The objective of this paper is to establish a framework that quantifies land use changes and forecasts urban growth trends. Satellite imageries with moderate resolution (Landsat TM 5 and 7) are used to study the changes in land cover and land uses over a 15 years period (1987 to 2002). Two land use/land cover maps are produced for the two dates, then processed using a two steps Markovian Cellular Automata model. To enhance the projected land use of 2006, socioeconomic preferences and anthropogenic factors are collected and mapped using a raster/vector hybrid geographic information system. The anthropogenic factors are identified and weighted by a selected group of stakeholders. Finally, these factors are mapped and presented in raster form. The final projection of land use and urban growth is assessed both spatially and quantitatively. The spatial assessment is achieved by comparing the projection land use for 2006 against a spatial high resolution image (IKONOS MS) of the same area and date. Quantitative assessment of the model is achieved by creating an error matrix that compares the results of the projected land use to the actual land use depicted in the high resolution image. The accuracy assessment demonstrated an accuracy of 69.5%, which is considered acceptable in the modeling of land use changes using Landsat imageries.


Land Use Changes – Urban Growth - Land Use Dynamics – Markovian Chain Analysis – Cellular Automata – Geospatial Modeling – Participatory GIS.


Architecture | Arts and Humanities | Education | Engineering



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.