Temporal-Spatial Simulation of Landscape Variations Using Combined Model of Markov Chain and Automated Cell

Abstract

Classification and preparation of land use map are the most commonly used methods in remote sensing data. Numerous advanced classification methods have been developed in a recent year. Among those methods, one can name support vector machine. Identifying land cover changes can play an important role in future decisions of regional managers. Therefore, the present study aimed at employing CA–Markov model to present a powerful but simple model for simulation and prediction of Yazd city. Accordingly, first, satellite images of 2000, 2005, 2010, and 2016 were classified by SVM method, and then land use maps of Yazd city were extracted. The results of the detection of changes indicated the expansion of residential areas and the reduction of dry land and vegetation during a 16-year period. Prediction of land use development in 2040 using CA–Markov model with a kappa coefficient of 84.43 shows the high accuracy of this model. Besides, the urban land use area shows 18,432 hectares increase in 2040 compared to 2010, while the area of dry land uses (− 15,570) rocky areas (− 186) and vegetation (− 2658) hectares decrease compared to 2010. Moreover, the results of CA–Markov model indicated the development of Yazd city by degradation of vegetation.

Bibliographic Information