Latent Diffusion Model for Generating Ensembles of Climate Simulations

TL;DR

This paper introduces a novel deep learning approach combining a variational autoencoder and a diffusion model to efficiently generate large climate simulation ensembles, improving uncertainty quantification with reduced computational resources.

Contribution

The paper presents a new generative model for climate ensembles that reduces computational costs by using latent space representations and a diffusion process.

Findings

Achieves good agreement with original climate ensembles in variability.

Enables rapid, memory-efficient generation of large climate simulation ensembles.

Improves efficiency of uncertainty quantification in climate modeling.

Abstract

Obtaining accurate estimates of uncertainty in climate scenarios often requires generating large ensembles of high-resolution climate simulations, a computationally expensive and memory intensive process. To address this challenge, we train a novel generative deep learning approach on extensive sets of climate simulations. The model consists of two components: a variational autoencoder for dimensionality reduction and a denoising diffusion probabilistic model that generates multiple ensemble members. We validate our model on the Max Planck Institute Grand Ensemble and show that it achieves good agreement with the original ensemble in terms of variability. By leveraging the latent space representation, our model can rapidly generate large ensembles on-the-fly with minimal memory requirements, which can significantly improve the efficiency of uncertainty quantification in climate simulations.