MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling

TL;DR

MambaDS is a novel downscaling model that effectively incorporates topography and multivariable correlations to produce high-resolution near-surface weather forecasts, outperforming previous methods.

Contribution

It introduces the selective state space model into meteorological downscaling, specifically addressing topography integration and long-range dependency modeling.

Findings

Achieves state-of-the-art results in multiple downscaling settings.

Effectively incorporates topography and multivariable correlations.

Demonstrates superior performance in China and the US.

Abstract

In an era of frequent extreme weather and global warming, obtaining precise, fine-grained near-surface weather forecasts is increasingly essential for human activities. Downscaling (DS), a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions from global-scale forecast results. Previous downscaling methods, inspired by CNN and Transformer-based super-resolution models, lacked tailored designs for meteorology and encountered structural limitations. Notably, they failed to efficiently integrate topography, a crucial prior in the downscaling process. In this paper, we address these limitations by pioneering the selective state space model into the meteorological field downscaling and propose a novel model called MambaDS. This model enhances the utilization of multivariable correlations and topography information, unique challenges in the downscaling process while retaining the advantages of Mamba in long-range dependency modeling and linear computational complexity. Through extensive experiments in both China mainland and the continental United States (CONUS), we validated that our proposed MambaDS achieves state-of-the-art results in three different types of meteorological field downscaling settings. We will release the code subsequently.