Producing land cover maps using remote sensing and decision tree algorithm (Case study: Bakhtegan national park and wildlife refuge)

Document Type : Research Paper

Authors

1 PhD Student of Environmental Planning, University of Tehran, Tehran, Iran

2 Professor of Remote Sensing, University of Tehran, Tehran, Iran

3 Assistant Professor of Environmental Planning and Management, University of Tehran, Tehran, Iran

4 MA. Of Remote Sensing, University of Tehran, Tehran, Iran

Abstract

 
 




Extended abstract
1- Introduction
Land cover mapping is essential in the management of natural resources and environment, land use plan preparation and land capability determination and is considered as one of the main sources in preparing development. National parks and protected areas are important part of Earth's ecosystems and are safe zones for wildlife. These areas have many environmental functions. Since land use and cover changes in each region can
 largely effect on ecological functions and processes, Inform of the latest status of this regions plays an essential role in the quality of their management. Bakhtegan national park and wildlife refuge that contain Neyriz wetland, in the east Shiraz, Fars province, has been studied in this paper (Fig 1).
 
2- Methodology
This paper aimed at improving classification accuracy and image quality improvement processing them based on a model of decision tree algorithm by combining the results of maximum likelihood algorithm. In this paper, a new model was developed for new land cover mapping of Bakhtegan national parks and wildlife refuge. In general, the process of investigation is shown in Figure 2.
 
 
 

 

 
Fig 1: Area of study
 
 
Fig 2: Landcovermappingprocessin thisstudy
 

 

Two kinds of data sources were used to land cover mapping for 2010 in this region: (1) TM images of landsat satellite from early summers of 2010and (2) Digital elevation model (DEM). The radiometric correction was applied on images by using histogram matching method. Histogram matching is a method in image processing for color adjustment by using the image histogram.
 
 
3- Discussion
Model function is branch that consists of four levels of decision making that ultimately five types of cover including agricultural land, pasture, water, salt and barren land will determine.
In this article, DEM, vegetation indices and water index is used to raise the accuracy of decision tree classification algorithm.
With model-based decision tree algorithm, regional land use map for 2010 with high accuracy were obtained (Fig.3). To evaluate the accuracy of image classification, the GPS ground control points had been harvested from the area were used. Overall accuracy, users and producer’s accuracy, and Kappa statistics were extracted from the error matrix. User and producer accuracy of classification is high and between 82 to 97 percent. Overall accuracy of  classification is 92.72 % and Kappa statistic value obtained 90.73%. Areas of each class were calculated in square kilometer and percentage (Fig 4).

 

 
 
Fig 3: Land cover map of study area with DT algorithm
 
 
Fig 4: Classes area andratio
 



4- Conclusion
In this study land cover map of Bakhtegan national parks and wildlife refuge was prepared through development of a model based on decision tree algorithms and its combination with classification results of maximum likelihood.
The results of this study indicate that vegetation indices separate vegetation cover from no vegetation cover and agricultural lands from range lands with high accuracy. The amounts of water index and ​reflective values of band 4 separated the water from other classes well. In the final stage, bare lands separated by using maximum likelihood classification results and the values ​​of the slope and altitude. This indicates the high flexibility of the DT-based algorithm model by using different sources of data and different algorithms. The results show that using combination methods and auxiliary data in images classification greatly increases the classification accuracy

Keywords

References

Alavipanah, S, K. Matinfar, H, R. Sarmadian, Fereydoon. (2005), Application of satellite data assessment of time savings, waste prevention methods of national resources conference, IRI Academy of Sciences, Tehran.
Alavipanah, S, K. Masudi, Masud. (2002), Land use mapping using Landsat digital data and GIS, Journal of Agricultural Sciences and Natural Resources, 8 year,65-76
Berberoglu, S., A. Akin,. (2009). Assessing different remote sensing techniques to detect land use/cover changes in the eastern Mediterranean, International Journal of Applied Earth Observation and Geo information, 11, 46–53.
Binh, T.N.K.D., Vromant, N., Hung, N.T., Hens, L., Boon, E.K., (2005). Land cover changes between 1968 and 2003 in Cai Nuoc, Ca Mau Peninsula, Vietnam. Environment, Development and Sustainability 7, 519–536.
Congalton, R. G., Green, K., (1999), Assessing the accuracy of remotely sensed data: Principles and practices, Boca Rotan, Florida’ Lewis Publishers.
Darvish sefat, A, A., Shetaii, SH,. (1997), Forest mapping using Landsat TM data by digital methods, Journal of Iran naturar resources, 50, 39-45, University of Tehran, Tehran.
Department of Environmental Protection, Fars Province, GIS unit, (2006) Land cover and land use maps of Bakhtegan national park and wildlife refuge.
Fatemi, S, B,. Rezaii, Y. (2008), Fundamentals of remote sensing, Azade publication, Tehran.
Huete A R, (1988), A soil-Adjusted Vegetation Index (SAVI), Remote Sensing of Environment, 25, 295-309.
Kandrika, S., P.S. Roy,.(2008). Land use land cover classification of Orissa using multi-temporalIRS-P6 awifs data: A decision tree approach, International Journal of Applied Earth Observation and Geo information, 10, 186–193.
Koh, C.N., Lee, P.F., Lin, R.S., (2006). Bird species richness patterns of northern Taiwan: primary productivity, human population density, and habitat heterogeneity. Diversity & Distributions 12 (5), 546–554.
Lawrence, R.L. and Wright, A., (2001), Rule-Based Classification systems using classification and regression tree (Cart) analysis, Photogrammetric Engineering & Remote Sensing, 67, 1137-1142.
Mather, P, M. (1999). Computer Processing Of Remotely Sensed Images 2nd Edition, John Willley & Sons.
McFeeters, S.K., (1996), the use of the normalized difference water index (NDWI) in the delineation of open water features, International Journal of Remote Sensing, 17, 1425–1432.
Mui J.K. and Fu, K.S. (1980), Automated Classification of Nucleated Blood Cells Using a Binary Tree Classifier, Pattern Analysis and Machine Intelligence, PAMI-2, 429–443.
Morawitz, D., Blewett, T., Cohen, A., Alberti, M., (2006). Using NDVI to assess vegetative land cover.
Otukei, J.R., T. Blaschke,. (2010), Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms, International Journal of Applied Earth Observation and Geo information, 12S, S27–S31.
Salah-eldin, A., Nagaty, K. and Elarif T., (2008). An enhanced histogram matching approach using the Retinal filters compression function for illumination normalization in face recognition, Springer Berlin/Heidelberg.
Schowengerdt, R.A., (1997), Remote Sensing: Models and Methods for Imagery Processing, 2nd ed.
Sesnie, S.E., Paul E. Gessler, Bryan Finegan, Sirpa Thessler,. (2008). Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments, Remote Sensing of Environment, 112, 2145–2159.
Shalaby,A., Ryutaro Tateishi,. (2007), Remote sensing and GIS for mapping and monitoring land cover and land-use changes in the Northwestern coastal zone of Egypt Applied Geography, 27, 28–41.
Shetaii, SH,. Abdi, O,. (2008), Mapping of land use in mountainous regions of Zagros using ETM+ data, Journal of Agricultural Sciences and Natural Resources, 57, 129-138, Agricultural Sciences and Natural Resources university of Gorgan, Gorgan.
Vogelmann, J.E., (2001), Completion of the 1990s national land cover data set for the conterminous United States from Landsat Thematic Mapper and ancillary data sources, Photogrammetric Engineering & Remote Sensing, 67, 650-662.
Wang, Y., Brian R Mitchell , Jarunee Nugranad-Marzilli, Gregory Bonynge, Yuyu Zhou, Gregory Shriver,. (2009), Remote sensing of land-cover change and landscape context of the National Parks:A case study of the Northeast Temperate Network ,Remote Sensing of Environment, 113, 1453–146.
Wentz, E.A., Stefanov, W.L., Gries, C., Hope, D., (2006). Landuse and land cover mapping from diverse data sources for an arid urban environments. Computers, Environment and Urban Systems 30, 320–346.
Wulder, A. Joanne C. White a, Samuel N. Goward b, Jeffrey G. Masek c,James R. Irons c, Martin Herold d, Warren B. Cohen e, Thomas R. Loveland f, Curtis E,.(2008), Landsat continuity: Issues and opportunities for land cover monitoringMichael A., Woodcockg Remote Sensing of Environment, 112, 955–969.
 
 
Geography and Environmental Planning
Volume 23, Issue 3 - Serial Number 3
December 2012
Pages 93-110

Files

History

  • Receive Date: 14 June 2016
  • Revise Date: 18 July 2018
  • Accept Date: 14 June 2016

Share

How to cite

Statistics