Transformer based super-resolution downscaling for regional reanalysis: Full domain vs tiling approaches

TL;DR

This paper compares transformer-based and other super-resolution methods for climate data downscaling, highlighting the trade-offs between full domain and tiling approaches in terms of performance and scalability.

Contribution

It introduces a Swin transformer-based super-resolution method and evaluates its effectiveness against benchmarks, emphasizing the scalability of tiling approaches for regional climate downscaling.

Findings

Tiling approach offers scalable downscaling with slightly lower performance.

Transformer-based Swin method outperforms simple bicubic interpolation.

Tiling approach is suitable for real-time, large-scale applications.

Abstract

Super-resolution (SR) is a promising cost-effective downscaling methodology for producing high-resolution climate information from coarser counterparts. A particular application is downscaling regional reanalysis outputs (predictand) from the driving global counterparts (predictor). This study conducts an intercomparison of various SR downscaling methods focusing on temperature and using the CERRA reanalysis (5.5 km resolution, produced with a regional atmospheric model driven by ERA5) as example. The method proposed in this work is the Swin transformer and two alternative methods are used as benchmark (fully convolutional U-Net and convolutional and dense DeepESD) as well as the simple bicubic interpolation. We compare two approaches, the standard one using the full domain as input and a more scalable tiling approach, dividing the full domain into tiles that are used as input. The methods are trained to downscale CERRA surface temperature, based on temperature information from the driving ERA5; in addition, the tiling approach includes static orographic information. We show that the tiling approach, which requires spatial transferability, comes at the cost of a lower performance (although it outperforms some full-domain benchmarks), but provides an efficient scalable solution that allows SR reduction on a pan-European scale and is valuable for real-time applications.