Marc Rußwurm banner portrait

Short Bio

Marc Rußwurm is Emmy Noether Group Leader and Junior Professor at the University of Bonn (starting Sept 2026), focused on Geospatial Representation Learning and Learning Concept Maps in Neural Nets. He heads the Machine Learning in Earth Observation Laboratory, where he develops machine learning models for socio-economic and environmental analysis with Earth observation data. He currently supervises two PhD candidates working on vegetation modelling and distribution shifts in agriculture. Previously he was Assistant Professor at Wageningen University, and a postdoctoral researcher at EPFL, Switzerland. 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 collaborated with the European Space Agency and participated in the Frontier Development Lab at the University of Oxford. His research focuses on geospatial representation learning and machine learning in Earth observation with a fundamental methodological core through publications at ICLR, AAAI, ICML and in collaboration applications in agriculture, species mapping, and marine litter monitoring published in journals such as Remote Sensing of Environment, ISPRS Journal of Photogrammetry and Remote Sensing, Nature Earth & Environment.

News

Research

Research in the Machine Learning in Earth Observation Laboratory focuses on:

Further details are available on the MEO Lab research pages.

Teaching

University of Bonn

I will set up the following course at the University of Bonn.

  • Geospatial Representation Learning
  • Starting in Winter Semester 2026/2027 for MSc Geodesy and Mobile Robotics students

Wageningen University

I taught at Wageningen the following courses.

  • 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)