Modelling land use change by an integrated Cellular Automata and Markov Chain Model (case study; Azadshahr County)

In this research, land-use changes in Azadshahr County were investigated from ۱۹۹۸ to ۲۰۰۹, using the imageries from Landsat ۵ satellite and an integration of the Markov chain and Cellular Automata methods. Using the object-based support-vector-machine image classification method, land-use maps were classified into three major categories, namely agriculture fields, forest lands and built-up areas for the years of ۱۹۸۷, ۱۹۹۸ and ۲۰۰۹; their overall accuracies have been obtained ۹۱.۰%(۱۹۸۷), ۹۱.۰% (۱۹۹۸) and ۸۸.۸% (۲۰۰۹), with the respective Kappa values of ۸۶.۵%(۱۹۸۷), ۸۶.۵% (۱۹۹۸) and ۸۳.۲%(۲۰۰۹). The built-up areas had the greatest changes by increasing ۲.۰۲% and ۲.۱۷% for the periods of ۱۹۸۷-۱۹۹۸ (as first period) and ۱۹۹۸-۲۰۰۹ (as second period), respectively. During the first period, forest area has shrunk by approximately -۱.۸۰%. However, as a result of the afforestation project during ۱۹۹۸-۲۰۰۹, forest area has increased ۱.۵۹%, while over the ۲۲-year period the total area of forest has merely reduced by -۰.۲۱%. Agricultural areas on the one hand has shrunk in favor of the built-up areas, and on the other hand, increased by the conversion of the forest lands, making a total reduction of -۰.۲۲ and -۳.۷۵% for the first and second periods, respectively. The land-use pattern of ۲۰۲۰ was simulated using the MULOSCE extension of the QGIS software based on the integrated cellular automata and Markov chain technique. It is expected for this period to encounter a ۰.۶۲% increase in built-up areas, with ۰.۴۸% and ۰.۱۵% reduction in agriculture fields and forest lands, respectively.

Keywords:

Landsat , Object-Oriented Classification , Support-Vector Machine , Markov chain , Azadshahr