Hyperspectral data for classification of selected vegetation species above tree-line in the Krkonoše Mts. National Park

The paper is focused on the classification of vegetation above the tree-line in the Krkonoše Mts. National Park (KRNAP) using hyperspectral data (APEX). The vegetation above tree-line (altitude above 1350 m) is the unique ecosystem which is characterized by mosaic of subalpine meadows with Nardus stricta and Pinus mugo growths, subalpine peat-bog, rocks and another areas of the lichen tundra in the highest parts in the Krkonoše Mts. Studying of Pinus mugo and competitive strong grasses (Molinia caerulea and Calamagrostis villosa) expansion to the original meadows with Nardus stricta is very important issue for environmental protection. The aim of this study is to classify two species Nardus stricta and Calluna vulgaris spatial distribution in the western part of tundra in the Krkonoše Mts. National Park. Different classification methods (e.g. support vector machine, spectral information divergence or spectral angle mapper) are used and evaluated. The goal is to find best classification method providing the most accurate outputs. The detailed abundance maps of Nardus stricta and Calluna vulgaris are also produced.