Vision Transformers for Multi-Variable Climate Downscaling: Emulating Regional Climate Models with a Shared Encoder and Multi-Decoder Architecture

TL;DR

This paper introduces a multi-variable Vision Transformer architecture for regional climate downscaling that improves accuracy and reduces computational costs by jointly modeling six climate variables from GCM data.

Contribution

The paper presents a novel multi-variable ViT with shared encoder and variable-specific decoders, outperforming single-variable models and other baselines in climate downscaling tasks.

Findings

Average MSE reduced by 5.5% compared to single-variable models

Achieved 29-32% lower inference time per variable

Outperformed alternative multi-variable baselines

Abstract

Global Climate Models (GCMs) are critical for simulating large-scale climate dynamics, but their coarse spatial resolution limits their applicability in regional studies. Regional Climate Models (RCMs) address this limitation through dynamical downscaling, albeit at considerable computational cost and with limited flexibility. Deep learning has emerged as an efficient data-driven alternative; however, most existing approaches focus on single-variable models that downscale one variable at a time. This paradigm can lead to redundant computation, limited contextual awareness, and weak cross-variable interactions.To address these limitations, we propose a multi-variable Vision Transformer (ViT) architecture with a shared encoder and variable-specific decoders (1EMD). The proposed model jointly predicts six key climate variables: surface temperature, wind speed, 500 hPa geopotential height, total precipitation, surface downwelling shortwave radiation, and surface downwelling longwave radiation, directly from GCM-resolution inputs, emulating RCM-scale downscaling over Europe. Compared to single-variable ViT models, the 1EMD architecture improves performance across all six variables, achieving an average MSE reduction of approximately 5.5% under a fair and controlled comparison. It also consistently outperforms alternative multi-variable baselines, including a single-decoder ViT and a multi-variable U-Net. Moreover, multi-variable models substantially reduce computational cost, yielding a 29-32% lower inference time per variable compared to single-variable approaches. Overall, our results demonstrate that multi-variable modeling provides systematic advantages for high-resolution climate downscaling in terms of both accuracy and efficiency. Among the evaluated architectures, the proposed 1EMD ViT achieves the most favorable trade-off between predictive performance and computational cost.