Grossflächige Klassifikation von Gebüschwald mit Fernerkundungsdaten

Abstract

Large-scale classification of shrub forest with remote sensing data Information on shrub forest distribution and development is important for a range of forestry- and ecologically-related questions, but current and area-wide datasets have been characterized by limited availability. In this study, the mapping of shrub forests dominated by green alder, mountain pine and hazel for the canton of Grison was investigated, based on available nationwide remote sensing data. Satellite data from Sentinel-1 and Sentinel-2, as well as a vegetation height and an elevation model were used. Training areas provided by the canton and supplemented by aerial imagery interpretation were used for a supervised classification with Random Forest, a decision tree-based machine learning algorithm. Independent validation of the results was carried out with data from the National Forest Inventory (NFI). Green alder and mountain pine forests were classified with high accuracy of 92.1% respectively 86.7%, whereas for hazel shrub forests, the internal model accuracy was only 66.7%. The resulting area expansion of the shrub forest was comparable with findings based on the NFI. A direct comparison with the NFI aerial imagery interpretation points revealed major discrepancies. The main reason for this is the different degree of spatial detail. However, NFI areas with a high percentage of shrubs were reliably classified as shrub forest. The method presented here underscores the potential of remote sensing data available throughout Switzerland for an essentially objective, costefficient and large-scale mapping of shrub forests with an accuracy applicable in practice.