Using An Explicit Multi-Feature Decision Tree For Wetland Information Extraction In Qomolangma National Nature Reserve

The Qomolangma National Nature Reserve (QNNR) has complex geomorphological characteristics of the high altitude Tibetan Plateau and aunique plateau wetland environment. In order to extract the wetland information effectively and accurately, this research utilizes an explicit decision tree (DT) classification strategy that incorporates multiple feature nodes by using the Landsat-8 OLI imagery as the main data source to interpret the spectral signatures and spatial distribution of the wetlands, and to construct acomprehensive DT classification process for wetland information extraction in QNNR. The multiple feature nodes include snow cover, non-wetland distribution, normalized difference vegetation index (NDVI), normalized difference water index (NDWI), digital elevation model (DEM), land surface temperature (LST) and slope. This strategy produces amore accurate wetland classification in QNNR where there are various interfering factors such as snow, mountain shadows, mineralized regions, grassland and woodland. The method is straightforward and easy to implement. Its classification result has an overall accuracy of 92.75%. This method could be applied to the plateaus with vertical-step ecosystems.