Our research follows a high-risk / high-gain approach. We work highly interdisciplinary and make best use of Data Science (Artificial intelligence / machine learning) for Earth observation data, having in mind grand challenges of society via our covered application fields, ultimately contributing to the Digital Twin of Earth.
So, who is ML4Earth?
Machine Learning for Earth observation (ML4Earth) is a new national center of excellence lead by the Technical University of Munich (TUM). The center is resting on a collaboration of competitive partners, including the German Aerospace Center’s Remote Sensing Technology Institute, The Alfred Wegener Institute, and the Universities of Potsdam, Leipzig, and Bristol. We conduct research at the highest level and develop novel Artificial Intelligence (AI) methods, applied to Earth observation (EO) satellite data. By contributing to the European mission of building a Digital Twin of Earth, we tackle a grand challenge of our time: climate change and its consequences for our environment and society.
ML4Earth is also engaging in building the international AI4EO community to foster collaborative thinking and knowledge exchange.
Data Science Methods
Data Science Methods used and developed as part of ML4Earth:physics-aware machine learning, reasoning, uncertainty estimation, explainable AI, sparse labels and transferability, as well as deep learning for complex data structures.
Immediate application fields
Immediate application fields around the Digital Twin of Earth: European water storage, permafrost thawing, sea level budget, climate and earth system modeling (for example climate tipping points), soil parameter mapping, and multi-sensor segmentation (identifying farmlands, urban areas, and other classes in EO images).
Why Us?
Our research follows a high-risk / high-gain approach. We work highly interdisciplinary and make best use of Data Science (Artificial intelligence / machine learning) for Earth observation data, having in mind grand challenges of society via our covered application fields, ultimately contributing to the Digital Twin of Earth.
Our unique selling point is our profound expertise in AI and data science in Earth observation. We pioneer the development of novel AI methods for big Earth observation data and form one of the leading research centers worldwide in that field. The research community can benefit from our expertise by attending our workshops or using benchmark datasets that we provide.
OUR VISION
By conducting research at the highest international level, we aim at consolidating our leading role in the European AI4EO community, at further building and strengthening that community, and at tackling the global challenges of our Earth System.
OUR mission
- We develop novel AI methods for big EO data that are inevitable for realizing the European mission of a Digital Twin of Earth.
- We focus on six fundamental tasks in machine learning for Earth Observation that create immediate benefits in six Digital-Twin-Earth-related application fields.
- We democratize AI in Earth observation among developers within science, economy, and authorities and in close coordination with the DLR space agency. In particular, we share benchmark datasets to be used by the community and organize workshops and hackathons to train the community.