Journal article · 2021 · Open access

MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain

Gabriele Accarino, Marco Chiarelli, Francesco Immorlano, Valeria Aloisi, Andrea Gatto, Giovanni Aloisio

AI, 2(4), 600–620 · Published 19 November 2021 · DOI 10.3390/ai2040036

Open PDFView at the publisherCite this paper

In brief

“MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain” is a 2021 journal article by Gabriele Accarino and 5 co-authors, published in AI. OpenAlex counts 16 citations as of 21 November 2026, which puts it in the top 8% of works published in 2021 by citations. It is open access under a CC BY licence: the full text is free to read at AI.

Citations
16
Most cited in
2024 (7)
Field-weighted impact
0.79
References
66
Authors
6

Abstract

One of the most important open challenges in climate science is downscaling. It is a procedure that allows making predictions at local scales, starting from climatic field information available at large scale. Recent advances in deep learning provide new insights and modeling solutions to tackle downscaling-related tasks by automatically learning the coarse-to-fine grained resolution mapping. In particular, deep learning models designed for super-resolution problems in computer vision can be exploited because of the similarity between images and climatic fields maps. For this reason, a new architecture tailored for statistical downscaling (SD), named MSG-GAN-SD, has been developed, allowing interpretability and good stability during training, due to multi-scale gradient information. The proposed architecture, based on a Generative Adversarial Network (GAN), was applied to downscale ERA-Interim 2-m temperature fields, from 83.25 to 13.87 km resolution, covering the EURO-CORDEX domain within the 1979–2018 period. The training process involves seasonal and monthly dataset arrangements, in addition to different training strategies, leading to several models. Furthermore, a model selection framework is introduced in order to mathematically select the best models during the training. The selected models were then tested on the 2015–2018 period using several metrics to identify the best training strategy and dataset arrangement, which finally produced several evaluation maps. This work is the first attempt to use the MSG-GAN architecture for statistical downscaling. The achieved results demonstrate that the models trained on seasonal datasets performed better than those trained on monthly datasets. This study presents an accurate and cost-effective solution that is able to perform downscaling of 2 m temperature climatic maps.

Cite this paper

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

APA 7

Accarino, G., Chiarelli, M., Immorlano, F., Aloisi, V., Gatto, A., & Aloisio, G. (2021). MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain. AI, 2(4), 600–620. https://doi.org/10.3390/ai2040036

MLA 9

Accarino, Gabriele, et al. “MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain.” AI, vol. 2, no. 4, 2021, pp. 600–620. https://doi.org/10.3390/ai2040036.

Chicago

Accarino, Gabriele, Marco Chiarelli, Francesco Immorlano, Valeria Aloisi, Andrea Gatto, and Giovanni Aloisio. 2021. “MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain.” AI 2 (4): 600–620. https://doi.org/10.3390/ai2040036.

Harvard

Accarino, G. et al. (2021) ‘MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain’, AI, 2(4), pp. 600–620. doi:10.3390/ai2040036.

IEEE

G. Accarino, M. Chiarelli, F. Immorlano, V. Aloisi, A. Gatto, and G. Aloisio, “MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain,” AI, vol. 2, no. 4, pp. 600–620, 2021, doi: 10.3390/ai2040036.

BibTeX

@article{accarino2021multi,
  title     = {{MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain}},
  author    = {Accarino, Gabriele and Chiarelli, Marco and Immorlano, Francesco and Aloisi, Valeria and Gatto, Andrea and Aloisio, Giovanni},
  journal   = {AI},
  year      = {2021},
  volume    = {2},
  number    = {4},
  pages     = {600--620},
  doi       = {10.3390/ai2040036},
  url       = {https://doi.org/10.3390/ai2040036}
}

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

Citations by year

YearCitationsShare of the best year
202222
202322
202477
202533
202622

Its field-weighted citation impact is 0.79: it has been cited 0.79 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

  • statistical downscaling
  • generative adversarial networks
  • 2 m air temperature
  • ERA-Interim reanalysis
  • EURO-CORDEX
  • super-resolution
  • model selection

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?

Accarino, G., Chiarelli, M., Immorlano, F., Aloisi, V., Gatto, A., & Aloisio, G. (2021). MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain. AI, 2(4), 600–620. https://doi.org/10.3390/ai2040036

How many times has this paper been cited?

16 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 AI: sign in and open the PDF from this page.

Who wrote this paper?

Gabriele Accarino, Marco Chiarelli, Francesco Immorlano, Valeria Aloisi, Andrea Gatto, Giovanni Aloisio.

What is the DOI of this paper?

10.3390/ai2040036, permanently at https://doi.org/10.3390/ai2040036. 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.