News and Recent Publications
- Our METEOR paper, i.e., “Meta-learning to address diverse Earth observation problems across resolutions” was published at Nature Earth & Environment. We train a meta-learning model to adapt to few-shot remote sensing problems across different spectral, spatial resolutions.
- We investigate location encoding in “Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks”, which was selected as spotlight (top 5%!) at the International Conference on Learning Representations (ICLR)
- I am the main organizer of the second Machine Learning for Remote Sensing (ML4RS) workshop at ICLR 2024. See you in Vienna, May 11th!
Short Bio
Marc Rußwurm is Assistant Professor of Machine Learning and Remote Sensing at Wageningen University. His background is in Geodesy and Geoinformation, and he obtained a Ph.D. in Remote Sensing Technology at TU Munich. During his Ph.D., he could visit the European Space Agency and the University of Oxford as a participant in the Frontier Development Lab in 2018, the Obelix Laboratory in Vannes, and the Lobell Lab in Stanford. As a postdoctoral researcher, he joined the Environmental Computational Science and Earth Observation Laboratory at EPFL, Switzerland. His research interests are developing modern machine learning methods for real-world remote sensing problems, such as classifying vegetation from satellite time series and detecting marine debris in the oceans. He is interested in domain shifts and transfer learning problems naturally arising from geographic data.
Community Engagement
I am active in the IAPR Thematic Committee 7 Remote Sensing & Mapping and the ISPRS TC2 Working Group 5 (TCII-WG5)
Recent Talks and Presentations
A selected list of recent talks and presentations. For a full list see this doc
-
Invited Talk
LifeCLEF 2023 Workshop at ImageCLEF
-
Panel discussion on Resource Efficient Machine Learning
Climate Change AI Workshok at the International Conference on Learning Representations (2023) in Kigali, Rwanda.
-
Marine debris detection with Sentinel-2 and Deep Segmentation Models
Visit Geoforschungszentrum (GFZ) Potsdam. 17.05.2023
-
Mapping crop type at large scale in Europe
Guest Speaker (virtual). Mila/McGill Montreal. Course COMP767. 15.02.2023
-
Guest Lecture on Interpretability of Time Series Models at the Univerisity of Bonn
University of Bonn. Geodesy Department. 19.10.2022
Teaching
A list of recent teaching activities
- WUR Advanced Earth Observation (GRS-32306) Period 3, lecture on Marine Applications
- WUR Machine Learning (FTE 35306) Period 4, lecture on Random Forests, coordination of projects.
- WUR Deep Learning (GRS-34806) Period 5, Lectures on regularization with CNNs and Segmentation
- IGARSS 2023 Tutorial part on Time Series [(link))](http://rhaensch.de/igarss23.html)
- EPFL CORE Course (ENV-408) lecture on Linear Regression
- EPFL IPEO Course (ENV-540) Exercises on deep learning for remote sensing.
- ISPRS 2022 Tutorial on Time Series
Selected Publications
A full list of publications available via google scholar
- Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks
- Large-scale detection of marine debris in coastal areas with Sentinel-2
- End-to-end learned early classification of time series for in-season crop type mapping
- Self-attention for raw optical satellite time series classification
- Meta-learning for few-shot land cover classification
Apps and Links
Some projects, I work(ed) on.