Forests fulfill many essential functions in the Earth system at different scales, from storing carbon to hosting diverse ecosystems. The vast amounts of remote sensing data captured over several decades, together with advances in machine learning methods, have enabled significant advances in forest monitoring.
However, improvements in the accuracy and interpretability of these methods are still needed to ensure they benefit scientists and decision makers. We aim to build machine learning approaches that are grounded in expert forestry knowledge and take decisions that are understandable by users.
Beyond extracting information from remote sensing data, we also strive to deepen our understanding of forest processes. At the local scale, we study alpine treeline dynamics in the Swiss Alps using historical aerial images. At a much larger scale, we investigate the drivers of deforestation in tropical regions.
Publications
- T.A. Nguyen, M. Rußwurm, G. Lenczner, and D. Tuia. Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning. Remote Sensing of Environment, 305, p.114109, 2024 (paper, github).
- J. Pišl, M. Rußwurm, L.H. Hughes, G. Lenczner, L. See, J.D. Wegner, and D. Tuia. Mapping drivers of tropical forest loss with satellite image time series and machine learning. Environmental Research Letters, 2024 (paper).
- N. van Tiel, F. Fopp, P. Brun, J. van den Hoogen, D.N. Karger, C.M. Casadei, L. Lyu, D. Tuia, N.E. Zimmermann, T.W. Crowther, and L. Pellissier. Regional uniqueness of tree species composition and response to forest loss and climate change. Nature Communications, 2024 (paper, github, data).
- T.A. Nguyen, B. Kellenberger, and D. Tuia. Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning. Remote Sensing of Environment, 281, p.113217, 2022 (paper, github).
