorsLuc AnselinBudhendra BhaduriTimothy NyergesNancy Wilkins-DiehrSenior PersonnelMichael GoodchildSergio ReyXuan ShiMarc SnirE. Lynn UseryIndustrial Partner: EsriSteve Kopp
16 Overarching GoalEstablish CyberGIS as a fundamentally new software framework comprising a seamless integration of advanced cyberinfrastructure, GIS, and spatial analysis and modeling capabilities and, thus, leads to widespread scientific breakthroughs and broad societal impacts
17 Long Tail – CyberGIS for Whom? CyberGIS GatewayCyberGIS ToolkitGISolve
20 Wang, S. , Anselin, L. , Bhaduri, B. , Crosby, C. , Goodchild, M. F Wang, S., Anselin, L., Bhaduri, B., Crosby, C., Goodchild, M. F., Liu, Y., and Nyerges, T. L. “CyberGIS Software: A Synthetic Review and Integration Roadmap.” International Journal of Geographical Information Science, DOI: /
21 CyberGIS Gateway – Broad Approach – Lowering Entry Door to CyberGIS Analytics
22 CyberGIS Toolkit – Deep Approach Integrated with advanced cyberinfrastructurePlug and playGeo/spatial as an integration axisOpenAccessCommunitySourceService
23 Science Drivers and Applications Climate scienceEmergency managementGeographic information scienceGeography and spatial sciencesHydrologyHumanitiesPolitical sciencePublic healthSustainability science
25 Education and Workforce Curriculum and pedagogyOpen ecosystemsCyberGIS GatewayCyberGIS ToolkitPartnerships
26 Data-Intensive Sciences and Applications VisionData-Intensive Sciences and ApplicationsComputationalThinkingSpatialThinkingCyberGIS GatewayCyberGIS ToolkitSpace-Time Integration & SynthesisGISolve MiddlewareCyberinfrastructure
27 A collaborative software framework encompassing many research fieldsGeoSpatialEmpowering numerous applications and sciencesSeamless integration of advanced cyberinfrastructure, GIS, and spatial analysis and modelingCapable of handling huge volumes of data, complex analysis and visualization required for many challenging applicationsEmpower high-performance and collaborative geospatial problem solvingGain fundamental understanding of scalable and sustainable CyberGIS ecosystems27
28 Acknowledgments Federal Agencies Industry Department of Energy’s Office of ScienceNational Science FoundationBCSEAROCIPHYPHYTeraGrid/XSEDE SES070004IndustryEnvironmental Systems Research Institute (Esri)Silicon Graphics, Inc. (SGI)28