Producing rangeland vegetation types map using different algorithms of satellite image classification

Document Type : Research Paper

Authors

1   Behbahan Khatam Alanbia University of Technology

2 Assistant professor Rangeland and watershed management department, Faculty of natural resources, Behbahan Khatam-Alanbia University of Technology

3 Rangeland and watershed management department, Faculty of natural resources, Behbahan Khatam-Alanbia University of Technology

Abstract

To better managing of rangeland the vegetation map is one of major factors, because plant communities is planning units of rangeland management and vegetation map shows the current status of plant communities. This research was conducted to produce vegetation type's map using Landsat 8 image classification in Behbahan, Khuzestan province. Rangelands of the study region is warm semi steppe and winter grazing. Geometric correction of satellite image was performed by ground control points with an error of less than one pixel. Atmospheric correction of existing data using the dark object subtraction was done. Field visits for vegetation type's border controlling and sampling training area was conducted. Eight supervised classification algorithms included Parallelepiped (PP), Minimum Distance to mean (MD), Mahalanobis distance (MAH), Maximum Likelihood (ML), Neural Net (NN) and Support Vector Machine (SVM) was performed. The results showed that ML algorithm has the highest overall accuracy (87.5 percent) and kappa (0.867) and PP algorithm has the lowest overall accuracy (67.1 percent) and kappa (0.571). It is suggested that, along with digital methods of classification of satellite images, visual interpretation should be used to clarify the boundary of the obtained vegetation types map.

Keywords


[1]        Alavipanah, S. K. 2016. Application of remote sensing in earth science (soil science). University of Tehran Press, 5rd edition, 496 p, (In Farsi).
[2]        Alavipanah, S. K., Ehsani, A. H. and Omidi, P. 2004. A study of desertification and changes of Damghan playa lands using multy spectral and multy temporal data. Desert, 9(1): 143-154, (In Farsi).
[3]        Allouche, O., Tsoar, A. and Kadmon, R. 2006. Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS). Applied Ecology, 43 (6): 1223–1232.
[4]        Bahadur, R. and Krishna K.C. 2009. Improving Landsat and IRS image classification: evaluation of unsupervised and supervised classification through band ratios and DEM in a mountainous landscape in Nepal.  Remote sensing, 1: 1257-1272.
[5]        Baqerifar P., Basiri R., Yousefi Khanghah S. and Pourkhabbaz H.R. 2014. Mapping of land use change using remote sensing and Geographic Information System techniques (Case study: forest Baghmalek city). 4th international conference on environmental challenges and dendrochronology, Sari, Iran, 14-15 May.
[6]        Daftare fani-mohandesi. 2005. Report of Country Vegetation Map Preparation Project. Forests, Range and Watershed Management Organization, 129 pages, (In Farsi).
[7]        Davoudi Monazam, Z., Hajinejad, A., Abbasnia, M. and Pourhashemi, S. 2014. Detecting of land use change with remote sensing technique (Case study: Shahriar province). RS & GIS for Natural Resources, 5(1): 1-13, (In Farsi).
[8]        Fazeli Farsani, A., Ghazavi, R. and Farzaneh, M. R. 2015. Investigation of land use classification algorithms using images fusion techniques (Case study: Beheshtabad Sub-basin). RS & GIS for Natural Resources, 6(1): 91-105, (In Farsi).
[9]        Freeman, E.A. and Moisen, G.G. 2008. A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and kappa. Ecological Modeling, 217 (1): 48–58.
[10]    https://earthexplorer.usgs.gov/  (15/06/2015)
[11]    Javadnia E., Mobasheri, M. R., and Kamali, Gh. A. 2009. MODIS NDVI Quality Enhancement Using ASTER Images. Agr. Sci. Tech., 11 (5): 549-558.
[12]    Lillesand T.M., Kiefer, R. W. and Chipman, W. 2004. Remote sensing and image interpretation. 5th Edition, New York, Jhon Willey and Sons, 763p.
[13]    Mather, P. and Tso, B. 2009. Classification Methods for Remotely Sensed Data. Second Edition, CRC Press, 376 Pages.
[14]    McPherson, J.M., Jetz, W. and D.J. Rogers. 2004. The effects of species' range sizes on the accuracy of distribution models: ecological phenomenon or statistical artefact? Applied Ecology, 41 (6): 811–823.
[15]    Mesdaghi, M. 2010. Range management in Iran. University of Imam Reza press, 6rd edition, 336 pages (In Farsi).
[16]    Niazi, Y., Ekhtesasi, M., Malekinezhad, H. and Hosseini, S. Z. 2011. Comparison Between two Classification Methods of Maximum likelihood and Artificial Neural Network for Providing Land use Maps Case Study: Ilam Dam Area. Geography and Development, 20: 119-132, (In Farsi).
[17]    Ojigi, M. L. 2006. Analysis of Spatial Variations of Abuja Land use and Land cover from Image Classification Algorithms. ISPRS Commission VII Mid-Term Symposium. Theme: Remote Sensing: From Pixel to Processes. 8-11th May, Enschede, Netherlands.
[18]    Pastor, I., Navarro, J., Gomez, I. and Koch, M. 2010 Detecting drought induced environmental changes in a Mediterranean wetland by remote sensing. Applied Geography, 30: 254-262.
[19]    Rasouli, A. A. 2009. Principles of applied remote sensing. University of Tabriz press, 806 pages, (In Farsi).
[20]    Rostami, K., Torahi, A. and Yousefi khanghah, S. 2014. Investigation of forest extends change detection using satellite imagery in Zagros forests (case study in Behbahan Province Hills in Iran). International Journal of Biosciences (IJB), 4(2): 47-54.
[21]    Shoshany M. and Karnibad, L. 2011. Mapping shrubland biomass along Mediterranean climatic gradients: The synergy of rainfall-based and NDVI-based models. Remote Sensing, 32 (24): 9497–9508
[22]    Weeks E. S., Gaelle, A., Ausseil, E., Shepherd, J. D. and Dymond, J. R. 2013. Remote sensing methods to detect land-use/cover changes in New Zealand’s indigenous grasslands, New Zealand geographer, 69 (1): 1-13.
[23]    Wulder, M. A., White, J. C., Goward, S. N., Masek, J. G., Irons, J. R., Herold, M. and Woodcock, C. E. 2008. Landsat continuity: Issues and opportunities for land cover monitoring. Remote Sensing of Environment, 112(3): 955-969.
[24]    Yousefi Khanghah S., Arzani, H., Javadi, S. A. and Jafari, M. 2013. Producing rangeland vegetation types Using LISS III and ASTER Satellite Sensors (Case Study Deylam Area). RS & GIS in Natural Resources, 4 (2): 81-91, (In Farsi).
[25]    Zhang W. W., Yao, L., Li, H., Sun, D. F. and Zhou, L. D. 2011. Research on Land Use Change in Beijing Hanshiqiao Wetland Nature Reserve Using Remote Sensing and GIS. 3rd International Conference on Environmental Science and Information Application Technology (ESIAT), Procedia Environmental Sciences, 10 (A):  583 – 588.
[26]    Zobeiry, M. and Majd, A. R. 2013. An introduction to remote sensing technology and its application in natural resources. University of Tehran Press, 10rd edition, 318 p, (In Farsi).
Volume 71, Issue 3
December 2018
Pages 847-856
  • Receive Date: 15 January 2018
  • Revise Date: 29 November 2018
  • Accept Date: 26 June 2018
  • First Publish Date: 22 November 2018