Journal article · 2026 · Open access

Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling

GUO Kemeng, LU Shu, XU Lin, Qin Jun, CHEN He, Li Lu

Digital engineering., 12, 100138 · Published 24 July 2026 · DOI 10.1016/j.dte.2026.100138

Open PDFView at the publisherCite this paper

In brief

“Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling” is a 2026 journal article by GUO Kemeng and 5 co-authors, published in Digital engineering.. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Digital engineering..

Citations
0
References
41
Authors
6

Abstract

To address systematic biases and insufficient spatial resolution in numerical weather prediction models, this paper proposes a two-stage deep learning model (LSTM-SR) that integrates bias correction and spatial downscaling using ECMWF-IFS high-resolution deterministic forecasts and CLDAS reanalysis data. In the first stage, a Long Short-Term Memory (LSTM) network produces hourly corrected temperature fields at 0.05° resolution. In the second stage, an improved U-Net downscaling model incorporating residual connections and a Transformer module refines the spatial resolution to 0.01°, generating high-resolution hourly temperature forecasts for the next 72 hours. To validate the proposed model, we conducted an ablation experiment in which the downscaling module of LSTM-SR was replaced by nearest-neighbor interpolation to create a benchmark model (LSTM-NN), and compared the results with those of ECMWF-IFS. The results show that: (1) For 1–3-day lead times, LSTM-SR improves the temporal resolution of ECMWF-IFS forecasts from 3/6-hourly to hourly, and reduces the mean absolute error (MAE), root mean square error (RMSE) and bias substantially relative to ECMWF-IFS and LSTM-NN, effectively mitigating the growth of forecast errors at longer lead times. (2) Spatially, the forecast errors of ECMWF-IFS and LSTM-NN exhibit a clear terrain dependence, with significantly larger errors in high-altitude areas than in plains, whereas LSTM-SR achieves an MAE ≤ 1.5°C for 88.5% – 99.2% of grid points, markedly improving forecast accuracy in high-altitude regions. (3) LSTM-SR demonstrates strong generalization ability across seasons: its median MAE is reduced by 19.10%–33.81% relative to ECMWF-IFS, and by an additional 6.89%–8.91% compared to LSTM-NN in spring, summer, and autumn. Error propagation analysis reveals that the second-stage downscaling inherits residual errors from the first-stage bias correction but does not cause error explosion. In summary, the LSTM-SR model achieves systematic bias correction and refined spatial reconstruction of numerical temperature forecasts, providing reliable technical support for operational medium-range gridded temperature forecasting.

Cite this paper

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

APA 7

Kemeng, G., Shu, L., Lin, X., Jun, Q., He, C., & Lu, L. (2026). Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling. Digital engineering., 12, 100138. https://doi.org/10.1016/j.dte.2026.100138

MLA 9

Kemeng, GUO, et al. “Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling.” Digital engineering., vol. 12, 2026, p. 100138. https://doi.org/10.1016/j.dte.2026.100138.

Chicago

Kemeng, GUO, LU Shu, XU Lin, Qin Jun, CHEN He, and Li Lu. 2026. “Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling.” Digital engineering. 12: 100138. https://doi.org/10.1016/j.dte.2026.100138.

Harvard

Kemeng, G. et al. (2026) ‘Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling’, Digital engineering., 12, p. 100138. doi:10.1016/j.dte.2026.100138.

IEEE

G. Kemeng, L. Shu, X. Lin, Q. Jun, C. He, and L. Lu, “Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling,” Digital engineering., vol. 12, p. 100138, 2026, doi: 10.1016/j.dte.2026.100138.

BibTeX

@article{kemeng2026deep,
  title     = {{Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling}},
  author    = {Kemeng, GUO and Shu, LU and Lin, XU and Jun, Qin and He, CHEN and Lu, Li},
  journal   = {Digital engineering.},
  year      = {2026},
  volume    = {12},
  pages     = {100138},
  doi       = {10.1016/j.dte.2026.100138},
  url       = {https://doi.org/10.1016/j.dte.2026.100138}
}

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
  • spatial downscaling
  • LSTM
  • U-Net
  • transformer models
  • ECMWF IFS
  • error propagation

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?

Kemeng, G., Shu, L., Lin, X., Jun, Q., He, C., & Lu, L. (2026). Deep learning-based temperature forecast postprocessing model integrating temporal bias correction and spatial downscaling. Digital engineering., 12, 100138. https://doi.org/10.1016/j.dte.2026.100138

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 Digital engineering.: sign in and open the PDF from this page.

Who wrote this paper?

GUO Kemeng, LU Shu, XU Lin, Qin Jun, CHEN He, Li Lu.

What is the DOI of this paper?

10.1016/j.dte.2026.100138, permanently at https://doi.org/10.1016/j.dte.2026.100138. 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.