GIS Models and Modeling.ppt

GIS Models and Modeling Chapter 14 Introduction A model is a simplified representation of a phenomenon or system GIS modeling is as the use of GIS in the process of building models with spatial data. spatial data use of modeling discipline specific GIS Modeling GIS assists modeling Integration of different sources then able to link and display together. Vector or raster? Raster: continuous, remotely sensed Vector: well defined locations and shapes or network. Can be integration of vector and raster. Just GIS or linked to other packages? Three Scenarios Loose coupling transfer of files to other programs export example statistical packages Tight coupling common user interface or menu selection to call Embedded system menus to call subsystems (ESRI products) Binary models A binary model uses logical expressions to select map features from a composite map or multiple grids. Map overlay to prepare for vector query Multiple grid process for raster Siting common application with multiple criteria (example Conservation Reserve Program) Binary models Binary models can be used for change detection. Sometimes binary models are used at the beginning stage of modeling. Index Models An index model used the index value calculated from a composite map or multiple grids to produced a ranked map. Selected variables are evaluated at two levels Relative importance, assigning a weight Observed values are evaluated and given scores. ArcView Model Builder Suitability and vulnerability analysis Regression Models Regression model relates a dependent variable to a number of independent variables in an equation. Linear regression is used when the dependent variables and independent variables are all numeric. Logistic regression is used when the dependent variable is a binary phenomenon and the independent variables are categorical or numeric. Process Models A process model integrates existing knowledge about the environmental processes in the real world into a set of relationships and equat