Monitoring land use changes with remote sensing and CA Markov model (case study: Isfahan city)
Subject Areas : KARBARI ARAZI
mohammad ebrahim afifi
1
*
,
khalil alinejad
2
,
Marzieh Mogholi
3
1 - Member of the Faculty of Geography Department of Islamic Azad University, Larestan Branc
2 - Student of Department of Geography, Larestan Azad University
3 - faculty member Department of Geography, Larestan Branch, Islamic Azad University, Larestan, Iran
Keywords: land use changes, remote sensing, CA Markov model, Isfahan,
Abstract :
For optimal use of land, knowledge of land use changes and its type of use is essential, which becomes possible by evaluating and predicting land use changes. The aim of this study was to monitor land use changes in the last three decades with remote sensing technique and CA Markov model in Isfahan city. To achieve this goal, the necessary corrections and processing were done on Landsat 2000, 2010 and 2020 satellite images. Classification was done by support vector machine method. The results of image classification showed that residential land in 2000 was equal to 16754.4 hectares (31%), which with the changes in land use and the conversion of forest, pasture, water, etc. to residential use in 2010 to 17248.64 hectares (32 %) reached, which means its area has increased by 24.494 hectares. Also, the classification results show that the growth and development of the residential areas of Isfahan city and the conversion of barren uses and irrigated agriculture, pastures, forests into residential have always been positive, so that the forecast map of 2030 is also indicative of this and the area of man-made lands in 2030 was predicted to be 09 reach 17984 hectares (35%). Kappa coefficient in 2000, 2010 and 2020 was 83.32, 85.22, 86.71 respectively. The results show that the Kappa coefficient and overall accuracy are high in the newer images, which can be attributed to the presence of ground control samples closer in time to these years and the higher resolution of the images.