Data-driven equation discovery of a sea ice albedo parametrisations + Machine Learning insights…

On June 16, our Storms, Eddies and Science Hour featured EERIE project scientists Diajeng Atmojo (University of Bremen) and Simon Michel (University of Oxford) speaking about “Data-driven equation discovery of …

Characterizing Uncertainty in Deep Convection Triggering Using Explainable Machine Learning

Realistically representing deep atmospheric convection is important for accurate numerical weather and climate simulations. However, parameterizing where and when deep convection occurs (“triggering”) is a well-known source of model uncertainty. …

Deep learning based reconstructions of the Atlantic meridional overturning circulation confirm twenty-first century decline

Gaining knowledge of the past and present variations of the Atlantic meridional overturning circulation (AMOC) is crucial for the development of accurate future climate projections. The short range covered by …

Atmospheric imprint of ocean eddies in high-resolution atmosphere-only simulations

Our April 2025 ‘Storms, Eddies and Science Hour’ features EERIE project scientist Matthias Aengenheyster talking about “Atmospheric imprint of ocean eddies in high-resolution atmosphere-only simulations”. Our joint WarmWorld + nextGEMs …

Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi-Member and Stochastic Parameterizations

Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here, we develop stochastic …