Machine learning emulation of precipitation from km-scale UK regional climate simulations using a diffusion model

TL;DR

This paper introduces a diffusion-based machine learning emulator that efficiently replicates high-resolution precipitation simulations from regional climate models, enabling cost-effective climate impact studies with realistic extreme event representation.

Contribution

The study presents a novel diffusion model-based emulator that downscales global climate model outputs to high-resolution precipitation, capturing convective effects and climate change features.

Findings

Emulator produces precipitation patterns similar to high-res CPM simulations.

It effectively captures extreme event statistics up to 100-year return times.

The method demonstrates transferability from perfect model training to real GCM inputs.

Abstract

High-resolution climate simulations are valuable for understanding climate change impacts. This has motivated use of regional convection-permitting climate models (CPMs), but these are very computationally expensive. We present a convection-permitting model generative emulator (CPMGEM), to skilfully emulate precipitation simulations by a 2.2km-resolution regional CPM at much lower cost. This utilises a generative machine learning approach, a diffusion model. It takes inputs at the 60km resolution of the driving global climate model and downscales these to 8.8km, with daily-mean time resolution, capturing the effect of convective processes represented in the CPM at these scales. The emulator is trained on simulations over England and Wales from the United Kingdom Climate Projections Local product, covering years between 1980 and 2080 following a high emissions scenario. The output precipitation has a similar spatial structure and intensity distribution as in the CPM simulations. The emulator is stochastic, which improves the realism of samples. We include some evidence about the emulator's skill for extreme events with return times up to ~100 years. We demonstrate successful transfer from a "perfect model" training setting to application using GCM variable inputs. It captures the main features of the simulated 21st century climate change, but exhibits some error in the magnitude. We also show that the method can be useful in situations with limited amounts of high-resolution data. Potential applications include producing high-resolution precipitation predictions for large-ensemble climate simulations and producing output based on different GCMs and climate change scenarios to better sample uncertainty.