Comparison of Multi- and Hyperspectral Remote Sensing Data for Use in Comprehensive Urban Biotope Mapping

We classified 922 urban biotopes from 11 different biotope types in a 50.6 km² study area in Berlin, Germany. As input advanced data products were derived from hyperspectral and simulated multispectral data. Urban surface materials were derived from the hyperspectral data by classification and linear spectral unmixing. Multispectral data was classified using four different per-pixel and object-oriented classifiers. The results show that our developed method for biotope classification works well with hyperspectral and with multispectral input data yielding comparable overall accuracies of 88.1 and 91.3 percent.