Journal article · 2026 · Open access

EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors

Shiji Zhang, Cheng Zhang, Tao Wu, Tao Zou, Yuanchang Dong

Sensors, 26(6), 1857 · Published 15 March 2026 · DOI 10.3390/s26061857

Open PDFView at the publisherCite this paper

In brief

“EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors” is a 2026 journal article by Shiji Zhang and 4 co-authors, published in Sensors. 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 Sensors.

Citations
0
References
38
Authors
5

Abstract

Precipitation downscaling aims to enhance coarse-resolution data to higher resolutions. Due to the similarity between downscaling and super-resolution (SR), deep learning-based SR approaches have been increasingly adopted in this domain. However, single-image super-resolution (SISR) methods applied to precipitation data face two main challenges: weak high-frequency signals and highly skewed distributions in precipitation datasets, which often lead to overly smooth reconstructions, failure to capture precipitation extremes, and loss of fine-scale variability with predictions biased toward mean values. To address these issues, we propose EdgeGeoDiff, a two-stage diffusion model for precipitation downscaling that leverages both edge information and geographical priors (e.g., terrain-related factors such as elevation). In the first stage, a residual network reconstructs an initial high-resolution precipitation field with preliminary structural details. In the second stage, edge features extracted using the Laplacian operator, together with geographical priors, guide a diffusion model to generate residuals that enhance fine-scale precipitation structures. Experimental results on real-world precipitation datasets show that EdgeGeoDiff effectively reconstructs fine-scale details while preserving large-scale patterns and outperforms conventional SISR methods in terms of its RMSE, PSNR, SSIM, and CSI, particularly demonstrating superior performance in the high-frequency region of the spectrum.

Cite this paper

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

APA 7

Zhang, S., Zhang, C., Wu, T., Zou, T., & Dong, Y. (2026). EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors. Sensors, 26(6), 1857. https://doi.org/10.3390/s26061857

MLA 9

Zhang, Shiji, et al. “EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors.” Sensors, vol. 26, no. 6, 2026, p. 1857. https://doi.org/10.3390/s26061857.

Chicago

Zhang, Shiji, Cheng Zhang, Tao Wu, Tao Zou, and Yuanchang Dong. 2026. “EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors.” Sensors 26 (6): 1857. https://doi.org/10.3390/s26061857.

Harvard

Zhang, S. et al. (2026) ‘EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors’, Sensors, 26(6), p. 1857. doi:10.3390/s26061857.

IEEE

S. Zhang, C. Zhang, T. Wu, T. Zou, and Y. Dong, “EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors,” Sensors, vol. 26, no. 6, p. 1857, 2026, doi: 10.3390/s26061857.

BibTeX

@article{zhang2026edgegeodiff,
  title     = {{EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors}},
  author    = {Zhang, Shiji and Zhang, Cheng and Wu, Tao and Zou, Tao and Dong, Yuanchang},
  journal   = {Sensors},
  year      = {2026},
  volume    = {26},
  number    = {6},
  pages     = {1857},
  doi       = {10.3390/s26061857},
  url       = {https://doi.org/10.3390/s26061857}
}

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

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques

  • precipitation downscaling
  • single image super-resolution
  • diffusion models
  • two-stage reconstruction
  • edge features
  • Laplacian
  • altitude
  • heavy rainfall

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhang, S., Zhang, C., Wu, T., Zou, T., & Dong, Y. (2026). EdgeGeoDiff: A Novel Two-Stage Diffusion Approach for Precipitation Downscaling with Edge Details and Geographical Priors. Sensors, 26(6), 1857. https://doi.org/10.3390/s26061857

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 Sensors: sign in and open the PDF from this page.

Who wrote this paper?

Shiji Zhang, Cheng Zhang, Tao Wu, Tao Zou, Yuanchang Dong.

What is the DOI of this paper?

10.3390/s26061857, permanently at https://doi.org/10.3390/s26061857. 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.