AN INTEGRATED APPROACH FOR SIMULATION AND PREDICTION OF LAND USE AND LAND COVER CHANGES AND URBAN GROWTH (CASE STUDY: SANANDAJ CITY IN IRAN)

Abstract

One of the growing areas in the west of Iran is Sanandaj city, the center of Kordestan province, which requires the investigation of the city's growth and the estimation of land degradation. Today, the combination of remote sensing data and spatial models is a useful tool for monitoring and modeling land use and land cover (LULC) changes. In this study, LULC changes and the impact of Sanandaj city growth on land degradation in geographical directions during the period 1989 to 2019 were investigated. Also, the accuracy of three models, artificial neural network-cellular automata (ANN-CA), logistic regression-cellular automata (LR-CA), and the weight of evidence-cellular automata (WOE-CA) for modeling LULC changes was evaluated, and the results of these models were compared with the CA-Markov model. According to the results of the study, ANN-CA, LR-CA, and WOE-CA models, with an accuracy of more than 80%, are efficient and effective for modeling LULC changes and growth of urban areas.

Keywords

• land use and land cover change
• artificial neural network
• logistic regression
• cellular automata
• Sanandaj