Transcript Spatial Database, Data Mining, GIS

(Geo) Informatics across Disciplines!
Why Geo-Spatial Computing?
• Societal:
• Google Earth, Google Maps, Navigation, location-based service
• Global Challenges facing humanity – many are geo-spatial!
• Future of Computer Science (CS) is to address societal challenges!
• Intellectual
• Challenges CS assumptions, opporunities for new research
• Ex. Shortest path problem – What algorithms are common today?
• Are these correct if edge travel-times is not fixed (e.g. rush-hour, non-rush-hour)?
• Is Dynamic Programming correct for spatio-temporal problems?
• Ex. Classical Data Mining, e.g. Decision trees, Association Rules, Regression, …
• Are these effective for spatial data?
• ACM SIGSPATIAL
• Special interest group started in 2008 to bring computer scientists together
• Annual Conference: ACM GIS
• Journals
• GeoInformatica: An Intl. Jr. on Advances in Computer Science for GIS
Shashi Shekhar
Mcknight Distinguished University Professor
URLs: www.cs.umn.edu/ ~shekhar
Area:
Spatial Databases, Spatial Data Mining, Geographic Info. Systems
Teaching:
• Fall 2009:
• Csci 4707: Database I
• iPhone programming (w/ Prof. Tripathi and Prof. Mokbel)
• Spring 2010:
• Csci 5708: Database Systems
• Csci 8715: Spatial Databases
Books, Surveys, etc.:
• Updating a survey paper on spatial and spatio-temporal data mining
• Textbook, Encyclopedia, …
Research Group: Spatial Database, Data Mining, GIS
URLs: www.spatial.cs.umn.edu
Weekly Meetings: www.spatial.cs.umn.edu/schedule.html
Current Projects:
• NSF: CRI:IAD Infrastructure for Research in Spatio-Temporal and Context-Aware Systems …
• NSF: III-CXT: Spatio-temporal Graph Databases for Transportation Science
• NSF: IGERT: Non-equilibrium Dynamics Across Space and Time
• USDOD: Spatio-Temporal Pattern Mining for Multi-Juris. Multi-Temporal Activity Datasets
• USDOD: Dynamic Purpose-Aware Graph Models for Composite Networks
• USDOD: Cascase Models for Multi-Scale Spatio-temporal Pattern Discovery
• UM: OVPR: Minnesota Futures: Exploring Spatio-temporal Future of Geo-Informatics
Current Ph.D. Students:
• James Kang
• Pradeep Mohan
• Mike Evans
• Dev Oliver
• Xun Zhou
Spatial Databases: Representative Projects
Evacutation Route Planning
Parallelize
Range Queries
only in old plan
Only in new plan
In both plans
Shortest Paths
Storing graphs in disk blocks
Spatial Data Mining : Representative Projects
Location prediction: nesting sites
Nest locations
Spatial outliers: sensor (#9) on I-35
Distance to open water
Vegetation durability
Co-location Patterns
Water depth
Tele connections
Spatio-Temporal (ST) Questions
• How do we conceptualize spatio-temporal (ST) worlds?
• How do we measure ST concepts, recognize them in (remotely) sensed information or in
the field, and identify their accuracy and quality?
• How do we represent ST concepts with incomplete/ uncertain information, with
alternative data models, and possibly with multiple representations for the same data, in
digital environments?
• How do we store, access, and transform ST concepts, facilitating data sharing, data
transfer, and data archiving, while ensuring minimum information loss?
• How do we explain ST phenomena through the application of appropriate methods of
forward or inverse models of physical and human processes?
• How do we visualize ST concepts on a variety of media such as maps on electronic
displays or animated displays ?
• How do we use ST concepts to think about spatio-temporal phenomena, and to seek
explanations for spatio-temporal patterns and phenomena?
• Source: Adaptation from NCGIA proposal to NSF by Goodchild et al.