Towards accurate extreme event likelihoods from diffusion model climate emulators

TL;DR

This paper demonstrates how diffusion model climate emulators can estimate the likelihood of extreme atmospheric events like Tropical Cyclones, enabling probabilistic analysis and importance sampling for better climate risk assessment.

Contribution

It introduces a method to use probability density estimates from diffusion models to quantify and compare the likelihood of extreme events under different guidance conditions.

Findings

Guided diffusion models can estimate the likelihood of Tropical Cyclones.

Likelihood ratios enable importance sampling to improve probability estimates.

Early results suggest potential for probabilistic climate event attribution.

Abstract

ML climate model emulators are useful for scenario planning and adaptation, allowing for cost-efficient experimentation. Recently, the diffusion model Climate in a Bottle (cBottle) has been proposed for generation of atmospheric states compatible with boundary conditions of solar position and sea surface temperatures. Crucially, cBottle can be guided to generate extreme events such as Tropical Cyclones (TCs) over locations of interest. Diffusion models such as cBottle work by approximating the probability density of the training data. Here, we show use cases of the probability density estimates of atmospheric states obtained from this climate emulator. Most importantly, these estimates allow us to calculate likelihoods of extreme events under guidance. When guiding the model towards states including TCs, comparing the probability density under the guided and unguided model enables us to quantify how much more likely the guidance has made the TC. We show how these odds ratios allow us to importance-sample from the TC distribution, reducing the standard error of the probability estimate compared to simple Monte Carlo sampling. Furthermore, we discuss results and limitations of the application of model probability densities to extreme event attribution-like experiments. We present these early but encouraging results hoping they will spur more research into probabilistic information that can be gained from diffusion models of the atmosphere.