Advertisement

Hydrobiologia

, Volume 661, Issue 1, pp 85–96 | Cite as

Accuracy assessment of supervised classification of submersed macrophytes: the case of the Gavaraget region of Lake Sevan, Armenia

  • T. K. AgyemangEmail author
  • J. Heblinski
  • K. Schmieder
  • H. Sajadyan
  • L. Vardanyan
LAKE SEVAN

Abstract

The necessity of assessing the accuracy of spatial data derived from remote sensing methods and used in geographic information system (GIS) analyses has been regarded as a critical component of many projects. In this article, supervised classified QuickBird satellite imageries of submersed macrophytes of the Gavaraget region of Lake Sevan (Armenia) during 2006–2008 are validated in a GIS environment. The results of this assessment are represented by error matrices presenting the overall accuracy, the user and producer accuracies in each category, as well as the kappa coefficients. The assessments were done at three levels: the vegetation types, the growth (vertical) type, and the species levels. At the vegetation level, an overall accuracy of more than 86% was achieved in 2006 and 2007, while that in 2008 was about 72%. Substantial agreements were achieved between the classified remote sensing data and the reference (groundtruth) data for both 2006 and 2007. Only a fair agreement was attained in 2008. The kappa coefficients ranged from 0.39 to 0.89. At the growth type level, only the 2006 classification attained a substantial agreement, with an overall accuracy of 80%. The 2007 and 2008 classifications had above average and average overall accuracies of 72 and 64%, respectively. The kappa coefficient had a lowest value of 0.35 and a highest value of 0.70 at the growth type level. At the species level, Chara spp. or Zannichellia palustris and Potamogeton pectinatus had high user accuracies of more than 90% and a high overall accuracy of 82% in 2006. High user accuracies (>80%) occurred for P. pectinatus (for 2007 and 2008) and No Vegetation (for 2007). The remaining species, however, had low user and producer accuracies of less than 64%. The kappa coefficients ranged between 0.36 and 0.73 at the species level.

Keywords

Submersed macrophytes Lake Sevan GIS Accuracy assessment Supervised classification Error matrix 

Notes

Acknowledgments

We would like to express our sincere thanks to the VW Foundation for sponsoring this research project.

References

  1. Babayan, A., S. Hakobyan, K. Jenderedjian, S. Muradyan & M. Voskanov, 2005. Lake Sevan: Experience and Lessons Learned Brief. Lake Basin Management Initiative (LBMI). ILEC Foundation. Otsu Shigyo, Otsu, Japan: 347–362.Google Scholar
  2. Chilingaryan, A. L., B. P. Mnatsakanyan, K. A. Aghababyan & H. V. Toqmagyan, 2002. Hydrology of Rivers and Lakes of Armenia. Yerevan, Armenia.Google Scholar
  3. Cohen, J., 1960. A coefficient of agreement for nominal scales. Educational and Psychological Measurement 20(1): 37–46.CrossRefGoogle Scholar
  4. Congalton, R. G., 1991. A review of assessing the accuracy of classification of remotely sensed data. Remote Sensing of Environment 37: 35–46.CrossRefGoogle Scholar
  5. Congalton, R. G., 2004. Putting the map back in map accuracy assessment. In Lunetta, R. S. & J. G. Lyon (eds), Remote Sensing and GIS Accuracy Assessment. CRC Press LLC, Florida: 1–12.Google Scholar
  6. Congalton, R. G. & K. Green, 1999. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. CRC Press Inc., Florida.Google Scholar
  7. Congalton, R. G., R. G. Oderwald & R. A. Mead, 1983. Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. Photogrammetric Engineering & Remote Sensing 49: 1671–1678.Google Scholar
  8. Deheryan, S., 2005. Rising interests: welcomed increase in water level recorded at Lake Sevan. ArmeniaNow.com 38(160) [available on internet at http://www.armenianow.com/?action=viewArticle&AID=1125&CID=1318&IID=1041&lng=eng Accessed: March 2007 (14/03/2007 11:02 CET)].
  9. DigitalGlobe, 2009. DigitalGlobe constellation: QuickBird imaging satellite [available on internet at http://www.digitalglobe.com/file.php/515/QuickBird_Datasheet_web.pdf. Accessed: August 2009 (25/08/2009 13:34 CET)].
  10. Environmental Systems Research Institute (ESRI), 2004. ArcGIS Desktop Help: ArcMap-Making Field Calculations. ESRI, Redlands, CA.Google Scholar
  11. Garibyan, M., 2007. In T. K. Agyemang (ed.), Lake Sevan Water Levels. Hydrometeorological Agency, Ministry of Nature Protection, Sevan, Armenia.Google Scholar
  12. Heblinski, J., T. K. Agyemang, K. Schmieder, H. Sajadyan & L. Vardanyan, 2008. Sevan Management Information System (SEMIS) Project Report, Stuttgart.Google Scholar
  13. Jensen, J. R., 1996. Introductory Digital Image Processing: A Remote Sensing Perspective. Prentice Hall, Upper Saddle River, NJ.Google Scholar
  14. Kalff, J., 2002. Limnology: Inland Water Ecosystems. Prentice Hall, Upper Saddle River, NJ.Google Scholar
  15. Kohler, A. & G. A. Janauer, 1995. Zur Methodik der Untersuchung von aquatischen Makrophyten in Fließgewässern. Handbuch angewandte Limnologie: Grundlagen; Gewässerbelastung; Restaurierung; aquatische Ökotoxikologie; Bewertung; Gewässerschutz. C. Steinberg, Bernhardt, H., Klapper, H. Landsberg am Lech, Ecomed.Google Scholar
  16. Landis, J. R. & G. G. Koch, 1977. The measurement of observer agreement for categorical data. Biometrics 33: 159–174.CrossRefPubMedGoogle Scholar
  17. Markosyan, A. & G. Nazaryan, 2003. Monitoring of Water Resources. Luys, Yerevan.Google Scholar
  18. Munoz, S. R. & S. I. Bangdiwala, 1997. Interpretation of kappa and B statistics measures of agreement. Journal of Applied Statistics 24(1): 105–111.CrossRefGoogle Scholar
  19. Northcote, T. G. & D. Y. Atagi, 1997. Ecological Interactions in the flooded Littoral Zone of Reservoirs: The Importance and Role of Submerged Terrestrial Vegetation with Special Reference to Fish, Fish Habitat and Fisheries in the Nechako Reservoir of British Columbia, Canada: 71.Google Scholar
  20. Sim, J. & C. C. Wright, 2005. The kappa statistic in reliability studies: use, interpretation, and sample size requirements. Physical Therapy 85(3): 257–268.PubMedGoogle Scholar
  21. Stehman, S. V., 1997. Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment 62: 77–89.CrossRefGoogle Scholar
  22. Stehman, S. V. & R. L. Czaplewski, 1998. Design and analysis for thematic map accuracy assessment: fundamental principles. Remote Sensing of Environment 64: 331–334.CrossRefGoogle Scholar
  23. Story, M. & R. G. Congalton, 1986. Accuracy assessment: a user’s perspective. Photogrammetric Engineering & Remote Sensing 52(3): 397–399.Google Scholar
  24. Viera, A. J. & J. M. Garrett, 2005. Understanding interobserver agreement: the kappa statistic. Family Medicine 37(5): 360–363.PubMedGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • T. K. Agyemang
    • 1
    Email author
  • J. Heblinski
    • 1
    • 4
  • K. Schmieder
    • 1
  • H. Sajadyan
    • 2
  • L. Vardanyan
    • 3
  1. 1.Institute of Landscape & Plant EcologyUniversity of HohenheimStuttgartGermany
  2. 2.State Agrarian UniversityYerevanArmenia
  3. 3.Department of BiologyUniversity of VenevanMartuniArmenia
  4. 4.EOMAP GmbH & Co. KGGilchingGermany

Personalised recommendations