# Marieke Wesselkamp
**Source**: https://www.biom.uni-freiburg.de/mitarbeiter/Marieke
**Parent**: https://www.biom.uni-freiburg.de/mitarbeiter/dormann/prof.-dr.-carsten-dormann?set_language=en
| | |
| --- | --- |
| | Marieke Wesselkamp [Department of Biometry and Environmental System Analysis](https://www.biom.uni-freiburg.de/) Tennenbacher Straße 4, 79106 Freiburg, Germany Room 03.063 phone: + fax: + 49 761 203-3751 Email: [marieke.wesselkamp@biom.uni-freiburg.de](mailto:marieke.wesselkamp@biom.uni-freiburg.de) |
## **Curriculum Vitae**
**2021-now**Postgraduate researcher, University of Freiburg.
| | | |
| --- | --- | --- |
| **2021** | | Research internship at the Max-Planck Institute (MPI) for Biogeochemistry, Model-Data Integration Group. Jena, Germany. |
| **2018-2021** | | MSc Environmental Sciences, Profile: Environmental Modeling and GIS applications. University of Freiburg Germany. Master's thesis: Process-guided transfer learning with sparse data. |
| **2018** | | Research internship at the University of York, Faculty of Biology, Department of Ecology and Evolution. York, United Kingdom. |
| **2013****-2018** | | BSc Geography, University of Freiburg, Germany. Bachelor thesis: Identifying ecotypes from climate data with spatially varying coefficients. |
| | | |
## **Publications**
- Wesselkamp, M., Roberts, D.R. & Dormann, C.F. Identifying potential provenances for climate-change adaptation using spatially variable coefficient models. *BMC Ecol Evo* **24**, 70 (2024). <https://doi.org/10.1186/s12862-024-02260-z>
- Wesselkamp, M., Moser, N., Kalweit, M., Boedecker, J., & Dormann, C. F. (2022). Process-guidance improves predictive performance of neural networks for carbon turnover in ecosystems. *arXiv preprint arXiv:2209.14229*. <https://doi.org/10.48550/arXiv.2209.14229> (submitted to: Ecology letters)
- Wesselkamp, M., Chantry, M., Pinnington, E., Choulga, M., Boussetta, S., Kalweit, M., ... & Balsamo, G. (2024). Advances in Land Surface Model-based Forecasting: A comparative study of LSTM, Gradient Boosting, and Feedforward Neural Network Models as prognostic state emulators. *arXiv preprint arXiv:2407.16463*. [arXiv:2407.16463v1](https://arxiv.org/abs/2407.16463v1) (submitted to: Geoscientific Model Developments)
##
| | | |
| --- | --- | --- |
| | | |
---