Journal article · 2024 · Open access

Deep Learning for Daily 2‐m Temperature Downscaling

Shuyan Ding, Xiefei Zhi, Yang Lyu, Yan Ji, Weijun Guo

Earth and Space Science, 11(2), e2023EA003227 · Published 1 February 2024 · DOI 10.1029/2023ea003227

Open PDFView at the publisherCite this paper

In brief

“Deep Learning for Daily 2‐m Temperature Downscaling” is a 2024 journal article by Shuyan Ding and 4 co-authors, published in Earth and Space Science. OpenAlex counts 19 citations as of 21 November 2026, which puts it in the top 8% of works published in 2024 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Earth and Space Science.

Citations
19
Most cited in
2026 (10)
Field-weighted impact
2.50
References
66
Authors
5

Abstract

This study proposes a novel method, which is a U‐shaped convolutional neural network that combines non‐local attention mechanisms, Res2net residual modules, and terrain information (UNR‐Net). The original U‐Net method and the linear regression (LR) method are conducted as benchmarks. Generally, the UNR‐Net has demonstrated promise in performing a 10× downscaling for daily 2‐m temperature over North China with lead times of 1–7 days and shows superiority to the U‐Net and LR methods. To be specific, U‐Net and UNR‐Net demonstrate higher Nash‐Sutcliffe Efficiency coefficient values compared to LR by 0.052 and 0.077, respectively. The corresponding improvements in pattern correlation coefficient are 0.013 and 0.016, while the root mean square error values are higher by 0.22 and 0.338, respectively. Additionally, the structural similarity index metric is higher by 0.033 and lower by 0.015. Furthermore, regions with significant errors are primarily distributed in complex terrain areas such as the Taihang Mountains, where UNR‐Net exhibits noticeable improvements. In addition, the 12 components‐based error decomposition method is proposed to analyze the error source of different models. Generally, the smallest errors are observed during the summer season and the sequence error component is proven to be the main source error of 2‐m temperature forecasts. Furthermore, UNR‐Net consistently demonstrates the lowest errors among all 12 error components. Therefore, combining the numerical weather prediction model and deep learning method is very promising in downscaling temperature forecasts and can be applied to routine forecasting of other atmospheric variables in the future.

Cite this paper

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

APA 7

Ding, S., Zhi, X., Lyu, Y., Ji, Y., & Guo, W. (2024). Deep Learning for Daily 2‐m Temperature Downscaling. Earth and Space Science, 11(2), e2023EA003227. https://doi.org/10.1029/2023ea003227

MLA 9

Ding, Shuyan, et al. “Deep Learning for Daily 2‐m Temperature Downscaling.” Earth and Space Science, vol. 11, no. 2, 2024, p. e2023EA003227. https://doi.org/10.1029/2023ea003227.

Chicago

Ding, Shuyan, Xiefei Zhi, Yang Lyu, Yan Ji, and Weijun Guo. 2024. “Deep Learning for Daily 2‐m Temperature Downscaling.” Earth and Space Science 11 (2): e2023EA003227. https://doi.org/10.1029/2023ea003227.

Harvard

Ding, S. et al. (2024) ‘Deep Learning for Daily 2‐m Temperature Downscaling’, Earth and Space Science, 11(2), p. e2023EA003227. doi:10.1029/2023ea003227.

IEEE

S. Ding, X. Zhi, Y. Lyu, Y. Ji, and W. Guo, “Deep Learning for Daily 2‐m Temperature Downscaling,” Earth and Space Science, vol. 11, no. 2, p. e2023EA003227, 2024, doi: 10.1029/2023ea003227.

BibTeX

@article{ding2024deep,
  title     = {{Deep Learning for Daily 2‐m Temperature Downscaling}},
  author    = {Ding, Shuyan and Zhi, Xiefei and Lyu, Yang and Ji, Yan and Guo, Weijun},
  journal   = {Earth and Space Science},
  year      = {2024},
  volume    = {11},
  number    = {2},
  pages     = {e2023EA003227},
  doi       = {10.1029/2023ea003227},
  url       = {https://doi.org/10.1029/2023ea003227}
}

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

Citations by year

YearCitationsShare of the best year
202422
202577
20261010

Its field-weighted citation impact is 2.50: it has been cited 2.50 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

  • temperature downscaling
  • non-local attention
  • terrain data
  • complex terrain
  • error decomposition
  • numerical weather prediction
  • North China
  • Taihang Mountains

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?

Ding, S., Zhi, X., Lyu, Y., Ji, Y., & Guo, W. (2024). Deep Learning for Daily 2‐m Temperature Downscaling. Earth and Space Science, 11(2), e2023EA003227. https://doi.org/10.1029/2023ea003227

How many times has this paper been cited?

19 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 Earth and Space Science: sign in and open the PDF from this page.

Who wrote this paper?

Shuyan Ding, Xiefei Zhi, Yang Lyu, Yan Ji, Weijun Guo.

What is the DOI of this paper?

10.1029/2023ea003227, permanently at https://doi.org/10.1029/2023ea003227. 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.