Document Type : Scientific extension


1 M. Sc. Student, Remote Sensing, Islamic Azad University Ramsar Branch, Geomatic Department Ramsar, Iran.

2 Assistant Professor, Islamic Azad University Ramsar Branch, Geomatic Department, Ramsar, Iran


This research aimed to study urban growth modeling of Rasht city using remote sensing and neural network techniques. To this purpose, land use changes have been detected by analyses of Landsat and sentinel images. Due to improvement of spectral and spatial resolutions of sentinel images compared with Landsat ones, it seems to observe improvements in the accuracy of image processing and monitoring of temporal changes. Map production from images was carried out by combining several classification methods using a decision tree approach and achieving best results from the Sentinel image with the Kappa coefficient of 0.92. For growth urban modeling, the images captured in years 2000 and 2011 were used in a neural network. In order to validate the model, the 2017 map was predicted using the generated model. The matching of the predicted map with the 2017 reference map based on the overall accuracy and Kappa coefficients was 0.9113 and 0.8422, respectively. Finally, according to efficiency of the model, the proposed method was used to predict the 2025 map.


[1]   Khoshgoftar, M. M. and Talei, M., "Simulation of urban growth in Tehran using CA-Markov model", Iran Remote Sensing and GIS, Vol. 2, No. 6, 2010, pp. 17-34 (In Persian).
[2]   Gharagozlu, A., Nouri Kermani, A. and Kishori, Z., "Evaluation of physical changes and analysis of urban development using high-resolution satellite data and RS/GIS systems (case study of five region of Tehran)", Journal of Environmental Science and Technology, Vol. 11, No. 1, 2009, pp. 219-229 (In Persian).
[3]   Faizizadeh, B. and Haji Mirrahimi, S. M., "Detecting land use changes using object-oriented classification method (case study: shahrek andisheh)", Geomatics Conference, National Mapping Organization, Tehran, Iran, 2008 (In Persian).
[4]   Haghighi Zaidehi, B., Jabarian Amiri, B., and Ebrahimpour, R., "Spatial growth prediction of Lahijan city using remote sensing technique and Automatic-Markov cell model", 3rd Environmental Planning and Management Conference, Tehran, University of Tehran, 2013 (In Persian).
[5]  Tayyebi, A., Pijanowski, B.C. and Tayyebi, AH. “An urban growth boundary model using neural networks, GIS and radial parameterization: An application to Tehran, Iran, “ Landscape and Urban Planning, Vol. 100, No. 1, 2011, pp. 35-44.
[6]   Pahlavani, P. and Askarian Omran, S., "Modelling and forecasting of urban expansion based on optimized feed-forward neural network and neighborhood filter with different threshold limits (study area: Tehran)", Scientific-Research Journal of Mapping Sciences and Techniques, vol. 6, No. 1, 2015, pp. 87-100 (In Persian).
[7]   Soyoung, P. et al. “Prediction and comparison of urban growth by land suitability index mapping using GIS and RS in South Korea,” Landscape and urban planning, Vol. 99, No. 2, 2011, pp. 104-114.
[8]   Izarazo, I. “Urban Land Cover and Land Use Classification Using Hsing High Spatial Resolution Images and Spatial Metrics,” Proceedings of the 2nd Workshop of the EARSEL SIG on Land Use and Land Cover, 2006, pp. 292-298.
[9]   Jianjun, J., Jie, Z., Hongan, W., Li, A., Hailing, Z., Li, Z., Jun, X. “Land Cover Changes in the Rural-urban Interaction of Xian Region Using Landsat TM/ETM+ Data,” Journal of Geographical Science, 2005, Vol. 15, No. 4, pp. 423-43.
[10]  Fatemi, S. B. and Rezaei, Y., Basics of Remote Sensing, Second Edition, Azadeh Publishing House, 2014 (In Persian).
[11] Wasserman, P. D., Advanced Methods in Neural Computing, 1rd Ed., John Wiley & Sons, 1993.