Document Type : Research Paper

Authors

1 Assist. Professor, Department of Remote Sensing and GIS, Faculty of Geographic Science, Kharazmi University, Tehran, Iran

2 M.A., Department of Remote Sensing and GIS, Faculty of Geographic Science, Kharazmi University, Tehran, Iran

Abstract

Among the various natural hazards, floods may be considered as the most devastating factor that inflicts great damage on human societies. Therefore, the importance of estimating flood damage and its scope in planning to reduce damages and determine points with high risk is very important. The aim of this study is to determine the extent of flood hazard using OLI satellite data. For this reason, a window of OLI satellite images of Landsat 8 was acquired before and after the Dezful flood of April 25, 2016. First, preprocessing operations include radiometric and atmospheric corrections of images were done, and the principal component analysis was then used to reduce the correlation of the data. Data processing was performed using a Support Vector Machine algorithm with linear and polynomial kernels. In order to train the Support Vector Machine algorithm, training samples for each class (agricultural land, flood extent, water resources, settlement areas, and recreational areas along the river boundary) were harvested at the user level. In order to evaluate the similarity of the classes and the degree of correlation between the samples, the quantitative assessment method of the Jeffries Matusita was performed. The results showed that the flood area was 11593.26 ha, the highest damage was due to agricultural land with a destruction of 8467.45 ha and recreational and tourist areas along the riverbank with a destruction of 2659.14 ha.

Keywords

Main Subjects

Abbasi B., Arefi H., Bigdeli B., and Roessner S. (2015). Automatic generation of training data for hyperspectral image classification using support vector machine. 36th International Symposium on Remote Sensing of Environment, Berlin, Germany.
 
Akbari E., Zanganeh Asadi M. A. and Taghavi E. (2016). Change detection land use and land cover regional Neyshabour using different methods of statistical training theory. Gegra. Plan. Space Quart. J., 6(20), 35-50 [In Persian].
 
Arkhi S. and Adibnejad M. (2011). Efficiency assessment of support vector machines for land use classification using landsat ETM+ satellite data (Case study: Ilam Dam Catchment). Iran J. Range. Desert Res., 18(3), 420-440 [In Persian].
 
Anonymous. (2015). Annual statistic of Dezful town. Dezful Deputy Planning and Development, Department of Statistics and Information Technology [In Persian]. 
 
Anonymous. (2006). Handbook of Damage Evaluation. Ministry of Energy, Iran Water Resources Management Company, Deputy Head of Research and Basic Studies, Office of Standards and Technical Standards [In Persian].
 
Alavipanah K. (2011). Principal of modern remote sensing and interpretation of satellite images and aerial photography. Tehran University publication. Tehran.
 
Bigdeli B. and Samadzadegan F. (2014). Classification of hyperspectral data using a band grouping-based SVM ensemble system. J. Geomat. Sci. Technol., 4(3), 253-286.
 
Chi M., Feng R. and Bruzzone L. (2008). Classification of hyperspectral remote sensing data with primal SVM for small sized training dataset problem. Adv. Space Res., 41(11), 1793–1799.
 
Daliran Firooz H., Mokhtari F., Soltani S. and Mousavi A. (2015). Flood damage assessment in Ghamsar and Ghohrood watershed basins using HEC-FIA. J. Water Soil Sci., 19(74), 63-76 [In Persian].
 
Fatemi B. and Rezaei Y. (2012). Principal of remote sensing. Azadeh publication. Tehran.
 
Farajzadeh M. (2012). The study of flood risk in Western Azarbaijan Province sub-basins using GIS. Quant. Geomorph. Res., 1(1), 59-68 [In Persian].
 
Keshavarz A. and GhasemianYazdi H. (2005). A rapid support vector machine-based algorithm for
classification of hyperspectral images using spatial correlation. Iran J. Elect. Com. Eng., 3(1), 37-44 [In Persian].
 
Mohammadi M., Vahedbardi Sh. and Saadaldin A. (2015). Modeling the effects of land use changes on flood hydrograph (A case study: Ja’farabad wastershed, Golestan Province). J. Water Soil Conserv., 22(5), 171-185.
 
Niknejad M., Mirzaei Zadeh V. and Heydari M. (2014). Comparing different classifications of satellite imagery in forest mapping (Case study: Zagros forests in Iran). Int. Res. J. Appl. Basic Sci., 7, 1407-1415.
 
Pal M. and Foody G.M. (2010). Feature selection for classification of hyperspectral data by SVM.  IEEE Trans. Geosci. Remote Sens., 48, 2297-2307.
 
Shojaiean A., Mokhtari S., Keshtkar L. and Soleymanirad E. (2014). Comparing the performance
of parametric and nonparametric methods in land cover classification using Landsat 8 satellite images (Case study: A part of Dezful city). Geogr. Data, 24(93), 53-64 [In Persian].
 
Samadzadegan F. and Hasani H. (2012). Determination of optimum SVMs based on genetic algorithms in classification of hyper spectral imagery. J. Inform. Comun. Technol., 4(13-14), 9-24 [In Persian].
 
Tavakkoli Sabour M. and hasani Moghaddam H. (2018). Evaluating the capability of multi temporal remote sensing data in estimation of flood extent. 2nd International congress of geographic information system and remote sensing innovation technologies in monitoring environmental changes, Tehran, Iran.
 
Torahi A. A. and Rai S. C. (2011). Land cover classification and forest change analysis using satellite imagery - A case study in Dehdez Area of Zagros Mountain in Iran. J. Geogr. Inform. Sys., 3(1), 1-11.  
 
Torahi, A. A., Hasani Moghaddam H. and Adliatiq R. (2016). Performance evaluation of Support Vector Machine in land use mapping. Proc. 2004, 2nd conference of spatial information engineering, KHNTU University. Tehran, Iran [In Persian].   
 
Taati A., Sarmadian F., Mousavi A., Taghati Hossien Pour C. and Esmaili Shahir A. H. (2015). Land use classification using support vector machine and maximum likelihood algorithms by Landsat 5 TM
images. Walailak J. Sci. Technol., 12(8), 681-687.
 
Yakhkeshi M., Meftah Helgi M., Zahiri A., Yakhsheki M. E. and Madadi M. R. (2014). Effect of construction of Narmaab storage dam on the reduction of flood plain and flood damage at downstream lands. Iran Irrig. Water Eng., 4(16), 24-36 [In Persian].
 
Zeaiean Firoozabadi P., Mousavi A., Shakiba A. and Naseri H. (2003). Flood incident simulation using remote sensing data and automatic cell model (Case study part of Ghaemshahr Talar River Basin). Geogr., 1, 125-144.