Host
Peter Deuben (ECMWF)
Speaker
Markus Reichstein, born 1972 in Kiel, Germany, studied Landscape Ecology at the University of Münster; 1998-2003 research assistant at the University of Bayreuth (PhD in 2001), EU-Marie-Curie research fellow at the University of Tuscia (Italy, with research stays at the University of Montana and the University of California, Berkeley, USA) 2004 to 2006; from 2006 to 2012 Research Group Leader at the Max Planck Institute of Biogeochemistry, Jena.
Director of the Department of Biogeochemical Integration at the Max Planck Institute of Biogeochemistry in Jena since 2012 and Professor of Global Geoecology at the Friedrich Schiller University Jena since 2014. His research interests include data-driven Earth system science, the application of artificial intelligence/machine learning, global biogeochemical cycles, soils in the Earth system, and climate extremes and system resilience. In 2020 Markus Reichstein was awarded the Gottfried Wilhelm Leibniz Prize, in 2019 the ERC Synergy Grant USMILE. He is the 2018 award winner for the Piers J. Sellers Mid-Career Award of the American Geophysical Union (AGU) and received the Max Planck Research Award of the Alexander von Humboldt Foundation and Max Planck Society in 2013.
Abstract
The Earth is a complex dynamic networked system. Machine learning, i.e. derivation of computational models from data, has already made important contributions to predict and understand components of the Earth system, specifically in climate, remote sensing and environmental sciences. For instance, classifications of land cover types, prediction of land-atmosphere and ocean-atmosphere exchange, or detection of extreme events have greatly benefited from these approaches. Such data-driven information has already changed how Earth system models are evaluated and further developed. However, many studies have not yet sufficiently addressed and exploited dynamic aspects of systems, such as memory effects for prediction and effects of spatial context, e.g. for classification and change detection. In particular new developments in deep learning offer great potential to overcome these limitations.
Yet, a key challenge and opportunity is to integrate (physical-biological) system modeling approaches with machine learning into hybrid modeling approaches, which combines physical consistency and machine learning versatility. A couple of examples are given with focus on the terrestrial biosphere, where the combination of system-based and machine-learning-based modelling helps our understanding of aspects of the Earth system.