CausalEarth is an interdisciplinary project, aiming to improve our understanding of the causal interdependencies between major drivers (modes) of climate variability by developing novel machine learning-based causal inference methods for both observations and model data. The modes’ interdependencies are characterized by common drivers, indirect effects, nonlinearities, nonstationarity, and all these between highly complex spatio-temporal phenomena. CausalEarth will develop causal inference methods that account for such complex characteristics and apply them to observational and climate model data to improve our understanding of the climate system and climate change.

IMIRACLI is a joint European PhD training network comprising a dozen institutions and industrial partners. The overall goal is to merge AI, machine learning and climate science to deliver a breakthrough in our understanding of the impact of aerosol-cloud interactions on climate. In the Causal Inference group the focus is on method development to address the problem of learning cause and effect relationships from observational data. These methods help to deepen our understanding of complex dynamical processes in the climate system such as the interactions of aerosols and clouds. There are two PhD projects involved, one on causal inference in the presence of multiple time scales and one on causal inference in the presence of latent variables.

XAIDA, an EU-funded project that started in September 2021, brings together the interdisciplinary expertise of a research consortium of 15 universities and research organizations. Our consortium unites experts in machine learning, statistics and climate modeling. Together we will design new methods and apply them to recent high-impact events to understand the role of climate change. Further, we will study if such events, or even more-intense ones, will occur in the future. We will collaborate with concerned stakeholders from different sectors to prepare risk assessment and adaptation strategies for extreme weather.

CausalFlood is a joint project between DLR and UFZ (Jakob Zscheischler). The overall goal is to understand which physical drivers cause floods which is crucial for flood forecasting and managing flood risk under changing environmental conditions. CausalFlood will advance the development of a state-of-the-art causal inference method to be tailored to the challenges related to causal inference of flood drivers.