Journal article · 2024 · Open access

On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation

Antoine Doury, Samuel Somot, Sébastien Gadat

Climate Dynamics, 62(9), 8587–8613 · Published 26 July 2024 · DOI 10.1007/s00382-024-07350-8

Open PDFCite this paper

In brief

“On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation” is a 2024 journal article by Antoine Doury and 2 co-authors, published in Climate Dynamics. OpenAlex counts 52 citations as of 21 November 2026, which puts it in the top 1% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Climate Dynamics.

Citations
52
Most cited in
2026 (21)
Field-weighted impact
5.45
References
43
Authors
3

Abstract

High resolution regional climate models (RCM) are necessary to capture local precipitation but are too expensive to fully explore the uncertainties associated with future projections. To resolve the large cost of RCMs, Doury et al. (2023) proposed a neural network based RCM-emulator for the near-surface temperature, at a daily and 12 km-resolution. It uses existing RCM simulations to learn the relationship between low-resolution predictors and high resolution surface variables. When trained the emulator can be applied to any low resolution simulation to produce ensembles of high resolution emulated simulations. This study assesses the suitability of applying the RCM-emulator for precipitation thanks to a novel asymmetric loss function to reproduce the entire precipitation distribution over any grid point. Under a perfect conditions framework, the resulting emulator shows striking ability to reproduce the RCM original series with an excellent spatio-temporal correlation. In particular, a very good behaviour is obtained for the two tails of the distribution, measured by the number of dry days and the 99th quantile. Moreover, it creates consistent precipitation objects even if the highest frequency details are missed. The emulator quality holds for all simulations of the same RCM, with any driving GCM, ensuring transferability of the tool to GCMs never downscaled by the RCM. A first showcase of downscaling GCM simulations showed that the RCM-emulator brings significant added-value with respect to the GCM as it produces the correct high resolution spatial structure and heavy precipitation intensity. Nevertheless, further work is needed to establish a relevant evaluation framework for GCM applications.

Cite this paper

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

APA 7

Doury, A., Somot, S., & Gadat, S. (2024). On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation. Climate Dynamics, 62(9), 8587–8613. https://doi.org/10.1007/s00382-024-07350-8

MLA 9

Doury, Antoine, et al. “On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation.” Climate Dynamics, vol. 62, no. 9, 2024, pp. 8587–8613. https://doi.org/10.1007/s00382-024-07350-8.

Chicago

Doury, Antoine, Samuel Somot, and Sébastien Gadat. 2024. “On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation.” Climate Dynamics 62 (9): 8587–8613. https://doi.org/10.1007/s00382-024-07350-8.

Harvard

Doury, A., Somot, S. and Gadat, S. (2024) ‘On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation’, Climate Dynamics, 62(9), pp. 8587–8613. doi:10.1007/s00382-024-07350-8.

IEEE

A. Doury, S. Somot, and S. Gadat, “On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation,” Climate Dynamics, vol. 62, no. 9, pp. 8587–8613, 2024, doi: 10.1007/s00382-024-07350-8.

BibTeX

@article{doury2024suitability,
  title     = {{On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation}},
  author    = {Doury, Antoine and Somot, Samuel and Gadat, Sébastien},
  journal   = {Climate Dynamics},
  year      = {2024},
  volume    = {62},
  number    = {9},
  pages     = {8587--8613},
  doi       = {10.1007/s00382-024-07350-8},
  url       = {https://doi.org/10.1007/s00382-024-07350-8}
}

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

Citations by year

YearCitationsShare of the best year
20241111
20252020
20262121

Its field-weighted citation impact is 5.45: it has been cited 5.45 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

  • convolutional neural networks
  • precipitation downscaling
  • asymmetric loss functions
  • precipitation distribution
  • high-resolution precipitation
  • GCM downscaling
  • transferability
  • heavy rainfall

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?

Doury, A., Somot, S., & Gadat, S. (2024). On the suitability of a convolutional neural network based RCM-emulator for fine spatio-temporal precipitation. Climate Dynamics, 62(9), 8587–8613. https://doi.org/10.1007/s00382-024-07350-8

How many times has this paper been cited?

52 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 Climate Dynamics: sign in and open the PDF from this page.

Who wrote this paper?

Antoine Doury, Samuel Somot, Sébastien Gadat.

What is the DOI of this paper?

10.1007/s00382-024-07350-8, permanently at https://doi.org/10.1007/s00382-024-07350-8. 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.