Journal article · 2025 · Open access

Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction

Ouadghiri Ouafae, Jingming Xia

International Journal for Research in Applied Science and Engineering Technology, 13(4), 400–408 · Published 5 April 2025 · DOI 10.22214/ijraset.2025.68206

Open PDFCite this paper

In brief

“Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction” is a 2025 journal article by Ouadghiri Ouafae and Jingming Xia, published in International Journal for Research in Applied Science and Engineering Technology. OpenAlex counts 0 citations as of 20 November 2026. It is open access: the full text is free to read at International Journal for Research in Applied Science and Engineering Technology.

Citations
0
References
15
Authors
2

Abstract

Biases in numerical weather prediction (NWP) outputs remain a persistent challenge, often degrading forecast reliability for end users. Recent advances in deep learning have enabled more effective bias correction of NWP forecasts by capturing complex nonlinear error patterns that elude traditional statistical methods. This paper provides a comprehensive review of deep learning–based bias correction techniques for global NWP. We outline the nature of forecast biases and conventional correction approaches, then survey state-of-the-art deep learning methods – including convolutional neural networks (CNNs), recurrent networks, and Transformers – applied to improve predictions of temperature, wind, and precipitation. The review synthesizes results from 2021–2025 studies, highlighting typical performance gains (e.g. reductions in root-mean-square error and improved extreme event skill). Common strengths (such as handling multivariate spatial biases) and limitations (such as data requirements and interpretability) are discussed. Looking ahead, we identify key challenges to operational deployment and propose future directions to enhance generalization, transparency, and physical consistency. Deep learning bias correction is shown to significantly enhance forecast fidelity, offering a promising complement to ongoing model improvements in NWP

Cite this paper

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

APA 7

Ouafae, O., & Xia, J. (2025). Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction. International Journal for Research in Applied Science and Engineering Technology, 13(4), 400–408. https://doi.org/10.22214/ijraset.2025.68206

MLA 9

Ouafae, Ouadghiri, and Jingming Xia. “Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction.” International Journal for Research in Applied Science and Engineering Technology, vol. 13, no. 4, 2025, pp. 400–408. https://doi.org/10.22214/ijraset.2025.68206.

Chicago

Ouafae, Ouadghiri and Jingming Xia. 2025. “Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction.” International Journal for Research in Applied Science and Engineering Technology 13 (4): 400–408. https://doi.org/10.22214/ijraset.2025.68206.

Harvard

Ouafae, O. and Xia, J. (2025) ‘Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction’, International Journal for Research in Applied Science and Engineering Technology, 13(4), pp. 400–408. doi:10.22214/ijraset.2025.68206.

IEEE

O. Ouafae and J. Xia, “Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction,” International Journal for Research in Applied Science and Engineering Technology, vol. 13, no. 4, pp. 400–408, 2025, doi: 10.22214/ijraset.2025.68206.

BibTeX

@article{ouafae2025forecast,
  title     = {{Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction}},
  author    = {Ouafae, Ouadghiri and Xia, Jingming},
  journal   = {International Journal for Research in Applied Science and Engineering Technology},
  year      = {2025},
  volume    = {13},
  number    = {4},
  pages     = {400--408},
  doi       = {10.22214/ijraset.2025.68206},
  url       = {https://doi.org/10.22214/ijraset.2025.68206}
}

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

  • bias correction
  • numerical weather prediction
  • deep learning
  • forecast bias
  • convolutional neural networks
  • recurrent neural networks
  • transformer models
  • temperature prediction

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?

Ouafae, O., & Xia, J. (2025). Forecast Fidelity: A Comprehensive Review of Deep Learning–Based Bias Correction in Numerical Weather Prediction. International Journal for Research in Applied Science and Engineering Technology, 13(4), 400–408. https://doi.org/10.22214/ijraset.2025.68206

How many times has this paper been cited?

0 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 International Journal for Research in Applied Science and Engineering Technology: sign in and open the PDF from this page.

Who wrote this paper?

Ouadghiri Ouafae, Jingming Xia.

What is the DOI of this paper?

10.22214/ijraset.2025.68206, permanently at https://doi.org/10.22214/ijraset.2025.68206. 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.