[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Current Issue :: Archive :: Search :: Submit :: Contact ::
:: Volume 7, Issue 4 (6-2018) ::
JGST 2018, 7(4): 119-131 Back to browse issues page
Urban Growth Modeling and Prediction using Logistic Regression and Markov Chain in Sari
H. Darabi *, A. Pirnia, B. Choubin, S. Rozbeh
Abstract:   (1845 Views)
Land use changes is an ecological processes in global and local status and it will be major problem in the twenty one century and even scientists believe more impact of land use changes than climate change. One of the methods used in planning to control land use changes, is its modelling. This research aims to predict land use changes carried out and with emphasis on physical development in Sari city using logistic regression and Markov chain. To analyze land use changes in the central area of the Sari city, TM sensor (Landsat 5) for 1987, 2001 and 2011 were used. For this purpose, the images taken from the USGS web, the necessary pre-processing (including radiometric and atmospheric correction) was performed in ENVI 5.1 software. Then, using supervised classification method and maximum likelihood algorithm land use maps were extracted in the study area. At this stage to predict of Land use, maps prepared imported to IDRISI software. Transition potential modeling was conducted using logistic regression in thee IDRISI software. The 6 variables were used (including two variable as a dynamic and four variables as a static variable) and 3 sub-models calibrated over time (1987- 2001, 2001- 2011 and 1987-2011). In order to prediction of land use in 2011 year, the calibration period of 1987-2011 using Markov chain model. And hard prediction was used. For accuracy assessment of LCM the KIA parameters was used. Finally from the 1987-2011 period in order to predict changes in land use, land use maps in 2025 and 2039 were used. Results showed that during 1987-2011, important changes occurred, including increasing of (4.49%) in residential area and decreasing in agricultural area by 13.4%. Also the results of transition potential modeling using logistic showed high accuracy in all scenarios (0.72 to 0.92). Kappa coefficient in the land use modeling for 2011 with calibration periods 1987-2011 and reference map in 2011 was higher than in other scenarios. The modeling results for the years 2025 and 2039 showed that physical development Sari in West, South, North and the East directions 8.02, 6.47, 6.37 and 4.41 % are respectively.
Keywords: Modeling, Urban Growth, Landsat Satellite, Logistic Regression and Markov Chain
Full-Text [PDF 839 kb]   (626 Downloads)    
Type of Study: Research | Subject: GIS
Send email to the article author

Add your comments about this article
Your username or Email:


XML   Persian Abstract   Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Darabi H, Pirnia A, Choubin B, Rozbeh S. Urban Growth Modeling and Prediction using Logistic Regression and Markov Chain in Sari. JGST. 2018; 7 (4) :119-131
URL: http://jgst.issge.ir/article-1-599-en.html

Volume 7, Issue 4 (6-2018) Back to browse issues page
نشریه علمی علوم و فنون نقشه برداری Journal of Geomatics Science and Technology