The Causal Inference group develops theoretical foundations, algorithms, and accessible software tools for causal inference and machine learning and closely works with domain experts within DLR as well as national and international partners.
Causal inference is a challenging and promising research field and its application to domains such as climate science will have a high impact both to advance science and to address topics of critical importance for the society. The core methodological topics include causal inference and causal discovery for spatio-temporal dynamical systems, machine learning, deep learning, and nonlinear time series analysis.
The group is nationally and internationally well-connected within the machine learning and artificial intelligence community through the Europearn ELLIS network and partners in the US. Our methodological research is inspired by a plethora of collaborations within international research consortia with partners from climate science and many other fields.