# Capturing Climatic Variability: Using Deep Learning for Stochastic Downscaling

arXiv: https://arxiv.org/abs/2406.02587 · HTML: https://mlsanity.com/paper/2406.02587/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 9 of 9)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network](https://mlsanity.com/paper/2005.10374/) (2020)
- [A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts](https://mlsanity.com/paper/2204.02028/) (2022)
- [Bayesian GAN](https://mlsanity.com/paper/1705.09558/) (2017)
- [ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network](https://mlsanity.com/paper/2001.08073/) (2020)
- [Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scales](https://mlsanity.com/paper/2302.08720/) (2023)

## Built on by (most cited first, 8 of 8)

- [TAUDiff: Highly efficient kilometer-scale downscaling using generative diffusion models](https://mlsanity.com/paper/2412.13627/) (2024)
- [Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentration](https://mlsanity.com/paper/2510.09891/) (2025)
- [Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speed](https://mlsanity.com/paper/2508.16686/) (2025)
- [Toward generative machine learning for boosting ensembles of climate simulations](https://mlsanity.com/paper/2602.06287/) (2026)
- [Enhancing operational wind downscaling capabilities over Canada: Application of a Conditional Wasserstein GAN methodology](https://mlsanity.com/paper/2412.06958/) (2024)
- [Summary Statistics of Large-scale Model Outputs for Observation-corrected Outputs](https://mlsanity.com/paper/2506.15845/) (2025)
- [Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictions](https://mlsanity.com/paper/2605.29172/) (2026)
- [Generalizable Neural Downscaling of Earth System Model Wind Fields via Continuous Dynamics Modeling](https://mlsanity.com/paper/2610.03757/) (2026)

## Abstract (arXiv)

Adapting to the changing climate requires accurate local climate information, a computationally challenging problem. Recent studies have used Generative Adversarial Networks (GANs), a type of deep learning, to learn complex distributions and downscale climate variables efficiently. Capturing variability while downscaling is crucial for estimating uncertainty and characterising extreme events - critical information for climate adaptation. Since downscaling is an undetermined problem, many fine-scale states are physically consistent with the coarse-resolution state. To quantify this ill-posed problem, downscaling techniques should be stochastic, able to sample realisations from a high-resolution distribution conditioned on low-resolution input. Previous stochastic downscaling attempts have found substantial underdispersion, with models failing to represent the full distribution. We propose approaches to improve the stochastic calibration of GANs in three ways: a) injecting noise inside the network, b) adjusting the training process to explicitly account for the stochasticity, and c) using a probabilistic loss metric. We tested our models first on a synthetic dataset with known distributional properties, and then on a realistic downscaling scenario, predicting high-resolution wind components from low-resolution climate covariates. Injecting noise, on its own, substantially improved the quality of conditional and full distributions in tests with synthetic data, but performed less well for wind field downscaling, where models remained underdispersed. For wind downscaling, we found that adjusting the training method and including the probabilistic loss improved calibration. The best model, with all three changes, showed much improved skill at capturing the full variability of the high-resolution distribution and thus at characterising extremes.