Mapping vegetation communities of the Karkonosze National Park using APEX hyperspectral data and Support Vector Machines
Journal Title: Miscellanea Geographica - Regional Studies on Development - Year 2014, Vol 18, Issue 2
Abstract
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.
Authors and Affiliations
Anna Jarocińska, Bogdan Zagajewski, Adriana Marcinkowska, Edwin Raczko, Adrian Ochtyra, Premysl Stych, Lucie Kupková, Koen Meuleman
Keywords
Related Articles
- EP ID EP169512
- DOI 10.2478/mgrsd-2014-0007
- Views 89
- Downloads 0
Demographic types of small cities in Poland
The aim of the study was to determine the demographic types of all small cities in Poland in 2013 and to identify the standards of their spatial diversity. The following questions were posed: Which demographic types are...
GEOGRAPHICAL PATHS AS AN AUXILIARY DIDACTIC RESOURCE - A STUDY PROPOSAL
Didactic paths play a very important part in modern education, on the primary school level as well as at universities. Beside other things, they let students compare book knowledge with the real world. Unfortunately, the...
Local Tax Competition in Poland?
The concept of tax competition has been successfully applied in an analysis conducted in several European countries, but so far it has not been systematically tested either in Poland or in other countries of Central and...
UNUSUAL GRAPHIC SOLUTIONS AND THEIR PLACE IN CLASSIFICATION OF CARTOGRAPHIC PRESENTATION METHODS
Examples of unusual and unconventional graphic solutions which we can often find in the times of fast developing computer technology are discussed in the article. Many of them are suggested by various GIS programs, few o...
Traditional sectors based on natural resources – a blessing or a curse for less developed regions? A case study of Podlaskie Voivodeship
The natural environment, as a source of natural resources, has long been perceived as being a factor in determining the development of many states and regions, especially less developed areas. The main research question...