Urban Sprawl Simulation Mapping of Urmia (Iran) by Comparison of Cellular Automata–Markov Chain and Artificial Neural Network (ANN) Modeling Approach

Considering urbanization can lead to irreversible land transformations, it is crucial provide city managers, environmental resources and even people with accurate predicting use/land cover (LULC) accomplish sustainable development goals. Although many methods have been used predict (LULC), few studies compared them. Therefore, by analyzing the results of various prediction models and, consequently, recognizing most reliable ones, we assist researchers.. In this regard, research compares Cellular Automata–Markov Chain Artificial Neural Network (ANN) as frequently overcome gap help those concerned about urban sprawl accuracy. first step, Landsat satellite images acquired in 2000, 2010, 2020 were classified Maximum Likelihood Classification (MLC), LULC maps prepared for each year. second investigate prediction, validation CA–Markov ANN was performed. way, simulation map based on 2000 2010; next, predicted actual using correctness, completeness, quality indices. Finally, 2030 generated both algorithms, corresponding change extracted, showing a reduction soil vegetation areas (respectively, 39% 12%) an expansion (58%) built-up regions. Moreover, test showed that two algorithms closer other; however, had highest completeness (96.21%) (93.8%), while correctness (96.47%). This study algorithm more future larger higher allocations (urban cover) small fewer (soil rock).