# ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flows

arXiv: https://arxiv.org/abs/2008.04679 · HTML: https://mlsanity.com/paper/2008.04679/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 25 of 25)

- [Increasing the accuracy and resolution of precipitation forecasts using deep generative models](https://mlsanity.com/paper/2203.12297/) (2022)
- [Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models](https://mlsanity.com/paper/2305.15618/) (2023)
- [Hard-Constrained Deep Learning for Climate Downscaling](https://mlsanity.com/paper/2208.05424/) (2022)
- [Convolutional conditional neural processes for local climate downscaling](https://mlsanity.com/paper/2101.07950/) (2021)
- [Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Machine Learning](https://mlsanity.com/paper/2403.02774/) (2024)
- [Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling](https://mlsanity.com/paper/2305.14452/) (2023)
- [Generative Diffusion-based Downscaling for Climate](https://mlsanity.com/paper/2404.17752/) (2024)
- [Deconditional Downscaling with Gaussian Processes](https://mlsanity.com/paper/2105.12909/) (2021)
- [Unpaired Downscaling of Fluid Flows with Diffusion Bridges](https://mlsanity.com/paper/2305.01822/) (2023)
- [AI Foundation Models for Weather and Climate: Applications, Design, and Implementation](https://mlsanity.com/paper/2309.10808/) (2023)
- [Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers](https://mlsanity.com/paper/2207.11417/) (2022)
- [A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation](https://mlsanity.com/paper/2412.15361/) (2024)
- [AtmoDist: Self-supervised Representation Learning for Atmospheric Dynamics](https://mlsanity.com/paper/2202.01897/) (2022)
- [SerpentFlow: Generative Unpaired Domain Alignment via Shared-Structure Decomposition](https://mlsanity.com/paper/2601.01979/) (2026)
- [Climate Variable Downscaling with Conditional Normalizing Flows](https://mlsanity.com/paper/2405.20719/) (2024)
- [Reflections from the Workshop on AI-Assisted Decision Making for Conservation](https://mlsanity.com/paper/2307.08774/) (2023)
- [Implicit Neural Representations for Simultaneous Reduction and Continuous Reconstruction of Multi-Altitude Climate Data](https://mlsanity.com/paper/2409.17367/) (2024)
- [DL4DS -- Deep Learning for empirical DownScaling](https://mlsanity.com/paper/2205.08967/) (2022)
- [Towards Climate Variable Prediction with Conditioned Spatio-Temporal Normalizing Flows](https://mlsanity.com/paper/2311.06958/) (2023)
- [Self Supervised Vision for Climate Downscaling](https://mlsanity.com/paper/2401.09466/) (2024)
- [Arbitrary-Scale Downscaling of Tidal Current Data Using Implicit Continuous Representation](https://mlsanity.com/paper/2401.15893/) (2024)
- [Weakly-Constrained 4D Var for Downscaling with Uncertainty using Data-Driven Surrogate Models](https://mlsanity.com/paper/2503.02665/) (2025)
- [Summary Statistics of Large-scale Model Outputs for Observation-corrected Outputs](https://mlsanity.com/paper/2506.15845/) (2025)
- [Zero-Shot Statistical Downscaling via Diffusion Posterior Sampling](https://mlsanity.com/paper/2601.21760/) (2026)
- [Generative Unsupervised Downscaling of Climate Models via Domain Alignment: Application to Wind Fields](https://mlsanity.com/paper/2604.03341/) (2026)

## Abstract (arXiv)

Downscaling is a landmark task in climate science and meteorology in which the goal is to use coarse scale, spatio-temporal data to infer values at finer scales. Statistical downscaling aims to approximate this task using statistical patterns gleaned from an existing dataset of downscaled values, often obtained from observations or physical models. In this work, we investigate the application of deep latent variable learning to the task of statistical downscaling. We present ClimAlign, a novel method for unsupervised, generative downscaling using adaptations of recent work in normalizing flows for variational inference. We evaluate the viability of our method using several different metrics on two datasets consisting of daily temperature and precipitation values gridded at low (1 degree latitude/longitude) and high (1/4 and 1/8 degree) resolutions. We show that our method achieves comparable predictive performance to existing supervised statistical downscaling methods while simultaneously allowing for both conditional and unconditional sampling from the joint distribution over high and low resolution spatial fields. We provide publicly accessible implementations of our method, as well as the baselines used for comparison, on GitHub.