Unpaired Downscaling of Fluid Flows with Diffusion Bridges

TL;DR

This paper introduces an unsupervised diffusion bridge method for downscaling geophysical fluid simulations, enabling high-resolution sample generation from low-resolution data without paired training, applicable to climate data.

Contribution

The novel approach combines diffusion maps and domain translation to downscale fluid flows without paired data, improving resolution and bias correction in geophysical simulations.

Findings

Enhances resolution of fluid simulations

Corrects context-dependent biases

Works without paired training data

Abstract

We present a method to downscale idealized geophysical fluid simulations using generative models based on diffusion maps. By analyzing the Fourier spectra of images drawn from different data distributions, we show how one can chain together two independent conditional diffusion models for use in domain translation. The resulting transformation is a diffusion bridge between a low resolution and a high resolution dataset and allows for new sample generation of high-resolution images given specific low resolution features. The ability to generate new samples allows for the computation of any statistic of interest, without any additional calibration or training. Our unsupervised setup is also designed to downscale images without access to paired training data; this flexibility allows for the combination of multiple source and target domains without additional training. We demonstrate that the method enhances resolution and corrects context-dependent biases in geophysical fluid simulations, including in extreme events. We anticipate that the same method can be used to downscale the output of climate simulations, including temperature and precipitation fields, without needing to train a new model for each application and providing a significant computational cost savings.