Machine learning emulation of a local-scale UK climate model
This work addresses the need for efficient, high-resolution climate projections to model flooding impacts, representing an incremental advance by applying diffusion models to a specific domain.
The authors tackled the problem of generating high-resolution rainfall projections for the UK, which are computationally expensive with physics-based models, by using diffusion models to produce realistic samples cheaply from low-resolution simulation data, achieving good matches in quantiles and time-mean with high-resolution counterparts.
Climate change is causing the intensification of rainfall extremes. Precipitation projections with high spatial resolution are important for society to prepare for these changes, e.g. to model flooding impacts. Physics-based simulations for creating such projections are very computationally expensive. This work demonstrates the effectiveness of diffusion models, a form of deep generative models, for generating much more cheaply realistic high resolution rainfall samples for the UK conditioned on data from a low resolution simulation. We show for the first time a machine learning model that is able to produce realistic samples of high-resolution rainfall based on a physical model that resolves atmospheric convection, a key process behind extreme rainfall. By adding self-learnt, location-specific information to low resolution relative vorticity, quantiles and time-mean of the samples match well their counterparts from the high-resolution simulation.