Research interests

My main research interests focus on combining data-driven machine learning approaches with physics-based weather and climate models. As part of my PhD, I work with deep learning methods from computer vision and image processing to improve numerical weather predictions of rainfall extremes and applications of generative models to climate projections.

Publikationen 2022

Philipp Hess, Markus Drüke, Stefan Petri, Felix M. Strnad, Niklas Boers: Physically constrained generative adversarial networks for improving precipitation fields from Earth system models. Nature Machine Intelligence volume 4, pages828–839

P. Hess, N.Boers: Deep Learning for Improving Numerical Weather Prediction of Rainfall Extremes, in revision at Journal of Advances in Modelling Earth Systems 14