# Downscaling climate projections to 1 km with single-image super resolution

arXiv: https://arxiv.org/abs/2509.21399 · HTML: https://mlsanity.com/paper/2509.21399/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling](https://mlsanity.com/paper/2309.15214/) (2023)
- [DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution](https://mlsanity.com/paper/1703.03126/) (2017)
- [Increasing the accuracy and resolution of precipitation forecasts using deep generative models](https://mlsanity.com/paper/2203.12297/) (2022)
- [Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling](https://mlsanity.com/paper/2305.14452/) (2023)
- [SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning](https://mlsanity.com/paper/2306.14070/) (2023)
- [Deep generative model super-resolves spatially correlated multiregional climate data](https://mlsanity.com/paper/2209.12433/) (2022)
- [Evaluating the transferability potential of deep learning models for climate downscaling](https://mlsanity.com/paper/2407.12517/) (2024)
- [Multi-variable Hard Physical Constraints for Climate Model Downscaling](https://mlsanity.com/paper/2308.01868/) (2023)
- [On the Effectiveness of Neural Operators at Zero-Shot Weather Downscaling](https://mlsanity.com/paper/2409.13955/) (2024)
- [Transformer based super-resolution downscaling for regional reanalysis: Full domain vs tiling approaches](https://mlsanity.com/paper/2410.12728/) (2024)

## Abstract (arXiv)

High-resolution climate projections are essential for local decision-making. However, available climate projections have low spatial resolution (e.g. 12.5 km), which limits their usability. We address this limitation by leveraging single-image super-resolution models to statistically downscale climate projections to 1-km resolution. Since high-resolution climate projections are unavailable, we train models on a high-resolution observational gridded data set and apply them to low-resolution climate projections. We cannot evaluate downscaled climate projections with common metrics (e.g. pixel-wise root-mean-square error) because we lack ground-truth high-resolution climate projections. Therefore, we evaluate climate indicators computed at weather station locations. Experiments on daily mean temperature demonstrate that single-image super-resolution models can downscale climate projections without increasing the error of climate indicators compared to low-resolution climate projections.