SwinRDM: Integrate SwinRNN with Diffusion Model Towards High-Resolution and High-Quality Weather Forecasting
Year: 2023
Type: preprint
Abstract: Data-driven medium-range weather forecasting has attracted much attention in recent years. However, the forecasting accuracy at high resolution is unsatisfactory currently. Pursuing high-resolution and high-quality weather forecasting, we develop a data-driven model SwinRDM which integrates an improved version of SwinRNN with a diffusion model. SwinRDM performs predictions at $0.25^\circ$ resolution and achieves superior forecasting accuracy to IFS (Integrated Forecast System), the state-of-the-art operational NWP model, on representative atmospheric variables including 500 hPa geopotential (Z500), 850 hPa temperature (T850), 2-m temperature (T2M), and total precipitation (TP), at lead times of up to 5 days. We propose to leverage a two-step strategy to achieve high-resolution predictions at $0.25^\circ$ considering the trade-off between computation memory and forecasting accuracy. Recurrent predictions for future atmospheric fields are firstly performed at $1.40625^\circ$ resolution, and then a diffusion-based super-resolution model is leveraged to recover the high spatial resolution and finer-scale atmospheric details. SwinRDM pushes forward the performance and potential of data-driven models for a large margin towards operational applications.
Source: arXiv (Cornell University)
DOI: 10.48448/zn7f-fc64
Authors: Association for Artificial Intelligence 2023, Chen, Lei, Du, Fei, Hu, Yuan, Wang, Fan, Wang, Zhibin
Institution: Alibaba Group (China)
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: green
OpenAlex ID: W4379919090