Mapping vegetation communities of the Karkonosze National Park using APEX hyperspectral data and Support Vector Machines

• Authors: Adriana Marcinkowska , Bogdan Zagajewski , Adrian Ochtyra , Anna Jarocińska , Edwin Raczko , Lucie Kupková , Premysl Stych , Koen Meuleman

Abstracts

EN

This research aims to discover the potential of hyperspectral remote sensing data for mapping mountain vegetation ecosystems. First, the importance of mountain ecosystems to the global system should be stressed due to mountainous ecosystems forming a very sensitive indicator of global climate change. Furthermore, a variety of biotic and abiotic factors influence the spatial distribution of vegetation in the mountains, producing a diverse mosaic leading to high biodiversity. The research area covers the Szrenica Mount region on the border between Poland and the Czech Republic - the most important part of the Western Karkonosze and one of the main areas in the Karkonosze National Park (M&B Reserve of the UNESCO). The APEX hyperspectral data that was classified in this study was acquired on 10th September 2012 by the German Aerospace Center (DLR) in the framework of the EUFAR HyMountEcos project. This airborne scanner is a 288-channel imaging spectrometer operating in the wavelength range 0.4-2.5 μm. For reference patterns of forest and non-forest vegetation, maps (provided by the Polish Karkonosze National Park) were chosen. Terrain recognition was based on field walks with a Trimble GeoXT GPS receiver. It allowed test and validation dominant polygons of 15 classes of vegetation communities to be selected, which were used in the Support Vector Machines (SVM) classification. The SVM classifier is a type of machine used for pattern recognition. The result is a post classification map with statistics (total, user, producer accuracies, kappa coefficient and error matrix). Assessment of the statistics shows that almost all the classes were properly recognised, excluding the fern community. The overall classification accuracy is 79.13% and the kappa coefficient is 0.77. This shows that hyperspectral images and remote sensing methods can be support tools for the identification of the dominant plant communities of mountain areas.

Keywords

EN

Hyperspectral data; APEX; Karkonosze National Park; mapping/ classification; vegetation communities

• Publisher: Wydział Geografii i Studiów Regionalnych Uniwersytetu Warszawskiego
• Journal: Miscellanea Geographica. Regional Studies on Development
• Year: 2014
• Volume: 18
• Issue: 2
• Pages: 23-29

Dates

published

2014

Contributors

author

Adriana Marcinkowska

• Department of Geoinformatics and Remote Sensing, Faculty of Geography and Regional Studies, University of Warsaw

author

Bogdan Zagajewski

• Department of Geoinformatics and Remote Sensing, Faculty of Geography and Regional Studies, University of Warsaw

author

Adrian Ochtyra

• Department of Geoinformatics and Remote Sensing, Faculty of Geography and Regional Studies, University of Warsaw
• College of Inter-Faculty Individual Studies in Mathematics and Natural Sciences, University of Warsaw

author

Anna Jarocińska

• Department of Geoinformatics and Remote Sensing, Faculty of Geography and Regional Studies, University of Warsaw

author

Edwin Raczko

• Department of Geoinformatics and Remote Sensing, Faculty of Geography and Regional Studies, University of Warsaw

author

Lucie Kupková

• Department of Applied Geoinformatics and Cartography, Faculty of Science, Charles University in Prague

author

Premysl Stych

• Department of Applied Geoinformatics and Cartography, Faculty of Science, Charles University in Prague

author

Koen Meuleman

• VITO - Centre for Remote Sensing and Earth Observation Processes

References

• Benediktsson, JA & Waske, B 2009, ‘Next Frontier for Classification Tools: SVM and Beyond, 3rd HYPER-I-NET School on Hyperspectral Imaging’, Data Processing: from hyperspectral images to information, Pavia. Available from: http://hyperinet.multimediacampus.it/images/Benediktsson.pdf>. [8-11 September 2009].
• Biuro Urządzenia Lasu i Geodezji Leśnej 2009. Available from: <http://www.buligl.pl/web/biuro-urzadzania-lasu-en/home>.
• Burges, CJC 1998, ‘A tutorial on support vector machines for pattern recognition, data mining and knowledge discovery’, Kluwer Academic Publishers, vol. 2, pp. 121-167.
• Camps-Valls, G, Gomez-Chova, L, Calpe-Maravilla, J, Martin- Guerrero, JD, Soria-Olivas, E, Alonso-Chorda, L & Moreno, J 2004, ‘Robust support vector method for hyperspectral data classification and knowledge discovery’, IEEE Transactions on Geoscience and Remote Sensing, vol. 42, no. 7, pp. 1530-1542.[Crossref]
• Chan, JCW, Beckers, P, Spanhove, T & Vanden Borre, T 2012, ‘An evaluation of ensemble classifiers for mapping Natura 2000 heathland in Belgium using spaceborne angular hyperspectral (CHRIS/Proba) imagery’, International Journal of Applied Earth Observation and Geoinformation, vol. 18, pp. 13-22.[WoS]
• Dalponte, M, Bruzzone, L & Gianelle, D 2008, ‘Fusion of hyperspectral and LIDAR Remote sensing data for classification of complex forest areas’, IEEE Transactions On Geoscience and Remote Sensing, vol. 46, no. 5, pp. 1416-1427.
• Delalieux, S, Somers, B, Haest, B, Kooistra, L, Mücher, CA & Vanden Borre, J 2010, ‘Monitoring heathland habitat status using hyperspectral image classification and unmixing’, Proceedings of the 2nd Whispers on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), IEEE GRSS, University of Iceland, Reykjawik, pp. 50-54.
• Dixon, B & Candade, N 2008, ‘Multispectral landuse classification using neural networks and support vector machines: one or the other, or both?’, International Journal of Remote Sensing, vol. 29, no. 4, pp. 1185-1206.
• Goetz, AFH 2009, ‘Three decades of hyperspectral remote sensing of the Earth: A personal view’, Remote Sensing of Environment, vol. 113, pp. S5-S16.[WoS]
• Gualtieri, JA & Cromp, RF 1998, Support vector machines for hyperspectral remote Sensing classification, Proceedings of the 27th AIPR Workshop’, Advances in Computer Assisted Recognition, pp. 221-232.
• Huang, C, Davis, LS & Townshend, JRG 2002, ‘An assessment of support vector machines for land cover classification’, International Journal of Remote Sensing, vol. 23 pp. 725-749.[Crossref]
• Itten, KI, Dell’Endice, F, Hueni, A, Kneubühler, M, Schläpfer, D, Odermatt, D, Seidel, D, Huber, S, Schopfer, J, Kellenberger, T, Bühler, Y, D’Odorico, P, Nieke, J, Alberti, E & Meuleman, K 2008, ‘APEX - the hyperspectral ESA airborne prism experiment’, Sensors, vol. 8, pp. 6235-6259.
• Kokaly, RF, Despain, DG, Clark, RN & Livo, KE 2003, ‘Mapping vegetation in Yellowstone National Park using spectral feature analysis of AVIRIS data’, Remote Sensing of Environment, vol. 84, pp. 437-456.
• Olesiuk, D, Bachmann, M, Habermeyer, M, Heldens, W & Zagajewski, B 2009, ‘Crop classification with neural networks using airborne hyperspectral imagery’, Roczniki Geomatyki, vol. VII, no. 32, pp. 107-112.
• Pal, M & Mather, PM 2004, ‘Assessment of the effectiveness of support vector machines for hyperspectral data’, Future Generation Computer Systems, vol. 20, no. 7, pp. 1215-1225.[Crossref]
• Pal, M & Mather, PM 2006, ‘Some issues in the classification of DAIS hyperspectral data’. International Journal of Remote Sensing, vol. 27, pp. 2895-2916.[Crossref]
• Szymura, TH, Dunajski, A, Aman, I, Makowski, M, & Szymura, M 2007, ‘The spatial pattern and microsites requirements of Abies alba natural regeneration in the Karkonosze Mountains’, Dendrobiology, vol. 58, pp. 51-57.
• Wojtuń, B, Żołnierz, L & Raj, A 2004, ‘Nowy operat ochrony ekosystemów nieleśnych Karkonoskiego Parku Narodowego, Geoekologické problémy Krkonoš’, Opera Corcontica, vol. 41, pp. 560-567.
• Zagajewski, B 2010, ‘Ocena przydatności sieci neuronowych i danych hiperspektralnych do klasyfikacji roślinności Tatr Wysokich’ (Assessment of neural networks and Imaging Spectroscopy for vegetation classification of the High Tatras), Teledetekcja Środowiska, vol. 43.
• Zagajewski, B & Sobczak, M 2003, ‘Field remote sensing techniques for mountains vegetation investigation’, Proceedings of the 3rd EARSeL Workshop on Imaging Spectroscopy, Oberpfaffenhofen, pp. 580-596.
• Zagajewski, B, Kozłowska, A, Krówczyńska, M, Sobczak, M & Wrzesień, M 2005, ‘Mapping high mountain vegetation using hyperspectral data’. EARSeL eProceedings, vol. 4, no. 1, pp. 70-78.

Identifiers

Biblioteka Nauki

2037399