Home Articles Evaluation of the Land Cover Features from Landsat TM over Saudi Arabia

Evaluation of the Land Cover Features from Landsat TM over Saudi Arabia

H. S. Lim, M. Z. MatJafri, K. Abdullah, N. M. Saleh, C. J. Wong
School of Physics, Universiti Sains Malaysia

Sultan AlSultan
ISPRS, Commission 7 WG VII/7, Middle East Coordinator
Riaydh City, Saudi Arabia

Land cover classification from remotely sensed image is an important research and widely used in remote sensing application. A Landsat TM scene was used for land cover mapping over AlQasim, Saudi Arabia. Standard supervised classification techniques were applied to the Landsat TM image. Training sites and land cover categories were selected within the satellite scene using polygon. An accuracy assessment was also carried out in this study. Maximum Likelihood classifier produced superior result and achieved a high degree of accuracy. Finally, a land cover map was generated using the optimum supervised classification technique. A brief discussion on the land cover over Saudi Arabia is given in this paper.

Remote sensing can be used in various purposes. In the past few years, there has been a growing interest in the use of remote-sensing systems for a regular monitoring of the earth’s surface (Bruzzone and Prieto, 2002). Remote sensing is the main source of space information. Since the launch of satellites, remotely sensed data have been used to produce topographic, land use and land cover maps. Land cover classification through remote sensing methods has been widely used by the United State Geological Survey Department (Adam, et al., 2002). Two of the most common uses of satellite images are mapping land cover via image classification and land cover change via change detection (Song, et al., 2001). The aim of this study is to investigate whether the high spatial resolution of Landsat TM imagery is suitable for land cover mapping using supervised classification techniques. In this study, supervised classification methods were applied to the satellite images. Maximum Likelihood classifier was found to produce the best accuracy in this study. The accuracy assessment of the classified images also has been done in this study.

The Landsat TM images used in this study was acquired on 15 June 1998 (Fig. 1). The satellite track is 168/43. The selected study area is centered on the city of Buraydah in Al-Qassim state, which is situated along Wadi Ar Rumah, Saudi Arabia. Figure 1 shows the study area of the City of Alkhabra and its surrounding desert terrain. The urban transportation network of Buraydah dominates the central portion of the image. Though large portions of the surrounding terrain contain desert features (sand dunes and Sabkah lakes). The western portion of the city is dominated by date palm grove vegetation and agriculture. There are definitely areas of Buraydah that are clearly being affected by dune encroachment. Our preliminary analysis clearly indicates that satellite imagery and the use of land cover mapping provides a means to identify and quantify the effects of desert processes upon urban areas.

Fig. 1 The study area of the City of Alkhabra, Saudi Arabia

The satellite used in this study was captured on 15/6/1998 (Fig. 2). A total of 42 training sample areas were selected in this analysis. For the satellite scene, six Landsat TM bands (except band 6) were used in the multispectral classification analysis using the classifiers mentioned earlier. The satellite image was classified into 3 classes, namely vegetation, soil and urban.

Three supervised classification methods were performed to the digital images (Maximum Likelihood, Minimum Distance-to-Mean, and Parallelepiped). Training sites were needed for supervised classification. Selection of training areas in this study was based on the colour image. A total of 200 samples were chosen randomly for the accuracy assessment. Many methods of accuracy assessment have been discussed in remote sensing literatures. Three measures of accuracy were tested in this study, namely overall accuracy, error matrix and Kappa coefficient. The most widely promoted and used accuracy measure, however, may be derived from a confusion or error matrix.

Kappa coefficient and overall accuracy values for the three classifications are shown in Table 1. The overall accuracy is expressed as a percentage of the test-pixels successfully assigned to the correct classes. Maximum Likelihood produced the highest degree of accuracy with overall accuracy of 91.2%, Minimum Distance-to-Mean gave overall classification accuracy of 75.2%, and Parallelepiped resulted in the overall classification accuracy of 41.0%. A classified image using Maximum Likelihood classifier is shown in Fig. 3.

Fig. 2 The study area imagery

Table 1: The overall classification accuracy and Kappa coefficient

Classification method Overall classification accuracy (%) Kappa coefficient
Maximum Likelihood 91.20 0.852
Minimum Distance-to-Mean 75.20 0.612
Parallelepiped 41.00 0.312

Fig. 3 The land cover changes map[Colour Code: Green = Vegetation, Blue = Land and Red = Urban]

From the three classified maps, Maximum Likelihood gives the best result for land cover mapping. The maximum likelihood supervised classifier produced the highest accuracy in this study. The classified map can be used to provide useful data for planning and management in theis area. The application of the Landsat TM imagery for land cover mapping produced reliable and accurate results.

We would like to thank the technical staff who participated in this project. Thanks are also extended to USM for support and encouragement


  1. Adam, Y. H., Mohd Yusoff, A. R., Buse, I., Aman, M. S. and Redza, M., 2002, Proceeding of the International Symposium and Exhibition on Geoinformation 2002.
  2. Bruzzone, L. and Prieto, D. F., 2002, A partially unsupervised cascade classifier for the analysis of multitemporal remote-sensing images. Pattern Recognition Letters, 23, 1063–1071.
  3. Song, C., Woodcock, C. E., Seto, K. C., Lenney,M. P. and Macomber, S. A., 2001, Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? Remote Sensing Environment, 75, 230–244.