Accuracy Assessment of Land Use Land Cover in Umabdalla Natural Reserved Forest, South Kordofan, Sudan
[1]
Osman Esaid Adlan Abdelkareem, Department of Gum Aarbic Research, Institute of Gum Arabic Research and Desertification Studies, University of Kordofan, Elobeid, Sudan.
[2]
Hatim Mohamed Ahmed Elamin, Department of Gum Aarbic Research, Institute of Gum Arabic Research and Desertification Studies, University of Kordofan, Elobeid, Sudan.
[3]
Muneer Elyas Siddig Eltahir, Department of Extension, Training and Documentation, Institute of Gum Arabic Research and Desertification Studies, University of Kordofan, Elobeid, Sudan.
[4]
Hassan Elnour Adam, Department of Forestry and Range Sciences, Faculty of Natural Resources and Environmental Studies, University of Kordofan, El Obeid, Sudan.
[5]
Mohamed Eltom Elhaja, Department of Desertification Studies and Environment, Institute of Gum Arabic Research and Desertification Studies, University of Kordofan, Elobeid, Sudan.
[6]
Abualgasim Majdeldin Rahamtalla, Institute of Photogrammetry & Remote Sensing (IPF) Technische Universität Dresden, Dresden, Germany.
[7]
Osunmadewa Babatunde, Institute of Photogrammetry & Remote Sensing (IPF) Technische Universität Dresden, Dresden, Germany.
[8]
Csaplovics Elmar, Institute of Photogrammetry & Remote Sensing (IPF) Technische Universität Dresden, Dresden, Germany.
Accuracy assessment is one of the most important tools for quantifying how accurate the classification product is. The current paper tends to describe the accuracy assessment of land use land cover classification in Umabdalla natural reserved forest UNRF, South Kordofan State, Sudan. Multi-temporal satellite imagery from Land sat and ASTER covering the study area was obtained. Image preprocessing including radiometric and geometric correction, and image enhancement were done. ERDAS 9.1 software was used for supervised classification of land use land cover. Accuracy assessment was calculated based on confusion matrix and Kappa coefficient. The results of land use land cover in UNFR for period 1992 and 2000 showed over all classification accuracy 83.33% and 85% and overall Kappa Statistics 0.80 and 0.82, respectively. The same accuracy assessment was also scrod for supervised classification of Land use land cover in UNFR for ASTER 2005 and 2012. The results revealed excellent classification with over all accuracy 82.02% and 85.42% and over all Kappa statistics of 0.788 and 0.828, respectively. However the results of accuracy assessment of supervised classification of land use land cover classes in UNRF in all years showed excellent classification for the majority of classes. The study concluded that accuracy assessment is one of the most important tools for quantifying how accurate the classification product is, more over confusion error matrix and Kappa coefficient were very efficient in the calculation of accuracy assessment.
Accuracy Assessment, Kappa Statistics, Natural Forest, South Kordofan
[1]
Adam, H. E., (2011). Integration of Remote Sensing and GIS in Studying Vegetation Trends and Conditions in the Gum Arabic Belt in North Kordofan, Sudan, PhD thesis, TU Dresden, Germany.
[2]
Banko, G.(1998). A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data and of Methods Including Remote Sensing Data in Forest Inventory, International Institute for Applied Systems Analysis, A-2361 Laxenburg. Austria INTERIM REPORT IR-98-081 /November 1998.
[3]
Congalton, R. G. and Green, K. (1999). Assessing the accuracy of remotely sensed data: principles and practices. Lewis Publishers.
[4]
Ewing B., Hillier L., Wendl M. C., and Green P., (2017). Base-Calling of Automated Sequencer Traces Using Phred. I. Accuracy Assessment, Downloaded from genome.cshlp.org on July 10, 2017 - Published by Cold Spring Harbor Laboratory Press ISSN 1054-9803/98.
[5]
FNC (1999). Umabdalla Forest Reserve Inventory. Kordofan Technical Sector. Fordland Castañeda, Christel Palmberg-Lerche and Petteri Vuorinen, May 2001. Forest Management Working Papers, Working Paper 5.
[6]
Foody, G. M., (2002). Status of land cover classification accuracy assessment, Remote Sensing of Environment 80: 185-201.
[7]
Foody, G. M., (2008) Harshness in image classification accuracy assessment. International Journal of Remote Sensing, 29 (11). pp. 3137-3158. ISSN 0143-1161.
[8]
Landis j., Koch G., (1977). The measurement of observer agreement for categorical data. Biometrics 33: 159-174.
[9]
Mather, P. M. (2009). Computer processing of remotely-Sensed images; an introduction. (4rd ed) The University of Nottingham. John Wiley and Sons Ltd.
[10]
Pontius, R. G. (2000). Quantification error versus location error in comparison of categorical maps. Photogrametric Engineering and Remote Sensing, 66(8): 1011-1016.
[11]
Rao K. V. G., P. Chand P., Murthy M. V. R., (2011). Image classification using content based image Retrieval system, International Journal of Image Processing and Applications, 2(1), 2011, pp. 85-91.
[12]
Rosenfield, G. and Fitzpatrick-Lins, K. (1986) A coefficient of agreement as a measure of thematic classification accuracy. Photogrammetric Engineering and Remote Sensing, 52(2):223–227.
[13]
Skidmore, A. K. (1999). Accuracy assessment of spatial information. In: Stein, A. van der Meer, F. and Gorte. B. (ed.). Spatial statistics for remote sensing Dordrecht, Kluwer Academic Publishers, Netherlands.
[14]
Story, M. and Congalton, R. G. (1986). Accuracy assessment: a user’s perspective. Photogrammetric Engineering and Remote Sensing, 52 (3): 397-399.
[15]
Tortosa, D. J. J. (2000). htt://hosting.soonet.Ca/eliris/remote sensing/b/130intro.htm.
[16]
Wilkie, D. S. and Finn, J. T. (1996). Remote sensing imagery for natural resources Monitoring. A guide for first-time users. Methods and cases in conservation science Series. New York, Chichester: Columbia University Press.
