Anthropogenic land use and land cover change, e.g. due to deforestation, agricultural intensification, and urbanization, is one of the major drivers of global environmental change, with impacts on climate, carbon cycle, water resources and biodiversity. Besides these transformations, subtle changes in land use can have a significant impact on the ecosystem, e.g., due to agricultural intensification that results in habitat loss, cropland irrigation that leads to groundwater depletion, and the use of agrochemicals, which escape into non-agricultural ecosystems. Thus, understanding the spatial-temporal patterns of land cover and land use change as well as the underlying processes and drivers, support surveying compliances of international environmental treaties and will contribute to a more sustainable land management.

During the last decades the availability of remote sensing data increased and Earth Observation systems provide spatially distributed and temporally frequent data on land use and land cover. Particularly in context of global change issues and environmental policies, land cover classifications of remote sensing data are the most commonly used EO product. While most remote sensing applications are based on single source data sets and standard methods for image analysis, the availability of diverse Earth Observation data as well as sophisticated methods for data analysis increased during the last years. Our current research activities and outputs concentrate on advanced techniques in remote sensing and land use cover change analysis to support our understanding of coupled human-environment systems. A particular focus is the combination of multitemporal SAR and multispectral data, using advanced machine learning techniques.