Monitoring the status of Bakhtegan Lake and surrounding areas using satellite imagery and computational intelligence

Document Type : Research Article

Authors

1 RS & GIS, Faculty of Environment and Energy,Islamic Azad University, Research Branch, Tehran, Iran

2 Assistant Professor, Remote Sensing and Spatial Information Systems, Faculty of Environment and Energy, Islamic Azad University, Research Branch, Tehran, Iran

Abstract

Multilispectral picture classification is one of the most important techniques for separating earth units.The phenomenon of global warming,expansion damming,water storage behind dams and excessive utilization of existing water for human uses has caused the drying of lakes, including Lake Bakhtegan. For this purpose, Landsat images of 1991, 2000, 2010, and 2017 were collected in Bakhtegan Lake and surrounding areas. These images were categorized based on educational samples in four classes of water, septicity, mountain and urban areas after pre-processing and corrections required by the supervised maximum likeness.The same image was then sorted by multi-layer perceptron neural network method in the above classes. Finally, for both methods, the error matrix was extracted and the overall accuracy and kappa coefficient were calculated.For the year 1991, the maximum probability and neural network method was 87% and 93%, and the kappa coefficient was calculated to be 0.86 and 0.90, respectively. . Therefore, due to the higher accuracy of Negative Network, images of the years 2000, 2010 and 2017 were categorized by this method.After classification, in order to evaluate it, Google Earth was considered as the test sample for each information class and the overall accuracy and kappa coefficient were 89% and 0.85, respectively.

Keywords

Main Subjects


Khosravani Z, Khajedin J, Mohebbi M, Safianian A. Check satellite imagery capability P5 and P6 in preparation of desert areas map, M.Sc degree Agriculture. Faculty of Agriculture and Natural Resources. Isfahan University of Technology.2008 [Persian].
[2].Alavipanah SK. Application of remote sensing in earth sciences. 4nd ed. Tehran:Tehran University. 2009. [Persian].
[3]. Khoshnudi N.www.irna.ir.. 2017;May 09. [Persian].
[4]. Teimuri I, Purahmad A, Habibi L, Salarvandian F. Determination of environmental liability of Tashk and Bakhtegan lakes using C-Fuzzy classification method. Natural Geography Research.2011; 77. 21-37. [Persian].
[5]. Zahedifard N, Khajeddin SJD. Application of digital data of TM sensor in preparation of land use map of Bazoft watershed basin. Agricultural Science and Technology.2004; 8(2). 91-105. [Persian].
[6]. Ghasemlu N, Mohammadzade A, Sahebizoj MR. The classification of large scale satellite images using artificial neural network methods and comparing them with the most similarity and least distances from the mean. Geomatics National Conference. Tehran: National Cartographic Center. 2009. [Persian].
[7]. Fatemi SB, Rezaee Y. Basics of remote sensing. 2nd ed. Tehran: Azadeh; 2014. [Persian].
[8]. Rahimzadegan M, Mobashri MR, Valadanzoj MJ, Maghsudimerani Y. Provides a method for classifying AVIRIS hybridization data by extracting attributes and combining classifiers. Iran Remote sensing and GIS.2014; 1(1). 99-114. [Persian].
[9]. Jafari M, Zahtabian GhR, Ehsani AH. Investigating the effect of thermal bonding and satellite-controlled satellite sorting algorithms on land use planning(case study: Kashan). Research on Range and Desert of Iran. 2015; 20(1). 72-87. [Persian].
[10]. Shafiee M, Sarkargarardakani A, Vahidnia MH. Comparison of classification with random forestry algorithms and neural networks on simulated hyperspectral images. Geomatics National Conference. Tehran: National Cartographic Center. 2017. [Persian].
 
[11]. Yaghubzade M, Akbarpur A. Investigation of the effect of satellite image categorization algorithms on the runoff and flood excursion maximum flood number using RS and GIS. Geography and development. 2011; 9(22). 5-22. [Persian].
[12]. Ahmadpur A, Soleimani K, Shokri M, Ghorbanipashakalaee J. Comparison of the efficiency of three common methods of supervised satellite data classification in coarse shear study. Remote Sensing and GIS in Natural Resources Science. 2011; 2(2). 69-81. [Persian].
[13]. Saberi A, Esmaeili A, Bagheri H. Improved ASTER image classification using ACO and GA algorithms. Geomatics National Conference. Tehran: National Cartographic Center. 2014. [Persian].
[14]. Alimoradi N, Jamali AA, Mazraemolaee M, Khajepur H. Investigation of land use change process using LCM model and landsat satellite image and future forecasting using neural network (MLP) (Borujerd County). Geomatics National Conference. Tehran: National Cartographic Center. 2017. [Persian].
[15]. Khezriahmadabad M, Bameri M, Bashghare M, Arkhi S. Monitoring land use change using satellite images and RS and GIS techniques (Case Study: Baharestan). Geomatics National Conference. Tehran: National Cartographic Center. 2017. [Persian].
[16]. Ghasemlu N, Mohammadzade A, Sahebi MR, Valadanzoj MJ. The classification of large-scale satellite images using artificial neural network methods and comparing them with the max-likelyhood and min distance from the mean. Geomatics National Conference. Tehran: National Cartographic Center. 2008. [Persian].
 
[17]. Yusefi S, Taze M, Mirzaee S, Moradi HR, Tavangar Sh. Comparison of different satellite image classification algorithms for land use mapping (case study: Noor city). Remote Sensing and GIS in Natural Resources Science. 2014; 5(3). 67-76. [Persian].
[18]. Bolhasani K, Zareei H, Kabolizade M. Investigating and evaluating the changes in vegatation in recent decades using RS and GIS. Geomatics National Conference. Tehran: National Cartographic Center. 2017. [Persian].
[19]. Giacinto G, Roli F, Bruzzone L. Combination of neural and statistical algorithms for supervised classification of remote sensing images. Pattern Recognition Letters. 2000; 21(5). 385-397.
[20]. Hepner N, George F. Artificial neural network classification using a minimal training set: comparision to conventional supervised classification. Photogrammetric Engineering and Remote Sensing. 1990; 56(4). 65-78.
[21]. Dennison F, Roberts D, Peterson S. Spectral shape based temporal composition algorithms for MODIS surface reflectance data. Remote Sensing of Enviroment. 2007; 109(4). 510-522.
[22]. Neagoen V, Neghina M, Datcu M. Neural network techniques for automated land-cover change detecion in multispectral satellite time series imagery. Mathematical Models and Methods In Applied Sciences. 2012; 1(6). 130-139.
[23]. Zeraati M, Matinfar HR, Alavipanah SK. Investigating and evaluating quantitative and qualitative methods of land use and land cover changes in Kashan region using remote sensing images analysis TM and ETM+. Geomatics National Conference. Tehran: National Cartographic Center. 2014. [Persian].
Volume 5, Issue 1
April 2018
Pages 251-263
  • Receive Date: 22 September 2017
  • Revise Date: 22 January 2018
  • Accept Date: 04 January 2018
  • First Publish Date: 21 March 2018
  • Publish Date: 21 March 2018