Marc Rußwurm
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.
Sessions
Earth Observation is entering an era of abundance—global satellite archives, growing in-situ networks, and an expanding open-source ecosystem—yet turning this distributed wealth into decision-ready environmental information remains difficult because data are heterogeneous, incomplete, and hard to combine across sensors, resolutions, and regions. This keynote outlines Earth Embeddings: compact, AI-native “mental maps” that summarize what makes a location unique by learning directly from imagery and context. Using an intuitive “Satellite GeoGuessr” contrastive training setup, neural networks learn place-specific visual and contextual signatures and distill them into dense vectors that can serve as portable location tokens in downstream models, enabling reuse across tasks and regions. This talk will give an overview over different strategies to generate embeddings and outline research gaps and steps forward towards global interoperable FAIR embeddings.