Journal article · 2022 · Open access

U-Net: A deep-learning method for improving summer precipitation forecasts in China

Qimin Deng, Peirong Lu, Shuyun Zhao, Naiming Yuan

Atmospheric and Oceanic Science Letters, 16(4), 100322 · Published 18 December 2022 · DOI 10.1016/j.aosl.2022.100322

Open PDFView at the publisherCite this paper

In brief

“U-Net: A deep-learning method for improving summer precipitation forecasts in China” is a 2022 journal article by Qimin Deng and 3 co-authors, published in Atmospheric and Oceanic Science Letters. OpenAlex counts 32 citations as of 20 November 2026, which puts it in the top 5% of works published in 2022 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Atmospheric and Oceanic Science Letters.

Citations
32
Most cited in
2025 (12)
Field-weighted impact
1.49
References
30
Authors
4

Abstract

A deep-learning method named U-Net was applied to improve the skill in forecasting summer (June–August) precipitation for at a one-month lead during the period 1981–2020 in China. The variables of geopotential height, soil moisture, sea level pressure, sea surface temperature, ocean salinity, and snow were considered as the model input to revise the seasonal prediction of the Climate Forecast System, version 2 (CFSv2). Results showed that on average U-Net reduced the root-mean-square error of the original CFSv2 prediction by 49.7% and 42.7% for the validation and testing set, respectively. The most improved areas were Northwest, Southwest, and Southeast China. The anomaly same sign percentages and temporal and spatial correlation coefficients did not present significant improvement but maintained the comparable performances of CFSv2. Sensitivity experiments showed that soil moisture is the most crucial factor in predicting summer rainfall in China, followed by geopotential height. Due to its advantages in handling small training dataset sizes, U-Net is a promising deep-learning method for seasonal rainfall prediction. 摘要 本研究应用了名为U-Net的深度学习方法来提高中国夏季 (6–8月) 降水的预报技能, 预报时段为1981–2020年, 预报提前期为一个月. 将位势高度场, 土壤湿度, 海平面气压, 海表面温度, 海洋盐度和青藏高原积雪等变量作为模型输入, 本文对美国NCAR气候预报系统第2版 (CFSv2) 的季节性预报结果进行了修正. 结果显示, 在验证集和测试集上, U-Net平均将原CFSv2预测的均方根误差分别减少了49.7%和42.7%. 预报结果改善最大的地区是中国的西北,西南和东南地区. 然而, 同号率和时空相关系数没有得到明显改善, 但仍与CFSv2的预测技巧持平. 敏感性实验表明, 土壤湿度是预测中国夏季降雨的最关键因素, 其次是位势高度场. 本研究显示了U-Net模型在训练小样本数据集方面的优势, 为我国汛期季节性降雨预测提供了一种有效的深度学习方法.

Cite this paper

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

APA 7

Deng, Q., Lu, P., Zhao, S., & Yuan, N. (2022). U-Net: A deep-learning method for improving summer precipitation forecasts in China. Atmospheric and Oceanic Science Letters, 16(4), 100322. https://doi.org/10.1016/j.aosl.2022.100322

MLA 9

Deng, Qimin, et al. “U-Net: A deep-learning method for improving summer precipitation forecasts in China.” Atmospheric and Oceanic Science Letters, vol. 16, no. 4, 2022, p. 100322. https://doi.org/10.1016/j.aosl.2022.100322.

Chicago

Deng, Qimin, Peirong Lu, Shuyun Zhao, and Naiming Yuan. 2022. “U-Net: A deep-learning method for improving summer precipitation forecasts in China.” Atmospheric and Oceanic Science Letters 16 (4): 100322. https://doi.org/10.1016/j.aosl.2022.100322.

Harvard

Deng, Q. et al. (2022) ‘U-Net: A deep-learning method for improving summer precipitation forecasts in China’, Atmospheric and Oceanic Science Letters, 16(4), p. 100322. doi:10.1016/j.aosl.2022.100322.

IEEE

Q. Deng, P. Lu, S. Zhao, and N. Yuan, “U-Net: A deep-learning method for improving summer precipitation forecasts in China,” Atmospheric and Oceanic Science Letters, vol. 16, no. 4, p. 100322, 2022, doi: 10.1016/j.aosl.2022.100322.

BibTeX

@article{deng2022deep,
  title     = {{U-Net: A deep-learning method for improving summer precipitation forecasts in China}},
  author    = {Deng, Qimin and Lu, Peirong and Zhao, Shuyun and Yuan, Naiming},
  journal   = {Atmospheric and Oceanic Science Letters},
  year      = {2022},
  volume    = {16},
  number    = {4},
  pages     = {100322},
  doi       = {10.1016/j.aosl.2022.100322},
  url       = {https://doi.org/10.1016/j.aosl.2022.100322}
}

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

Citations by year

YearCitationsShare of the best year
202333
202488
20251212
202699

Its field-weighted citation impact is 1.49: it has been cited 1.49 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 › Environmental Science › Global and Planetary Change › Climate variability and models

  • U-Net
  • seasonal rainfall forecasting
  • soil moisture
  • geopotential height

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Deng, Q., Lu, P., Zhao, S., & Yuan, N. (2022). U-Net: A deep-learning method for improving summer precipitation forecasts in China. Atmospheric and Oceanic Science Letters, 16(4), 100322. https://doi.org/10.1016/j.aosl.2022.100322

How many times has this paper been cited?

32 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 Atmospheric and Oceanic Science Letters: sign in and open the PDF from this page.

Who wrote this paper?

Qimin Deng, Peirong Lu, Shuyun Zhao, Naiming Yuan.

What is the DOI of this paper?

10.1016/j.aosl.2022.100322, permanently at https://doi.org/10.1016/j.aosl.2022.100322. 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.