Journal article · 2020 · Open access

A comparative study of convolutional neural network models for wind field downscaling

Kevin Höhlein, Michael Kern, Timothy Hewson, Rüdiger Westermann

Meteorological Applications, 27(6), e1961 · Published 1 November 2020 · DOI 10.1002/met.1961

Open PDFView at the publisherCite this paper

In brief

“A comparative study of convolutional neural network models for wind field downscaling” is a 2020 journal article by Kevin Höhlein and 3 co-authors, published in Meteorological Applications. OpenAlex counts 172 citations as of 21 November 2026, which puts it in the top 2% of works published in 2020 by citations. It is open access under a CC BY licence: the full text is free to read at Meteorological Applications.

Citations
172
Most cited in
2025 (44)
Field-weighted impact
4.18
References
99
Authors
4

Abstract

We analyze the applicability of convolutional neural network (CNN) architectures for downscaling of short‐range forecasts of near‐surface winds on extended spatial domains. Short‐range wind forecasts (at the 100 m level) from European Centre for Medium Range Weather Forecasts ERA5 reanalysis initial conditions at 31 km horizontal resolution are downscaled to mimic high resolution (HRES) (deterministic) short‐range forecasts at 9 km resolution. We evaluate the downscaling quality of four exemplary CNN architectures and compare these against a multilinear regression model. We conduct a qualitative and quantitative comparison of model predictions and examine whether the predictive skill of CNNs can be enhanced by incorporating additional atmospheric variables, such as geopotential height and forecast surface roughness, or static high‐resolution fields, like land–sea mask and topography. We further propose DeepRU, a novel U‐Net‐based CNN architecture, which is able to infer situation‐dependent wind structures that cannot be reconstructed by other models. Inferring a target 9 km resolution wind field from the low‐resolution input fields over the Alpine area takes less than 10 ms on our graphics processing unit target architecture, which compares favorably to an overhead in simulation time of minutes or hours between low‐ and high‐resolution forecast simulations.

Cite this paper

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

APA 7

Höhlein, K., Kern, M., Hewson, T., & Westermann, R. (2020). A comparative study of convolutional neural network models for wind field downscaling. Meteorological Applications, 27(6), e1961. https://doi.org/10.1002/met.1961

MLA 9

Höhlein, Kevin, et al. “A comparative study of convolutional neural network models for wind field downscaling.” Meteorological Applications, vol. 27, no. 6, 2020, p. e1961. https://doi.org/10.1002/met.1961.

Chicago

Höhlein, Kevin, Michael Kern, Timothy Hewson, and Rüdiger Westermann. 2020. “A comparative study of convolutional neural network models for wind field downscaling.” Meteorological Applications 27 (6): e1961. https://doi.org/10.1002/met.1961.

Harvard

Höhlein, K. et al. (2020) ‘A comparative study of convolutional neural network models for wind field downscaling’, Meteorological Applications, 27(6), p. e1961. doi:10.1002/met.1961.

IEEE

K. Höhlein, M. Kern, T. Hewson, and R. Westermann, “A comparative study of convolutional neural network models for wind field downscaling,” Meteorological Applications, vol. 27, no. 6, p. e1961, 2020, doi: 10.1002/met.1961.

BibTeX

@article{hohlein2020comparative,
  title     = {{A comparative study of convolutional neural network models for wind field downscaling}},
  author    = {Höhlein, Kevin and Kern, Michael and Hewson, Timothy and Westermann, Rüdiger},
  journal   = {Meteorological Applications},
  year      = {2020},
  volume    = {27},
  number    = {6},
  pages     = {e1961},
  doi       = {10.1002/met.1961},
  url       = {https://doi.org/10.1002/met.1961}
}

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

Citations by year

YearCitationsShare of the best year
202199
20222222
20232525
20244040
20254444
20263232

Its field-weighted citation impact is 4.18: it has been cited 4.18 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

  • convolutional neural networks
  • U-Net
  • ERA5 reanalysis
  • high-resolution numerical weather prediction
  • multiple linear regression
  • geopotential height
  • surface roughness
  • land-sea mask

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?

Höhlein, K., Kern, M., Hewson, T., & Westermann, R. (2020). A comparative study of convolutional neural network models for wind field downscaling. Meteorological Applications, 27(6), e1961. https://doi.org/10.1002/met.1961

How many times has this paper been cited?

172 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 Meteorological Applications: sign in and open the PDF from this page.

Who wrote this paper?

Kevin Höhlein, Michael Kern, Timothy Hewson, Rüdiger Westermann.

What is the DOI of this paper?

10.1002/met.1961, permanently at https://doi.org/10.1002/met.1961. 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.