Team · Research Staff
Henry Addison
Senior Research Associate
Jan 2022 – present
My research is in the field of AI for climate science. I am studying the use of machine learning to complement dynamical downscaling with cheaper methods to generate high-resolution climate projections. I am also interested in how to ensure these methods benefit producers and consumers of projection datasets.
For my PhD, I developed CPMGEM (Convection-Permitting Model Generative EMulator), an application of a generative machine learning model, a diffusion model, that skilfully emulates a convection-permitting model. This achieves similar results on England and Wales domain at daily timescales to dynamical downscaling at a fraction of the computational cost compared to the Met Office’s CPM.
Projects
- CHAI Funded project
Using diffusion models to enhance coarse, health-relevant climate model data to 2.2–5 km, 3-hourly resolution over the UK climate, so that we can better understand how extreme weather affects health, particularly maternal health and hospitalisation.