| ||Dr Sebastian Van der Linden
Humboldt-Universität zu Berlin, Geomatics Lab|
Tel: +49 30 2093 6872
Fax: +49 30 2093 6848
Sebastian van der Linden is a senior scientist at the Geomatics Lab of Humboldt-Universität zu Berlin. He is an Environmental Scientist with background in remote sensing, spatial analysis and geostatistics. His expertise is the analysis of hyperspectral and multisensoral imagery and the application of support vector machines for land cover/use classification. He has sound experience in field- and laboratory spectroscopy for the derivation of environmental and biophysical parameters and in image processing and GIS software.
Sebastian van der Linden received an M.Sc. degree in Applied Environmental Sciences from the University of Trier, Germany, in 2002 and the Ph.D. degree from Humboldt-Universität zu Berlin (HU), Germany, in January 2008. From 1999 to 2000, he studied at the University of Edinburgh, U.K. In 2006, he spent three months as a Visiting Scholar with the Lamont-Doherty Earth Observatory, Columbia University, New York.
Dr. van der Linden’s current scientific interests include the development, implementation and application of machine learning based approaches for qualitative and quantitative analysis of remote sensing imagery, especially imaging spectroscopy data. His research is closely linked to the planned German hyperspectral satellite mission EnMAP and he coordinates the development of the EnMAP-Toolbox. Together with Andreas Rabe and other colleagues at the Geomatics Lab of HU he conceptualized and implemented the imageSVM software for user-oriented support vector classification of remote sensing imagery. In 2007 Sebastian van der Linden participated in the ESA-funded field campaign CEFLES-2 in southern France and subsequent analyses of field measurements.
Activities in education:
Sebastian van der Linden has several years of teaching experience at bachelor and master level. Classes taught in German and English include:
- Introduction to Remote Sensing (Lecture and Seminar)
- Introduction to Digital Image Processing (Seminar)
- Advanced Image Processing (Seminar)
- Hyperspectral Image Processing (Seminar)
- Remote Sensing of Vegetation Parameters (Field Seminar and Study Project)
- Mapping Climate Variables with Geostatistics (Seminar)
- Introduction to Statistics (Lecture and Seminar)
He currently coordinates and/or participates in the following projects at HU’s Geomatics Lab:
EnMAP Core Science Team – Monitoring Ecosystem Transition. The project is on the analysis of gradual changes and the dynamics of different ecosystems and their services, which are frequently subject to conflicts of use and are thus not directly assigned to individual land use classes, a particular ecosystem or a scientific discipline. In its content, this research links with that of other Core Science Team members and can be broken down into the following key focus areas, such as: ecology of (semi-)natural systems; land abandonment; forest disturbance; land degradation; urban to peri-urban gradients; etc. More information at www.enmap.org.
EnMAP-Box – Development of a Toolbox for the Processing and Analysis of Hyperspectral EnMAP Data. The EnMAP Box is a license-free and platform-independent software interface designed to process hyperspectral remote sensing data, and particularly developed to handle data from the EnMAP sensor.
Remote Sensing of Urban Ecology. The scientific focus of this DFG-funded project is to characterize the city of Berlin with imaging spectroscopy data. A special emphasis is put on the spatial distribution and the state of urban vegetation along the urban to peri-urban gradient. Vegetation is a key natural component within the urban ecosystem providing numerous regulating services, e.g., for urban climate. The project aims at developing a methodology to quantify vegetation along with built-up and impervious areas in universal and transferable approaches that will be needed once space-borne data is available.
Sebastian van der Linden is author and co-author of more than 60 publications, including peer reviewed journal papers (13), book chapters (3), edited books, reports and conference proceedings or abstracts. A full list of publications is available at www.hu-geomatics.de.
The five most relevant publications in the context of urban mapping are:
Waske, B., van der Linden, S., Benediktsson, J., Rabe, A., Hostert, P. (2010). Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data. IEEE Transactions on Geosciences and Remote Sensing, 48 (7), 2880-2889. [doi: 10.1109/TGRS.2010.2041784]
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. [doi:10.1016/j.rse.2009.09.012]
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. [doi:10.1016/j.rse.2009.06.004]
van der Linden, S., Janz, A., Waske, B., Eiden, M., Hostert, P. (2007). Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines. Journal of Applied Remote Sensing, 1, 013543. [DOI: 10.1117/1.2813466]
Schiefer, S.*, Damm, A., Hostert, P. (2006). Correcting brightness gradients in hyperspectral data from urban areas. Remote Sensing of Environment, 101, 25-37. [doi:10.1016/j.rse.2005.12.003]
*Please note that I have changed my last name from Schiefer to van der Linden in 2007.