mlsanityData to 14 Oct 2026

Diffusion Model-based Probabilistic Downscaling for 180-year East Asian Climate Reconstruction

arXiv 2402.06646 ↗First posted 2 Feb 2024physics.ao-ph cs.LG physics.geo-phcited by 25

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

As our planet is entering into the "global boiling" era, understanding regional climate change becomes imperative. Effective downscaling methods that provide localized insights are crucial for this target. Traditional approaches, including computationally-demanding regional dynamical models or statistical downscaling frameworks, are often susceptible to the influence of downscaling uncertainty. Here, we address these limitations by introducing a diffusion probabilistic downscaling model (DPDM) into the meteorological field. This model can efficiently transform data from 1deg to 0.1deg resolution. Compared with deterministic downscaling schemes, it not only has more accurate local details, but also can generate a large number of ensemble members based on probability distribution sampling to evaluate the uncertainty of downscaling. Additionally, we apply the model to generate a 180-year dataset of monthly surface variables in East Asia, offering a more detailed perspective for understanding local scale climate change over the past centuries.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 11 of its 59 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

11 of 59 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  8. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  9. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  10. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 371
  11. 2024Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Methodcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 14; 2026: 3.

25 papers.

Sort:

By area:

  1. 2024CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modellingcited by 56
  2. 2024Dynamical-generative downscaling of climate model ensemblescited by 20
  3. 2025Deep Learning and Foundation Models for Weather Prediction: A Surveycited by 16
  4. 2024FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Modelcited by 15
  5. 2024Diffusion Models Need Visual Priors for Image Generationcited by 13
  6. 2024MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modelingcited by 12
  7. 2024PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplinescited by 6
  8. 2024Stochastic Flow Matching for Resolving Small-Scale Physicscited by 5
  9. 2025Direct Distributional Optimization for Provable Alignment of Diffusion Modelscited by 5
  10. 2025RainShift: A Benchmark for Precipitation Downscaling Across Geographiescited by 5
  11. 2025Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusioncited by 4
  12. 2025Spatiotemporal Pyramid Flow Matching for Climate Emulationcited by 4
13 more
  1. 2025MODS: Multi-source Observations Conditional Diffusion Model for Meteorological State Downscalingcited by 3
  2. 2025A Comprehensive Review of Diffusion Models in Smart Agriculture: Progress, Applications, and Challengescited by 2
  3. 2025Controlling Ensemble Variance in Diffusion Models: An Application for Reanalyses Downscalingcited by 1
  4. 2025Conditional Diffusion Models for Global Precipitation Map Inpaintingcited by 1
  5. 2025Probabilistic Super-Resolution for Urban Micrometeorology via a Schr"odinger Bridgecited by 1
  6. 2025On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscalingcited by 1
  7. 2024MetaSD: A Unified Framework for Scalable Downscaling of Meteorological Variables in Diverse Situationscited by 0
  8. 2025Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Windscited by 0
  9. 2025Spatiotemporal Satellite Image Downscaling with Transfer Encoders and Autoregressive Generative Modelscited by 0
  10. 2025AODDiff: Probabilistic Reconstruction of Aerosol Optical Depth via Diffusion-based Bayesian Inferencecited by 0
  11. 2026Generating DDPM-based Samples from Tilted Distributionscited by 0
  12. 2026Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependenciescited by 0
  13. 2026Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscalingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Kriging-informed Conditional Diffusion for Regional Sea-Level Data Downscaling
  2. 2024A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation
  3. 2025Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling
  4. 2026IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales
  5. 2025Km-scale dynamical downscaling through conformalized latent diffusion models
  6. 2024Conditional diffusion models for downscaling and bias correction of Earth system model precipitation
  7. 2023Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models
  8. 2024TAUDiff: Highly efficient kilometer-scale downscaling using generative diffusion models