Preprint · 2026 · Open access

Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts

Haoyu Song, Huidong Jin, Zhaohui Lin, Xi Wu

Research Square · Published 6 August 2026 · DOI 10.21203/rs.3.rs-10229215/v1

Open PDFView at the publisherCite this paper

In brief

“Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts” is a 2026 preprint by Haoyu Song and 3 co-authors, published in Research Square. OpenAlex counts 0 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.

Citations
0
References
43
Authors
4

Abstract

Kilometre-scale daily precipitation forecasts at Sub-seasonal to Seasonal (S2S) lead times are critical for climate-sensitive sectors, but General Circulation Model (GCM) outputs are coarse and biased. Their ensemble nature also undermines traditional downscaling methods such as Quantile Mapping, which assume predefined relationships. Generative Adversarial Networks (GANs) can generate realistic precipitation fields but are unstable to train, while diffusion models struggle with mismatched coarse-to-fine training pairs and frequent zero-precipitation values. This study introduces the Conditional Diffusion Downscaling Model (CDDM), which frames S2S downscaling as conditional image translation from coarse GCM forecasts to fine-resolution observed precipitation fields. Drawing on the Brownian bridge process, CDDM modifies standard forward diffusion by terminating at a hybrid state that blends the coarse forecast with controlled Gaussian noise, rather than pure noise. The reverse process, conditioned on the raw GCM forecast, then learns a stochastic mapping to fine-scale precipitation fields. A composite loss function combining Mean Absolute Error (MAE) and relative Bias (rBias) further improves forecast accuracy.CDDM is evaluated by downscaling nine-member ACCESS-S2 ensemble forecasts from 60 km to 5 km resolution over eastern Australia. Averaged over three evaluation years and 42-day forecast horizons, CDDM consistently outperforms QM, a climatology benchmark, and a state-of-the-art GAN across probabilistic and deterministic metrics, including the continuous ranked probability score (CRPS), MAE, and rBias. It achieves improvements of at least 8.29\% in CRPS and 9.01\% in MAE, and remains robust across La Niña, neutral, and El Niño conditions.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Song, H., Jin, H., Lin, Z., & Wu, X. (2026). Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts. Research Square. https://doi.org/10.21203/rs.3.rs-10229215/v1

MLA 9

Song, Haoyu, et al. “Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-10229215/v1.

Chicago

Song, Haoyu, Huidong Jin, Zhaohui Lin, and Xi Wu. 2026. “Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts.” Research Square. https://doi.org/10.21203/rs.3.rs-10229215/v1.

Harvard

Song, H. et al. (2026) ‘Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts’, Research Square. doi:10.21203/rs.3.rs-10229215/v1.

IEEE

H. Song, H. Jin, Z. Lin, and X. Wu, “Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts,” Research Square, 2026, doi: 10.21203/rs.3.rs-10229215/v1.

BibTeX

@misc{song2026conditional,
  title     = {{Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts}},
  author    = {Song, Haoyu and Jin, Huidong and Lin, Zhaohui and Wu, Xi},
  howpublished = {Research Square},
  year      = {2026},
  doi       = {10.21203/rs.3.rs-10229215/v1},
  url       = {https://doi.org/10.21203/rs.3.rs-10229215/v1}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • precipitation downscaling
  • subseasonal-to-seasonal forecasting
  • diffusion models
  • Brownian bridge
  • probabilistic forecasting
  • relative bias
  • eastern Australia
  • El Niño/La Niña

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Song, H., Jin, H., Lin, Z., & Wu, X. (2026). Conditional Diffusion Downscaling for Probabilistic Subseasonal-to-Seasonal Precipitation Forecasts. Research Square. https://doi.org/10.21203/rs.3.rs-10229215/v1

How many times has this paper been cited?

0 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Research Square: sign in and open the PDF from this page.

Who wrote this paper?

Haoyu Song, Huidong Jin, Zhaohui Lin, Xi Wu.

What is the DOI of this paper?

10.21203/rs.3.rs-10229215/v1, permanently at https://doi.org/10.21203/rs.3.rs-10229215/v1. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.