Journal article · 2024 · Open access

Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism

Jieli Liu, Chunxiang Shi, Lingling Ge, Ruian Tie, Xiaojian Chen, Tao Zhou, Xiang Gu, Zhanfei Shen

Remote Sensing, 16(11), 1867 · Published 23 May 2024 · DOI 10.3390/rs16111867

Open PDFView at the publisherCite this paper

In brief

“Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism” is a 2024 journal article by Jieli Liu and 7 co-authors, published in Remote Sensing. OpenAlex counts 16 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at Remote Sensing.

Citations
16
Most cited in
2026 (9)
Field-weighted impact
2.10
References
37
Authors
8

Abstract

Before 2008, China lacked high-coverage regional surface observation data, making it difficult for the China Meteorological Administration Land Data Assimilation System (CLDAS) to directly backtrack high-resolution, high-quality land assimilation products. To address this issue, this paper proposes a deep learning model named UNET_DCA, based on the UNET architecture, which incorporates a Dual Cross-Attention module (DCA) for multiscale feature fusion by introducing Channel Cross-Attention (CCA) and Spatial Cross-Attention (SCA) mechanisms. This model focuses on the near-surface 10-m wind field and achieves spatial downscaling from 6.25 km to 1 km. We conducted training and validation using data from 2020–2021, tested with data from 2019, and performed ablation experiments to validate the effectiveness of each module. We compared the results with traditional bilinear interpolation methods and the SNCA-CLDASSD model. The experimental results show that the UNET-based model outperforms SNCA-CLDASSD, indicating that the UNET-based model captures richer information in wind field downscaling compared to SNCA-CLDASSD, which relies on sequentially stacked CNN convolution modules. UNET_CCA and UNET_SCA, incorporating cross-attention mechanisms, outperform UNET without attention mechanisms. Furthermore, UNET_DCA, incorporating both Channel Cross-Attention and Spatial Cross-Attention mechanisms, outperforms UNET_CCA and UNET_SCA, which only incorporate one attention mechanism. UNET_DCA performs best on the RMSE, MAE, and COR metrics (0.40 m/s, 0.28 m/s, 0.93), while UNET_DCA_ars, incorporating more auxiliary information, performs best on the PSNR and SSIM metrics (29.006, 0.880). Evaluation across different methods indicates that the optimal model performs best in valleys, followed by mountains, and worst in plains; it performs worse during the day and better at night; and as wind speed levels increase, accuracy decreases. Overall, among various downscaling methods, UNET_DCA and UNET_DCA_ars effectively reconstruct the spatial details of wind fields, providing a deeper exploration for the inversion of high-resolution historical meteorological grid data.

Cite this paper

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

APA 7

Liu, J., Shi, C., Ge, L., Tie, R., Chen, X., Zhou, T., Gu, X., & Shen, Z. (2024). Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism. Remote Sensing, 16(11), 1867. https://doi.org/10.3390/rs16111867

MLA 9

Liu, Jieli, et al. “Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism.” Remote Sensing, vol. 16, no. 11, 2024, p. 1867. https://doi.org/10.3390/rs16111867.

Chicago

Liu, Jieli, Chunxiang Shi, Lingling Ge, Ruian Tie, Xiaojian Chen, Tao Zhou, Xiang Gu, and Zhanfei Shen. 2024. “Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism.” Remote Sensing 16 (11): 1867. https://doi.org/10.3390/rs16111867.

Harvard

Liu, J. et al. (2024) ‘Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism’, Remote Sensing, 16(11), p. 1867. doi:10.3390/rs16111867.

IEEE

J. Liu et al., “Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism,” Remote Sensing, vol. 16, no. 11, p. 1867, 2024, doi: 10.3390/rs16111867.

BibTeX

@article{liu2024enhanced,
  title     = {{Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism}},
  author    = {Liu, Jieli and Shi, Chunxiang and Ge, Lingling and Tie, Ruian and Chen, Xiaojian and Zhou, Tao and Gu, Xiang and Shen, Zhanfei},
  journal   = {Remote Sensing},
  year      = {2024},
  volume    = {16},
  number    = {11},
  pages     = {1867},
  doi       = {10.3390/rs16111867},
  url       = {https://doi.org/10.3390/rs16111867}
}

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

Citations by year

YearCitationsShare of the best year
202411
202566
202699

Its field-weighted citation impact is 2.10: it has been cited 2.10 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • U-Net
  • cross-attention
  • multi-scale feature fusion
  • 10 m wind speed
  • CLDAS
  • land data assimilation
  • high-resolution meteorological data
  • terrain effects on wind

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?

Liu, J., Shi, C., Ge, L., Tie, R., Chen, X., Zhou, T., Gu, X., & Shen, Z. (2024). Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism. Remote Sensing, 16(11), 1867. https://doi.org/10.3390/rs16111867

How many times has this paper been cited?

16 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 Remote Sensing: sign in and open the PDF from this page.

Who wrote this paper?

Jieli Liu, Chunxiang Shi, Lingling Ge, Ruian Tie, Xiaojian Chen, Tao Zhou, Xiang Gu, Zhanfei Shen.

What is the DOI of this paper?

10.3390/rs16111867, permanently at https://doi.org/10.3390/rs16111867. 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.