Geographical Information System (GIS) to Knowledge

Geographical Information System (GIS) to Knowledge April 2003 Peter Bajcsy, Ph.D. Research Scientist Adjunct Assistant Professor, CS Department, UIUC Automated Learning Group National Center for Supercomputing Applications University of Illinois pbajcsy@ncsa.uiuc.edu Outline • • • • • • • Problem Statement Top Level Overview Input Information Extraction and Representation Georeferencing and Raster Information Extraction Feature Driven Boundary Aggregation and Evaluation Error Evaluation of New Boundary Aggregations and Decision Making Summary alg | Automated Learning Group Acknowledgement • Project Team Members: Peter Bajcsy, Peter Groves, Sunayana Saha, Tyler Alumbaugh • Support: Michael Welge, Loretta Auvil, Dora Cai, Tom Redman, David Clutter, Duane Searsmith, Lisa Gatzke, Andrew Shirk, Ruth Aydt, Greg Pape, David Tcheng, Chris Navaro, Marquita Miller. alg | Automated Learning Group Problem Statement • Problem Statement: search for the best partition of any geographical area that is • • • • (a) based on raster or point information, (b) formed by aggregations of known boundaries, (c) constrained or unconstrained by spatial locations of know boundaries and (d) minimizing an error metric. Grid-based information, e.g., from satellite or air-borne sensors Geographical point information, e.g., from GPS or address data base Man-made, e.g., Counties, US Census Bureau Territories Defined by environmental characteristics, e.g., Eco-regions, Historical isocontours Defined by applications • • Raster or Point Information: • • • • Boundaries (Vector Data): • Spatial Constraints and Error Metric: • alg | Automated Learning Group Top Level Overview References: ALG Technical Reports: TR-20030226-1.doc, TR-20030211-1.doc, TR-20021011-1.doc Conferences: Peter Bajcsy and Tyler Jeffrey Alumbaugh, ―Georeferencing Maps With Contours,‖ Proceedings of the 7th World Multiconference on Systemics, Cybernetics and Informatics (SCI 2003), Orlando, Florida, July 27-30, 2003. •Peter Bajcsy, ―Automatic Extraction Of Isocontours From Historical Maps,‖ Proceedings of the 7th World Multiconference on Systemics, Cybernetics and Informatics (SCI 2003), Orlando, Florida, July 27-30, 2003. alg | Automated Learning Group Input Information Extraction and Representation alg | Automated Learning Group Input Information Extraction and Representation alg | Automated Learning Group Data Types and Representation: Examples • Raster Information: GeoImage Object • Boundary Information: Shape Object • • Tabular Information: Table Object Neighborhood Information: NBH Object alg | Automated Learning Group Raster Data: File Formats • • USGS Digital Elevation Data (DEM) Files • • • Header file with georeferencing information Floating point values, 30 m spatial resolution, IL coverage, published in 2002 Georeferencing information from: – One or more standardized files are distributed along with TIFF image data as .tfw and/or .txt files. – The metadata is encoded in the image file using private TIFF tags. – An extension of the TIFF format called GeoTIFF is used. Forest labels, 1km spatial resolution, – Forest Cover Types: 29 labels, USA coverage, published in 2000 – Forest Fragmentation Index Map of North America, 8 labels, USA coverage, published in 1993 Land use labels, 1km spatial resolution, world wide coverage, published in 2001 TIFF Files • • alg | Automated Learning Group Vector Data: File Formats • Computational Tradeoffs Between Vector Information Retrieval and Data Storage — US Census Bureau TIGER Files – Elaboration of the chain file structure (CFS) – Used record files 1, 2, I, S, P — Environmental Systems Research Institute (ESRI) Shapefiles – Location list data structure (LLS) – shp, shx, dbf files • TIGER to ESRI Shapefiles alg | Automated Learning Group Point Data: File Formats • FBI Crime Reports United States Crimes Database, years 94-98, USA states, reports per county, published in 2001 • United States Crimes Database, years 98-00, IL state, reports per county, published in 2002 • • Entries • Theme_Keyword: crime, arrests, murder, forcible rape, rape, robbery, aggravated assault, assault, burglary, larceny, motor vehicle theft, theft, arson Multiple Files Varying notation Association with geographical boundary information • Challenges • • • alg | Automated Learning Group Data Size Data size driven operations : • Sub-setting • Sub-sampling • Cropping • Zooming alg | Automated Learning Group Formation of Vector Data • Iso-contour extraction from historical maps • Segmentation and clustering of raster data into homogeneous regions alg | Automated Learning Group alg | Automated Learning Group Georeferencing Data Sets and Raster Information Extraction alg | Automated Learning Group Georeferencing Data Sets and Raster Information Extraction alg | Automated Learning Group alg | Automated Learning Group Georeferencing Based on Data Types • Raster and Raster • Vector and Vector • Raster and Vector alg | Automated Learning Group Georeferencing Based on Coordinate Systems alg | Automated Learning Group Raster Information Extraction: Categorical Variable Frequency of Occurrence alg | Automated Learning Group Raster Information Extraction: Continuous Variable Elevation Statistics Per County Sample Mean alg | Automated Learning Group Standard Deviation Skew Kurtosis Feature Driven Boundary Aggregation and Evaluation alg | Automated Learning Group Feature Driven Boundary Aggregation and Evaluation alg | Automated Learning Group alg | Automated Learning Group Spatially Unconstrained Boundary Aggregation • Hierarchical clustering of crime data with the exit criterion being the number of clusters and the clustered feature being “auto theft in 2000” leads to six aggregations. Boundaries Geographical Display Boundary Aggregations Tabular Display alg | Automated Learning Group Spatially Constrained Boundary Aggregation • Hierarchical segmentation and hierarchical clustering of oak hickory feature with the exit criterion of 18 numbers of county aggregations Boundaries With Spatial Constraint Without Spatial Constraint Boundary Aggregations alg | Automated Learning Group Boundary Aggregation With Hierarchical Output • Hierarchical segmentation of extracted forest statistics (oak hickory occurrence) with two output partitions. Boundaries 43 aggregations 21 aggregations Boundary Aggregations alg | Automated Learning Group Error Evaluations of New Territorial Partitions • Error evaluation of partitions obtained by clustering and segmentation of mean elevation feature per Illinois county with Variance error metric alg | Automated Learning Group Geographical Error Evaluations and Decision Making • Geographical error evaluation of partitions obtained by clustering and segmentation of mean elevation feature per Illinois county with Variance error metric Partition Index Eval#0 Eval#1 Eval#2 Eval#3 alg | Automated Learning Group Decision Making • Which global partition minimizes a chosen error metric? • Which partition minimizes a chosen error metric at a selected fundamental area definition? • What is the geographical error distribution given a territorial partition? alg | Automated Learning Group Documentation alg | Automated Learning Group Summary • Applications of GIS tools — — — — — — — Remote Sensing Agriculture Hydrology Water Quality Survey Atmospheric Science Military Socio-Economics • Interested ? Useful ? Let us know. alg | Automated Learning Group