Determination of Best Supervised Classification Algorithm for Land Use Maps using Satellite Images (Case Study: Baft, Kerman Province, Iran)

Document Type: Research and Full Length Article


Department of Ecology, Institute of Science and High Technology and Environmental Sciences, Graduate University of Advanced Technology, Kerman, Iran


According to the fundamental goal of remote sensing technology, the image classification of desired sensors can be introduced as the most important part of satellite image interpretation. There exist various algorithms in relation to the supervised land use classification that the most pertinent one should be determined. Therefore, this study has been conducted to determine the best and most suitable method of supervised classification for preparing the land use maps involving no grazing, heavy and moderate grazing rangelands, ploughed rangelands for harvesting licorice roots and dry land and fallow lands in Baft, Kerman province, Iran. After being assured of accuracy and lack of geometric and radiometric errors, the images of Landsat and ETM+ sensors achieved on 3 July 2014 have been used. A variety of algorithms involving Mahalanobis distance, Minimum distance, Parallelepiped, Neural network, Binary encoding and Maximum likelihood was investigated based on field data which were obtained simultaneously. These algorithms were compared with respect to error matrix indices, Kappa coefficient, total accuracy, user accuracy and producer accuracy of maps using ENVI 4,5. The results indicated that the Maximum likelihood algorithm with Kappa coefficient and total accuracy of map estimated as 0.969 and 97.77% were regarded as the best supervised classification algorithm in order to prepare the land use maps. Mahalanobis distance algorithm had a low ability for recognizing two types of dry land and fallow land uses concerning the extracted maps. According to the findings, various land use maps as rangelands under three grazing intensities and ploughed rangelands to harvest the licorice roots provided by the means of algorithms related to neural networks were not of sufficient accuracy. The highest Kappa coefficient of Neural network algorithms was estimated as 0.5 and attributed to the algorithm of multilayer perceptron neural network with the logistic activation function and one hidden layer.


Main Subjects

Ahmadisani, N., Darvishsefet, A.A., Zobeiri, M. and Farzaneh, A., 2008. Potentiality of ASTER images for forest density mapping in Zagros (case study: Marivan forests). Iranian Jour. Natural Res., 61(3): 603-614. (In Persian).

Alavipana, S.K., 2003. The application of remote sensing in the earth sciences (soil sciences).­ University of Tehran press., 478 pp. (In Persian).

Alavipana, S.K., Matinfar, H.R., Rafiei Emam, A., 2009. The application of information technology in the earth sciences (on digital soil mapping). University of Tehran press., 457pp. (In Persian).

Alavipanah, S.K., Porbagher, A.M., Khalilpor, S.A., Mashadi, N., 2001. Investigation on vegetation and soil salinity based on remote sensing and geographical information system (Case study; Soor river watershed, Karaj). Desert, 6(1): 69-86.

Alborzi, M., 2007. Neural computing: information (Translation). Sharif University of Technology press., 137pp. (In Persian).

Ariapour, A., Dadrasi Sabzevar, A., Toloee, S., 2013. Estimation of vegetation and land use changes using remote sensing techniques and geographical information system (Case Study: Roodab plain, Sabzevar City). Jour. Rangeland Science., 4(1): 1-13. (In Persian).

Arzani H., Mirakhorlou K.H. and Hosseini S.Z., 2009. Land use mapping using Landsat7 ETM data (Case study in middle catchment’s of Taleghan). Iranian Jour. Range Desert Research, 16(2): 150-160. (In Persian).

Dellepiane, S. G. and Smith, P. C., 1999. Quality assessment of image classification algorithms for land cover mapping: A review and a proposal for a cost-based approach. International Jour. Remote Sensing, 20(8): 1461-1486.

Esmali, A., Abdollahi, K., 2010. Watershed management & soil conservation. University of Mohaghegh Ardabili., 578 pp. (In Persian).

Faramarzi, M., Fathizad, H., Pakbaz, N., Golmohamadi, B., 2013. Application of different methods of decision tree algorithm for mapping rangeland using satellite imagery (Case study: Doviraj catchment in Ilam Province). Jour. Rangeland Science., 3(4): 321-330. (In Persian).

Foody, G. M., 1992. Compensation for chance agreement in image classification for assessment. Photogrammetric Engineering and Remote Sensing., 58, 1459-1460.

Jafari, M., Zehtabian, G.H. and Ehsani, A.H., 2013. Effect of thermal bonding and supervised classification algorithms of satellite data in making land use maps (Case study: Kashan). Iranian Jour. Range Desert Research., 20(1): 72-87. (In Persian).

Lillesand, T.M. and Kiefer, R.W., 2012. Remote sensing & image interpretation. 3th Ed., John Wiley & Sons Inc. New York., 750 pp.

Luciana, P.B., Edward, A., Ellis, B., Gholz, H.L., 2007. Land use dynamics and landscape history in La Montana, Campeche, Mexico. Landscape and Urban Planning. 82: 198-207.

Mazaheri, M. R., Esfandiari, M., Masih Abadi, M.H. and Kamali, A., 2013. Detecting temporal land use changes using remote sensing and GIS techniques (Case study: Jiroft, Kerman Province). Jour. Applied RS & GIS Techniques Natural Resource Science. 4(2): 25-39. (In Persian).

Nasri, M., Sarsangi, A., Yeganeh, H., 2013. Detection of land use changes for thirty years using remote sensing and GIS (Case Study: Ardestan Area). Jour. Rangeland Science. 4(1): 23-33. (In Persian).

Research Systems Institute., 2008. ENVI 4.5 User’s Guide: the environment for visualizing images. Lafayette.

Saffari, M., 2004. Investigating of politics and operation of watershed management, soil and water resources. First National Congress of Watershed Management & Soil and Water Resources, Kerman, 410 pp. (In Persian).

Sanjari, S. and Boroomand, N., 2013. Land use/cover change detection in last three decades using remote sensing technique(Case study: Zarand region, Kerman province). Jour. Applied RS & GIS Techniques in Natural Resource Science., 4(1): 51-67. (In Persian).

Shirazi, M., Zehtabian, G.H., Matinfar, H.R., 2010. Survey of capability of remote sensing indices for enhancement of land cover in arid areas (case study: Najmabad). Iranian Jour. Range Desert Research., 17(2): 256-275. (In Persian).

Shresth, P.D., Zinck, J.A., 2001. Land use classification in mountainous areas (application to Nepal). International Jour. Applied Earth Observation Geo Information., 3 (1): 31- 53.

Srivastava, S.K. and Gupta, R.D., 2003. Monitoring of change in land use/land cover using multisensor satellite data. Map India conference, India., 275 pp.

Vahedi, R., 2001. Utilization of Landsat image in rangeland analysis. M.Sc. thesis of rangeland management. Tehran university., 174 pp. (In Persian).

Yousefi, S., Mirzaee, S., Tazeh, M., Pourghasemi, H., Karimi H., 2015. Comparison of different algorithms for land use mapping in dry climate using satellite images: a case study of the Central regions of Iran. Desert., 20 (1): 1-10. (In Persian).