Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Resolution-Agnostic Transformer-based Climate Downscaling

Declan Curran, Hira Saleem, Sanaa Hobeichi, Flora Salim

TL;DR

This study introduces a cost-efficient downscaling method using a pretrained Earth Vision Transformer (Earth ViT) model that holds promise for generating large ensembles of regional climate simulations by downscaling GCMs with varying input resolutions without incurring additional training costs.

Abstract

Understanding future weather changes at regional and local scales is crucial for planning and decision-making, particularly in the context of extreme weather events, as well as for broader applications in agriculture, insurance, and infrastructure development. However, the computational cost of downscaling Global Climate Models (GCMs) to the fine resolutions needed for such applications presents a significant barrier. Drawing on advancements in weather forecasting models, this study introduces a cost-efficient downscaling method using a pretrained Earth Vision Transformer (Earth ViT) model. Initially trained on ERA5 data to downscale from 50 km to 25 km resolution, the model is then tested on the higher resolution BARRA-SY dataset at a 3 km resolution. Remarkably, it performs well without additional training, demonstrating its ability to generalize across different resolutions. This approach holds promise for generating large ensembles of regional climate simulations by downscaling GCMs with varying input resolutions without incurring additional training costs. Ultimately, this method could provide more comprehensive estimates of potential future changes in key climate variables, aiding in effective planning for extreme weather events and climate change adaptation strategies.

Resolution-Agnostic Transformer-based Climate Downscaling

TL;DR

This study introduces a cost-efficient downscaling method using a pretrained Earth Vision Transformer (Earth ViT) model that holds promise for generating large ensembles of regional climate simulations by downscaling GCMs with varying input resolutions without incurring additional training costs.

Abstract

Understanding future weather changes at regional and local scales is crucial for planning and decision-making, particularly in the context of extreme weather events, as well as for broader applications in agriculture, insurance, and infrastructure development. However, the computational cost of downscaling Global Climate Models (GCMs) to the fine resolutions needed for such applications presents a significant barrier. Drawing on advancements in weather forecasting models, this study introduces a cost-efficient downscaling method using a pretrained Earth Vision Transformer (Earth ViT) model. Initially trained on ERA5 data to downscale from 50 km to 25 km resolution, the model is then tested on the higher resolution BARRA-SY dataset at a 3 km resolution. Remarkably, it performs well without additional training, demonstrating its ability to generalize across different resolutions. This approach holds promise for generating large ensembles of regional climate simulations by downscaling GCMs with varying input resolutions without incurring additional training costs. Ultimately, this method could provide more comprehensive estimates of potential future changes in key climate variables, aiding in effective planning for extreme weather events and climate change adaptation strategies.

Paper Structure

This paper contains 12 sections, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Earth Vision-Transformer
  3. Experiments and Results
  4. Discussion
  5. Acknowledgement
  6. Experiments
  7. Hyperparameters
  8. Hardware Requirements
  9. Datasets
  10. ERA5
  11. BARRA-SY
  12. Results

Figures (2)

  • Figure 1: ERA5 downscaling of 2-meter Temperature using Earth ViT with modified loss function. From left to right: coarse resolution (50km), ground truth high resolution (25km), predicted high resolution (25km)
  • Figure 2: ERA5 downscaling of 2-meter Temperature using Earth ViT with modified loss function. From left to right: coarse resolution (50km), ground truth high resolution (25km), predicted high resolution (25km)