Satellite Data Classification Accuracy Assessment Based from Reference Dataset

Authors: Mohd Hasmadi Ismail, Kamaruzaman Jusoff

Abstract:

In order to develop forest management strategies in tropical forest in Malaysia, surveying the forest resources and monitoring the forest area affected by logging activities is essential. There are tremendous effort has been done in classification of land cover related to forest resource management in this country as it is a priority in all aspects of forest mapping using remote sensing and related technology such as GIS. In fact classification process is a compulsory step in any remote sensing research. Therefore, the main objective of this paper is to assess classification accuracy of classified forest map on Landsat TM data from difference number of reference data (200 and 388 reference data). This comparison was made through observation (200 reference data), and interpretation and observation approaches (388 reference data). Five land cover classes namely primary forest, logged over forest, water bodies, bare land and agricultural crop/mixed horticultural can be identified by the differences in spectral wavelength. Result showed that an overall accuracy from 200 reference data was 83.5 % (kappa value 0.7502459; kappa variance 0.002871), which was considered acceptable or good for optical data. However, when 200 reference data was increased to 388 in the confusion matrix, the accuracy slightly improved from 83.5% to 89.17%, with Kappa statistic increased from 0.7502459 to 0.8026135, respectively. The accuracy in this classification suggested that this strategy for the selection of training area, interpretation approaches and number of reference data used were importance to perform better classification result.

Keywords: Image Classification, Reference Data, Accuracy Assessment, Kappa Statistic, Forest Land Cover

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1334223

References:

[1] Achard, F. and Estreguil, C. 1995. Forest classification of Southeast Asia using NOAA AVHRR data. Remote Sensing of Environment. 54(3):198-208.
[2] Fitzgerald,R.W and Lees,B.G. 1994. Assessing the classification accuracy of multi-sources remote sensing data. Remote Sensing of Environment, 47: 362-368.
[3] Foody,G.M. and Hill,R.A. 1996. Classification of tropical forest classes from Landsat TM data. International Journal of Remote Sensing,17(12):2353-2368.
[4] Franklin, J. 1993. Discrimination of tropical vegetation using SPOT MS data. Geocarto International. 8: 57-63.
[5] Franklin, S.E. 2001. Remote sensing for sustainable forest management. Lewis Publisher,New York,U.S.A;407p.
[6] Hartson,G.S. 1980. Neotropical forest dynamic. Biotopica, 12: 23-30.
[7] ]Hudson,W.D and Ramm,C.W. 1987. Correct formulation of the kappa coefficient of agreement. Photogrammetry Engineering and Remote Sensing, 53, (4): 421-422.
[8] Janssen, L. F. J., and F. J. M. Van Der Wel. 1994. Accuracy assessment of satellite derived land cover data: A review. Photogrammetric Engineering and Remote Sensing 60:419-426.
[9] Jensen,J.R. 1996. Introductory digital image processing. A remote sensing perspective.2nd Edition, Prentice Hall, Englewood, NJ.
[10] Kamaruzaman.J and Abdul Haye.S. 1993. Detection of logging disturbance using satellite imagery. Paper presented at The South East Asian Regional Conference on Education and Research in Remote Sensing, 28-30 June 19993, University Teknologi Malaysia, Skudai, Johor, Malaysia.15p.
[11] Kamaruzaman.j and Souza, G.D. 1997. Use of satellite remote sensing in Malaysia forestry and its potential. International Journal of Remote Sensing, 18, (1): 57-70.
[12] Khali,A.H. 2001. Remote sensing, GIS and GPS as a tool to support precision forestry practices in Malaysia. Paper presented at the 22nd Asian Conference on Remote Sensing, 5-9 November 2001, Singapore.5p.
[13] Landis,J.R. and Koch,G.C. 1987. The measurement of observer agreement for categorical data. Biometric, 33: 159-179.
[14] Lowell, K. 1994. A fuzzy surface cartographic representation for forestry based on voronoi diagram area stealing, Canadian Journal of Forest Resources, 24: 1970-1980
[15] Mohd Hasmadi, I and Kamaruzaman,J. 1999. Use of satellite remote sensing in forest resource management in Malaysia. Paper presented at Second Malaysian Remote Sensing and GIS Conference, 16-18 March, 1999, ITM Resort & Convention Centre, Shah Alam, Selangor, Malaysia. 24p.
[16] Mohd Hasmadi,I. 2000. Forest cover change detection and water yield relationship in Semenyih and Langat watershed using remote sensing technique. M. Sc. (Thesis), Universiti Putra Malaysia, Serdang, Selangor. 174p.
[17] Monserud,R.A.1990. Method for comparing global vegetation map. WP- 90-40 II ASA,Laxenburg.
[18] Paul,M. 1991. Computer processing of remotely sensed images: An introduction, Biddley Limited Publication.352p.
[19] Rosenfield, G.H and Fitzpatrick, L.K.1986. A coefficient of agreement as a measure of thematic classification. Photogrammetry Engineering and Remote Sensing, 52, (2): 223-227.
[20] Sodowski ,F.G. and Danjoy,W.A. 1980. Some observation on the utility of remote sensors for humid tropical forest. Paper presented at the 14th International Symposium on Remote Sensing of Environment, April 1980,Costa Rica, Brazil.3p.
[21] Stehman,S.V. 1997. Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment, 62:77-89.
[22] ]Story,M. and Congalton,R.G. 1986). Accuracy assessment: A users perspective. Photogrammetry Engineering and Remote Sensing, 52(3):397-399.
[23] Wilson,E.H. and Sader,S.A. 2002. Detection of forest harvest type using multiple dates of Landsat TM imagery. Remote Sensing of Environment, 80: 385-396
[24] Zailani, K. 2000. Timber inventory and volume estimation in Gunung Stong Forest Reserve using remote sensing technique. M.Sc. (Thesis), Universiti Putra Malaysia. 138p.