Dr. Sebastian van der Linden
Humboldt-Universität zu Berlin
Geography Department, Geomatics Lab
Unter den Linden 6, 10099 Berlin, Germany
Unter den Linden 6, 10099 Berlin, Germany
rsebastian.linden[at]hu-berlin.de
https://www.geographie.hu-berlin.de/en/professorships/geomatics
https://www.geographie.hu-berlin.de/en/professorships/geomatics
Background
Sebastian van der Linden is a senior scientist at the Geography Department of Humboldt-Universität zu Berlin (since 2010) and managing director of the university’s Integrative Research Institut on Transformations of Human-Environment Systems (IRI THESys). He has studied applied Environmental Sciences at Trier University, Germany, and the University of Edinburgh, UK. He holds a doctoral degree from Humboldt-Universität zu Berlin. In his research, he explores machine learning approaches for mapping complex environments from Earth Observation data. His doctoral studies aimed at mapping urban land cover from airborne imaging spectroscopy data with support vector machines (2004-2007). Based on this work, approaches for mapping land cover fractions in urban and semi-natural environments were developed using regression and adapted classification algorithms together with synthetic spectral training data. As part of the lab’s role as a member in the Science Advisory Group for the German EnMAP satellite mission (Environmental Mapping and Analysis Program) most of the work focused on the step from air- to spaceborne data, i.e. from 3-9 m to 30 m spatial resolution. Sebastian van der Linden leads the development of the EnMAP-Box, where several algorithms for imaging spectroscopy data are collected and implemented in standardized and user-friendly applications. In two current projects, capabilities of machine learning for multi-temporal analysis of imaging spectroscopy data (EnSAG project) and the cross-sensor transfer of regression models (UrbanEARS project) are explored.
Activities in education
Sebastian van der Linden has more than ten year experience in teaching remote sensing with a focus on imaging spectroscopy, remote sensing of vegetation and remote sensing of urban areas at bachelor and master level. He has been a lecturer at ESA’s Advanced Training Course in Land Remote Sensing in 2011 and the jointly organized Trans-Atlantic Training by ESA and NASA in Krakow, 2014. He has supervised two doctoral researchers and several bachelor and master students.
Recent projects
- UrbanEARS (PI, 2014-2017, funded by BelSPO, Belgium)
- EnMAP-Box development (PI, since 2008, funded by DLR/BMWi through GFZ Potsdam, Germany)
- EnMAP Science Advisory Group (Co-PI, since 2010, funded by DLR/BMWI, Germany)
For all proects see: http://www.hu-geomatics.de
IRI THESys at Humboldt-Universität zu Berin (Managing director, 2012-2017, DFG, Germany, www.iri-thesys.org)
Selected publications
- Okujeni, A., van der Linden, S., Hostert, P. (2015). Extending the Vegetation-Impervious-Soil model using simulated EnMAP data and machine learning. Remote Sensing of Environment, 158, 69-80.
- Griffiths, P., van der Linden, S., Kuemmerle, T., Hostert, P. (2013). A pixel-based Landsat compositing algorithm for large area land cover mapping. IEEE Journal of Selected Topics in Applied Remoste Sensing, 6, 2088-2101.
- Okujeni, A., van der Linden, S., Tits, L., Somers, B., Hostert, P. (2013). Support vector regression and synthetically mixed training data for quantifying urban land cover. Remote Sensing of Environment, 137, 184-197.
- Griffiths, P., Hostert, P., Gruebner, O., van der Linden, S. (2010). Mapping megacity growth with multi-sensor data. Remote Sensing of Environment, 114, 426-439.
- van der Linden, S., Hostert, P. (2009). The influence or urban surface structures on the accuracy of impervious area maps from airborne hyperspectral data. Remote Sensing of Environment, 113, 2298-2305.
See http://www.researcherid.com/rid/B-4516-2008 for full list of peer reviewed publications.
