Urban vegetation classification: Benefits of multitemporal RapidEye satellite data

Abstract

Global climate change and sustained urban growth have increased the necessity of assessing the role that urban vegetation plays in urban dwellers' lives, as well as in urban ecosystem services. Urban environmental studies, however, still lack methods to characterize urban vegetation with adequate detail and across large areas. To remedy this gap, we apply a Support-Vector-Machine approach to classify eight frequent tree genera in the capital city of Berlin, Germany. We investigate different spectral and temporal band combinations of five RapidEye images acquired during the 2009 phenological season, and use ancillary surface and terrain models for orthorectification and improved tree masking. Results show that intra-annual time-series of RapidEye data can be used for high-precision tree genera classification in an urban environment. Differences within RapidEye time-series correlate well with empirical phenological studies of different tree genera, and RapidEye's red-edge band supports class separability. Further assessment is needed on the individual tree level and mixed stands regarding the quality of mapping urban individual trees, as our sampling approach mainly focused on larger stands with only a single tree genus. Urban applications will benefit from multitemporal RapidEye data, which offers area-wide monitoring and allows in-depth vegetation analysis to augment existing assessments. Such information is indispensable for assessing differences in urban ecosystem services related to carbon storage, cooling or air filtering, all of which differ between tree species. Therefore, the importance of in-depth analyses of urban vegetation cannot be underestimated in today's context of climate change.