Skip to main content

Deep learning for a better understanding of the Earth System?

Beijer Hall, The Royal Swedish Academy of Sciences Lilla Frescativägen 4A, Stockholm

Stockholm Seminar 21 August with Markus Reichstein, director of the Biogeochemical Integration Department at the Max-Planck Institute for Biogeochemistry, Jena.

Arranged by: 
Stockholm Seminars and AI Innovation of Sweden

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, where the combination of system-based and machine-learning-based modelling helps our understanding of aspects of the Earth system.

About Markus Reichstein
Markus Reichstein is director of the Biogeochemical Integration Department at the Max-Planck Institute for Biogeochemistry, Jena, Professor for Global Geoecology at the FSU Jena, and Director at the Michael-Stifel-Center Jena for Data-driven and Simulation Science in Jena.

His main research interests include the effect of climate variability/extreme and change on global ecosystems, in particular carbon and water cycles. He and his research group tackle these topics by combining experimental, ground- and satellite-based observations with machine-learning based data-driven and process-oriented system models in a model-data integration approach. Prof. Reichstein has authored >185 publications and has been part of the iLEAPS/IGBP Scientific Steering Committee, and lead author of the IPCC special report on Climate Extremes (SREX).

Currently he is serving as member of the Thuringian panel on climate change, and chairing the Future Earth/IRDR/WCRP Knowledge Action Network “Extreme events and emergent Risks”. In 2013 he was awarded with the Max-Planck Research Award by the Alexander von Humboldt foundation, and in 2018 the Piers J Sellers mid-career award on Global Environmental Change by the American Geophysical Union.

Read more and sign up here