Composite Classifier-Free Guidance for Multi-Modal Conditioning in Wind Dynamics Super-Resolution

TL;DR

This paper introduces a novel composite classifier-free guidance method for diffusion models, significantly improving wind data super-resolution quality while reducing costs compared to traditional approaches.

Contribution

It proposes a new guidance technique for diffusion models that effectively handles multiple conditioning inputs, enhancing wind data super-resolution performance.

Findings

CCFG outputs are higher-fidelity than standard CFG in wind super-resolution.

WindDM achieves state-of-the-art reconstruction quality.

WindDM reduces costs by up to 1000 times compared to classical methods.

Abstract

Various weather modelling problems (e.g., weather forecasting, optimizing turbine placements, etc.) require ample access to high-resolution, highly accurate wind data. Acquiring such high-resolution wind data, however, remains a challenging and expensive endeavour. Traditional reconstruction approaches are typically either cost-effective or accurate, but not both. Deep learning methods, including diffusion models, have been proposed to resolve this trade-off by leveraging advances in natural image super-resolution. Wind data, however, is distinct from natural images, and wind super-resolvers often use upwards of 10 input channels, significantly more than the usual 3-channel RGB inputs in natural images. To better leverage a large number of conditioning variables in diffusion models, we present a generalization of classifier-free guidance (CFG) to multiple conditioning inputs. Our novel composite classifier-free guidance (CCFG) can be dropped into any pre-trained diffusion model trained with standard CFG dropout. We demonstrate that CCFG outputs are higher-fidelity than those from CFG on wind super-resolution tasks. We present WindDM, a diffusion model trained for industrial-scale wind dynamics reconstruction and leveraging CCFG. WindDM achieves state-of-the-art reconstruction quality among deep learning models and costs up to $1000\times$ less than classical methods.