Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
Climate downscaling is a crucial technique within climate research, serving to project low-resolution (LR) climate data to higher resolutions (HR). Previous research has demonstrated the effectiveness of deep learning for downscaling tasks. However, most deep learning models for climate downscaling may not perform optimally for high scaling factors (i.e., 4x, 8x) due to their limited ability to capture the intricate details required for generating HR climate data. Furthermore, climate data behaves differently from image data, necessitating a nuanced approach when employing deep generative models. In response to these challenges, this paper presents a deep generative model for downscaling climate data, specifically precipitation on a regional scale. We employ a denoising diffusion probabilistic model (DDPM) conditioned on multiple LR climate variables. The proposed model is evaluated using precipitation data from the Community Earth System Model (CESM) v1.2.2 simulation. Our results demonstrate significant improvements over existing baselines, underscoring the effectiveness of the conditional diffusion model in downscaling climate data.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 7 of its 13 references that are in the map. First posted on arXiv 12 Dec 2023.
Builds on
7 of 13 references.
References · 7
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2021Image Super-Resolution via Iterative Refinementcited by 1,506
- 2017DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolutioncited by 80
Built on by
Citing papers per year: 2025: 3.
3 papers.
- 2025A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Modelcited by 10
- 2025Frequency-Aware Vision Transformers for High-Fidelity Super-Resolution of Earth System Modelscited by 1
- 2025ViSIR: Vision Transformer Single Image Reconstruction Method for Earth System Modelscited by 0
- 2025A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Model1 Jul 2025
- 2025Frequency-Aware Vision Transformers for High-Fidelity Super-Resolution of Earth System Models18 Feb 2025
- 2025ViSIR: Vision Transformer Single Image Reconstruction Method for Earth System Models10 Feb 2025
Similar, not cited
Close in wording, no citation either way
- 2024Downscaling Precipitation with Bias-informed Conditional Diffusion Model
- 2024Conditional diffusion models for downscaling and bias correction of Earth system model precipitation
- 2026Precipitation Downscaling Using Foundation Model-Conditioned Diffusion
- 2024Dynamical-generative downscaling of climate model ensembles
- 2024Towards Kriging-informed Conditional Diffusion for Regional Sea-Level Data Downscaling
- 2024A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation
- 2025Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling
- 2025China Regional 3km Downscaling Based on Residual Corrective Diffusion Model