University of Tehran Journal of Range and Watershed Managment 5044-2008 75 4 2022 12 22 Development of an integrated model based on Cellular automata and Markov chain to predict land use/cover changes, Case Study: Karaj City Development of an integrated model based on Cellular automata and Markov chain to predict land use/cover changes, Case Study: Karaj City 519 537 90845 10.22059/jrwm.2023.351534.1687 FA Haniyeh Rezaie Master student of Land Assessment and Spatial Planning, Department of Environment, Faculty of Natural Resources, University of Tehran, Karaj, Iran. Sharareh Pourebrahim Associate Professor, Department of Environment, Faculty of Natural Resources, University of Tehran, Karaj, Iran. Mohammad Karimadini Assistant Professor, Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, Arak University of Technology, Arak, Iran. Journal Article 2022 10 24 Due to the ability of land use/cover changes monitoring and predicting to understand the performance and health of ecosystems, this purposed method can provide possibility of sustainable land use management and planning, especially in the rapid change areas without master/land use plan. The present study has aimed to introduce Google Earth Engine to evaluate the pattern of land changes during 2006- 2021 and predict the pattern of future changes by using an integrated model based on Cellular automata and Markov chain using Google Earth Engine system. Three Landsat images (2006, 2014 and 2021) were classified using the support vector machine classifier method, and were simulated using the integrated model of cellular automata and Markov chain. In order to evaluate the accuracy of the predicted map of 2021, the classified map of the same year was applied. The accuracy of classified and simulated maps was Kno=0.812, Klocation=0.816, Kstandard=0.786 respectively. Evaluation of the land use/cover changes shows that between 2006 and 2035, the buildup areas will reach from 4839.01 hectares to 7199.76 hectares with increasing of 2360.75 hectares. These results indicate the necessity of land use planning principles. Simulation models can reduce the risks of long-term decision-making in land use management and Google Earth Engine can reduce the time and cost for classification and satellite image processing. Due to the ability of land use/cover changes monitoring and predicting to understand the performance and health of ecosystems, this purposed method can provide possibility of sustainable land use management and planning, especially in the rapid change areas without master/land use plan. The present study has aimed to introduce Google Earth Engine to evaluate the pattern of land changes during 2006- 2021 and predict the pattern of future changes by using an integrated model based on Cellular automata and Markov chain using Google Earth Engine system. Three Landsat images (2006, 2014 and 2021) were classified using the support vector machine classifier method, and were simulated using the integrated model of cellular automata and Markov chain. In order to evaluate the accuracy of the predicted map of 2021, the classified map of the same year was applied. The accuracy of classified and simulated maps was Kno=0.812, Klocation=0.816, Kstandard=0.786 respectively. Evaluation of the land use/cover changes shows that between 2006 and 2035, the buildup areas will reach from 4839.01 hectares to 7199.76 hectares with increasing of 2360.75 hectares. These results indicate the necessity of land use planning principles. Simulation models can reduce the risks of long-term decision-making in land use management and Google Earth Engine can reduce the time and cost for classification and satellite image processing. https://jrwm.ut.ac.ir/article_90845_acd063652f2d7f04948bc5c4c7b67a34.pdf