Short Bio

Marc Rußwurm is a Junior Research Group Leader of the MEO-lab at the University of Bonn. He was previously 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 visited the European Space Agency and the University of Oxford as a participant in the Frontier Development Lab (2018), and conducted research stays at the Obelix Laboratory in Vannes and the Lobell Lab at Stanford. As a postdoctoral researcher, he joined the Environmental Computational Science and Earth Observation Laboratory at EPFL, Switzerland. His research focuses on modern machine learning for Earth observation, with an emphasis on geospatial representation learning and Earth Embeddings. He develops methods that enable robust, transferable analysis of geospatial data and applies them to challenges such as agriculture, species mapping, and marine litter monitoring, with a particular interest in domain shifts and transfer learning in geographic settings.

News and Recent Publications

  • I start the MEO-Lab as new Junior Research Group Leader at the Institute of Food and Resources Economics at the University of Bonn in February 2026
  • The fourth Machine Learning for Remote Sensing (ML4RS) workshop at ICLR was accepted and will take place in Rio in April 2026.
  • Our paper on “SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery” was accepted for publication at AAAI 2025. arXiv

Selected Publications

A full list of publications available via google scholar

Teaching

I regularly teach in the following courses at Wageningen University.

  • Advanced Earth Observation (GRS-32306)
  • Machine Learning (FTE-35306)
  • Deep Learning (GRS-34806)

Academic CV

For a detailed list of talks, teaching activities, community engagement, and publications, please see my Academic CV

Apps and Links

Some projects, I work(ed) on.

SatCLIP - A pre-trained location encoder to express different geographic locations in vectors.
Siren(SH) LocationEncoders - A large comparative study of location encoders and the proposition of using Siren with Spherical Harmonic basis functions.
BreizhCrops - A benchmark dataset for crop type mapping.
Beat The MAML - An interactive interfact for few-shot land cover classification.
Marine Debris Explorer - An interactive Earthengine app to compare the performance of different marine debris detectors.
TSLearn - A machine learning library for time series. (minor contributions while working on ELECTS)