Different Method to find Optimum Training Data in Artificial Neural Network (ANN) for Urban Growth ModelingCase Study: Sanandaj City in IRAN

Different approaches have been attempted in spatial modeling. Artificial Neural network (ANN) models are knowledge-based models and fit within the regression type models of land use changes. ANNs are powerful tools that use a machine learning approach to quantify and model complex behavior and patterns. In this research we use artificial neural networks and our case study is Sanandaj .We use Landsat imagery, taken in 2000 - 2006.Our parameters in this study are: distance to principle roads, distance to residence region, Elevation, Slope, distance to faults, distance to facilities, distance to downtown and the number of urban pixels in an neighborhood with radius of 1 pixel. Finally we predict land us change for 2012

کلیدواژه ها:

Artificial Neural Network ، Urban Growth Modelling