Journal article · 2021 · Open access

Deep Learning for Daily Precipitation and Temperature Downscaling

Fang Wang, Di Tian, Lisa L. Lowe, Latif Kalin, John C. Lehrter

Water Resources Research, 57(4), e2020WR029308 · Published 1 April 2021 · DOI 10.1029/2020wr029308

Open PDFView at the publisherCite this paper

In brief

“Deep Learning for Daily Precipitation and Temperature Downscaling” is a 2021 journal article by Fang Wang and 4 co-authors, published in Water Resources Research. OpenAlex counts 269 citations as of 21 November 2026, which puts it in the top 4% of works published in 2021 by citations. It is open access: the full text is free to read at Water Resources Research.

Citations
269
Most cited in
2025 (72)
Field-weighted impact
9.29
References
58
Authors
5

Abstract

Downscaling is a critical step to bridge the gap between large‐scale climate information and local‐scale impact assessment. This study presents a novel deep learning approach: Super Resolution Deep Residual Network (SRDRN) for downscaling daily precipitation and temperature. This approach was constructed based on an advanced deep convolutional neural network with residual blocks and batch normalizations. The data augmentation technique was utilized to address overfitting that is due to highly imbalanced precipitation and nonprecipitation days and sparse precipitation extremes. Synthetic experiments were designed to downscale daily maximum/minimum temperature and precipitation data from coarse resolutions (25, 50, and 100 km) to a high resolution (4 km). The results showed that, during the validation period, the SRDRN approach not only captured the spatial and temporal patterns remarkably well, but also reproduced both precipitation and temperature extremes in different locations and time at the local scale. Through transfer learning, the trained SRDRN model in one region was directly applied to downscale precipitation in another region with a different environment, and the results showed notable improvement compared to classic statistical downscaling methods. The outstanding performance of the SRDRN approach stemmed from its ability to fully extract spatial features without suffering from degradation and overfitting issues due to the incorporations of residual blocks, batch normalizations, and data augmentations. The SRDRN approach is thus a powerful tool for downscaling daily precipitation and temperature and can potentially be leveraged to downscale any hydrologic, climate, and earth system data.

Cite this paper

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

APA 7

Wang, F., Tian, D., Lowe, L. L., Kalin, L., & Lehrter, J. C. (2021). Deep Learning for Daily Precipitation and Temperature Downscaling. Water Resources Research, 57(4), e2020WR029308. https://doi.org/10.1029/2020wr029308

MLA 9

Wang, Fang, et al. “Deep Learning for Daily Precipitation and Temperature Downscaling.” Water Resources Research, vol. 57, no. 4, 2021, p. e2020WR029308. https://doi.org/10.1029/2020wr029308.

Chicago

Wang, Fang, Di Tian, Lisa L. Lowe, Latif Kalin, and John C. Lehrter. 2021. “Deep Learning for Daily Precipitation and Temperature Downscaling.” Water Resources Research 57 (4): e2020WR029308. https://doi.org/10.1029/2020wr029308.

Harvard

Wang, F. et al. (2021) ‘Deep Learning for Daily Precipitation and Temperature Downscaling’, Water Resources Research, 57(4), p. e2020WR029308. doi:10.1029/2020wr029308.

IEEE

F. Wang, D. Tian, L. L. Lowe, L. Kalin, and J. C. Lehrter, “Deep Learning for Daily Precipitation and Temperature Downscaling,” Water Resources Research, vol. 57, no. 4, p. e2020WR029308, 2021, doi: 10.1029/2020wr029308.

BibTeX

@article{wang2021deep,
  title     = {{Deep Learning for Daily Precipitation and Temperature Downscaling}},
  author    = {Wang, Fang and Tian, Di and Lowe, Lisa L. and Kalin, Latif and Lehrter, John C.},
  journal   = {Water Resources Research},
  year      = {2021},
  volume    = {57},
  number    = {4},
  pages     = {e2020WR029308},
  doi       = {10.1029/2020wr029308},
  url       = {https://doi.org/10.1029/2020wr029308}
}

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

Citations by year

YearCitationsShare of the best year
202144
20223939
20234444
20244444
20257272
20266666

Its field-weighted citation impact is 9.29: it has been cited 9.29 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

  • climate downscaling
  • daily precipitation
  • daily temperature
  • convolutional neural networks
  • residual blocks
  • batch normalization
  • data augmentation
  • transfer learning

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?

Wang, F., Tian, D., Lowe, L. L., Kalin, L., & Lehrter, J. C. (2021). Deep Learning for Daily Precipitation and Temperature Downscaling. Water Resources Research, 57(4), e2020WR029308. https://doi.org/10.1029/2020wr029308

How many times has this paper been cited?

269 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 Water Resources Research: sign in and open the PDF from this page.

Who wrote this paper?

Fang Wang, Di Tian, Lisa L. Lowe, Latif Kalin, John C. Lehrter.

What is the DOI of this paper?

10.1029/2020wr029308, permanently at https://doi.org/10.1029/2020wr029308. 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.