Journal article · 2025 · Open access

Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts

Peiting Liu, Wei Chen, Jun Dong, Li Zhang, Jin Pang, Haipeng Yang

Journal of Physics Conference Series, 2958(1), 012002 · Published 1 February 2025 · DOI 10.1088/1742-6596/2958/1/012002

Open PDFView at the publisherCite this paper

In brief

“Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts” is a 2025 journal article by Peiting Liu and 5 co-authors, published in Journal of Physics Conference Series. OpenAlex counts 1 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at Journal of Physics Conference Series.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
2.46
References
17
Authors
6

Abstract

Modern weather forecast operations rely on numerical model predictions, and improving the accuracy of model forecasts is crucial for enhancing refined intelligent gridded forecasts. In this study, based on three deep learning models, namely Coupled U-Nets (CU-Net), Attention U-Net (Att-Unet) and Swin-Unet, the integration of meteorological factors and terrain data for modelling is conducted in the Huang-Huai River Basin and its surrounding areas by using the European Centre for Medium-Range Weather Forecasts multi-element forecast data from March 2017 to April 2022. The results from the deep learning-based methods are analyzed and compared with those from the traditional Anomaly Numerical-correction with Observations (ANO) method. The results indicate that the deep learning methods exhibit more remarkable positive correction effects than the ANO method. Specifically, the Swin-Unet model performs the best in correcting 2-m temperature (T2m ) forecasts and 2-m specific humidity forecasts, while the Att-Unet model is optimal for correcting 10-m zonal wind, 10-m meridional wind and surface pressure forecasts. The credibility curves of the corrected results indicate that the correction benefits of various deep learning methods tend to be related to the different ranges of corrected elements. For example, the Att-Unet and Swin-Unet models perform the best when T2m 25°C, respectively. However, in terms of the correction for 10-m wind speed forecasts, the advantages of deep learning methods are outstanding when wind speed is less than 8 m·s−1. The CU-Net model excels in high-humidity regions. Moreover, the Swin-Unet model, which is based on a U-shaped encoder-decoder with a pure transformer, demonstrates a stronger ability to portray the details in individual correction cases, such as characterizing high-temperature regions, extreme humidity areas and local wind speed variations in the Yangtze River Basin.

Cite this paper

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

APA 7

Liu, P., Chen, W., Dong, J., Zhang, L., Pang, J., & Yang, H. (2025). Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts. Journal of Physics Conference Series, 2958(1), 012002. https://doi.org/10.1088/1742-6596/2958/1/012002

MLA 9

Liu, Peiting, et al. “Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts.” Journal of Physics Conference Series, vol. 2958, no. 1, 2025, p. 012002. https://doi.org/10.1088/1742-6596/2958/1/012002.

Chicago

Liu, Peiting, Wei Chen, Jun Dong, Li Zhang, Jin Pang, and Haipeng Yang. 2025. “Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts.” Journal of Physics Conference Series 2958 (1): 012002. https://doi.org/10.1088/1742-6596/2958/1/012002.

Harvard

Liu, P. et al. (2025) ‘Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts’, Journal of Physics Conference Series, 2958(1), p. 012002. doi:10.1088/1742-6596/2958/1/012002.

IEEE

P. Liu, W. Chen, J. Dong, L. Zhang, J. Pang, and H. Yang, “Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts,” Journal of Physics Conference Series, vol. 2958, no. 1, p. 012002, 2025, doi: 10.1088/1742-6596/2958/1/012002.

BibTeX

@article{liu2025deep,
  title     = {{Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts}},
  author    = {Liu, Peiting and Chen, Wei and Dong, Jun and Zhang, Li and Pang, Jin and Yang, Haipeng},
  journal   = {Journal of Physics Conference Series},
  year      = {2025},
  volume    = {2958},
  number    = {1},
  pages     = {012002},
  doi       = {10.1088/1742-6596/2958/1/012002},
  url       = {https://doi.org/10.1088/1742-6596/2958/1/012002}
}

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

  • deep learning
  • Swin-Unet
  • Attention U-Net
  • 2 m air temperature
  • specific humidity
  • wind speed
  • surface pressure
  • Yangtze River Basin

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, P., Chen, W., Dong, J., Zhang, L., Pang, J., & Yang, H. (2025). Deep Learning Methods for Multi-Element Bias Correction in Numerical Weather Forecasts. Journal of Physics Conference Series, 2958(1), 012002. https://doi.org/10.1088/1742-6596/2958/1/012002

How many times has this paper been cited?

1 times, according to OpenAlex on 20 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 Journal of Physics Conference Series: sign in and open the PDF from this page.

Who wrote this paper?

Peiting Liu, Wei Chen, Jun Dong, Li Zhang, Jin Pang, Haipeng Yang.

What is the DOI of this paper?

10.1088/1742-6596/2958/1/012002, permanently at https://doi.org/10.1088/1742-6596/2958/1/012002. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 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.