Page Content
Prof. Dr. Birgit Kleinschmit
- © B. Kleinschmit
Head
Phone: +49 (0)30 / 314 - 72 84 7
Email: birgit.kleinschmit(at)tu-berlin.de
Room: EB 235a
Consultation hour: by arrangement
| Date and place of birth: 1973 (Münster, Westphalia, Germany) |
| 2011 | Announced as University Professor and Head of the Department of Geoinformation in Environmental Planning at the Institute of Landscape Architecture and Environmental Planning of the Berlin University of Technology |
| 2003-2011 | Assistant Professor (“Juniorprofessorin”) at the Department of Geoinformation Processing for Landscape and Environmental Planning of the Berlin University of Technology |
| 2001-2003 | Consultant and software developer, INTEND Geoinformatik GmbH, Kassel, Germany |
| 1998-2001 | Scientific staff member ("Wissenschaftliche Mitarbeiterin"), Georg-August-Universität, Göttingen, Department of Forest Assessment & Remote Sensing, Forest Growth, Forest Planning |
| 1993-1998 | Diploma study of forest science at the University of Göttingen |
| 2001 | Doctorate (doctor forest), Georg-August Universität Göttingen, Grade: magna cum laude |
| 1998 | Diploma, Georg-August Universität Göttingen, Grade: 1,9 (on a scale from 1 to 6, where 1 is highest) |
Research Topics
- Studying land use dynamics on different scales to understand natural and human environmental systems using geospatial information technologies (GIS & Remote Sensing)
- Modelling environmental changes and assessing the impacts on humans and ecosystems
- Knowledge-based combination of geoinformation and remote sensing data
- Evaluating of new sensor technologies
Important Functions, Awards, Honors
- Since 2019
Member of Scientific Advisory Board on Forest Policy at the Federal Ministry of Food and Agriculture - Since 2019
Research Transfer advisory board Member, TU Berlin - Since 2018
Deputy Director, Institute of Landscape Architecture and Environmental Planning, TU Berlin - Since 2015
Co-speaker of the DFG research training group Urban water interfaces - Since 2016
Admissions and Steering Committee member of the Berlin International Graduate School in Model and Simulation based Research (BIMoS), TU Berlin - 2012-2018
Leader of the Special Interest Group „Analysis of remote sensing data” of the German Association for Photogrammetry, Remote Sensing and Geoinformation - Since 2018
Member of the Commission for the Allocation of Doctoral Grants of Elsa Neumann Scholarships - Since 2010
Steering Committee member of Geo.X – Research Network for Geosciences in Berlin and Potsdam
Other Publications
| Citation key | Vulova2020 |
|---|---|
| Author | Vulova, S. and Meier, F. and Fenner, D. and Nouri, H. and Kleinschmit, B. |
| Pages | 1-15 |
| Year | 2020 |
| ISSN | 1939-1404 |
| DOI | 10.1109/JSTARS.2020.3019696 |
| Journal | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Volume | 562 |
| Abstract | Urban areas tend to be warmer than their rural surroundings, well-known as the “urban heat island” effect. Higher nocturnal air temperature (Tair) is associated with adverse effects on human health, higher mortality rates, and higher energy consumption. Prediction of the spatial distribution of Tair is a step towards the “Smart City” concept, providing an early warning system for vulnerable populations. The study of the spatial distribution of urban Tair was thus far limited by the low spatial resolution of traditional data sources. Volunteered geographic information (VGI) provides alternative data with higher spatial density, with citizen weather stations monitoring Tair continuously in hundreds or thousands of locations within a single city. In this study, the aim was to predict the spatial distribution of nocturnal Tair in Berlin, Germany, one day in advance at a 30- m resolution using open-source remote sensing and geodata from Landsat and Urban Atlas, crowdsourced Tair data, and machine learning (ML) methods. Results were tested with a “leave-onedate- out” training scheme (testingcrowd) and reference Tair data (testingref). Three ML algorithms were compared - Random Forest (RF), Stochastic Gradient Boosting (GBM), and Model Averaged Neural Network (avNNet). The optimal model based on accuracy and computational speed is RF, with an average RMSE for testingcrowd of 1.16 °C (R2 = 0.512) and RMSE for testingref of 1.97 °C (R2 = 0.581). Overall, the most Important GIS predictors were morphometric parameters and albedo. The proposed method relies on open-source datasets and can, therefore, be adapted to many cities worldwide. |
| Bibtex Type of Publication | Kleinschmit |
Zusatzinformationen / Extras
Quick Access:
Schnellnavigation zur Seite über Nummerneingabe
Auxiliary Functions
This site uses Matomo for anonymized webanalysis. Visit Data Privacy for more information and opt-out options.
Geoinformation in Environmental Planning Lab
Office EB5
Straße des 17. Juni 145
D - 10623 Berlin
Phone: +49 (0)30 314 - 73 29 0
Fax: +49 (0)30 314 - 23 50 7
e-mail query
Office EB5
Straße des 17. Juni 145
D - 10623 Berlin
Phone: +49 (0)30 314 - 73 29 0
Fax: +49 (0)30 314 - 23 50 7
e-mail query