Journal cover Journal topic
Geoscientific Model Development An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 5.154 IF 5.154
  • IF 5-year value: 5.697 IF 5-year
    5.697
  • CiteScore value: 5.56 CiteScore
    5.56
  • SNIP value: 1.761 SNIP 1.761
  • IPP value: 5.30 IPP 5.30
  • SJR value: 3.164 SJR 3.164
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 59 Scimago H
    index 59
  • h5-index value: 49 h5-index 49
Discussion papers
https://doi.org/10.5194/gmd-2019-278
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-2019-278
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: model experiment description paper 28 Oct 2019

Submitted as: model experiment description paper | 28 Oct 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Geoscientific Model Development (GMD).

Configuration and Intercomparison of Deep Learning Neural Models for Statistical Downscaling

Jorge Baño-Medina1, Rodrigo Manzanas2, and José Manuel Gutiérrez1 Jorge Baño-Medina et al.
  • 1Santander Meteorology Group, Institute of Physics of Cantabria (CSIC-Univ. of Cantabria), Santander, Spain
  • 2Santander Meteorology Group, Dpto. de Matemática Aplicada y Ciencias de la Computación, Universidad de Cantabria, Santander, Spain

Abstract. Deep learning techniques (in particular convolutional neural networks, CNNs) have recently emerged as a promising approach for statistical downscaling due to their ability to learn spatial features from huge spatio-temporal datasets. However, existing studies are based on complex models, applied to particular case studies and using simple validation frameworks, which makes difficult a proper assessment of the (possible) added value offered by these techniques. As a result, these models are usually seen as black-boxes generating distrust among the climate community, particularly in climate change problems. In this paper we undertake a comprehensive assessment of deep learning techniques for continental-scale statistical downscaling, building on the VALUE validation framework. In particular, different CNN models of increasing complexity are applied for downscaling temperature and precipitation over Europe, comparing them with a few standard benchmark methods from VALUE (linear and generalized linear models) which have been traditionally used for this purpose. Besides analyzing the adequacy of different components and topologies, we also focus on their extrapolation capability, a critical point for their possible application in climate change studies. To do this, we use a warm test period as surrogate of possible future climate conditions. Our results show that, whilst the added value of CNNs is mostly limited to the reproduction of extremes for temperature, these techniques do outperform the classic ones for the case of precipitation for most aspects considered. This overall good performance, together with the fact that they can be suitably applied to large regions (e.g. continents) without worrying about the spatial features being considered as predictors, can foster the use of statistical approaches in international initiatives such as CORDEX.

Jorge Baño-Medina et al.
Interactive discussion
Status: open (until 23 Dec 2019)
Status: open (until 23 Dec 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Jorge Baño-Medina et al.
Jorge Baño-Medina et al.
Viewed  
Total article views: 229 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
172 55 2 229 2 2
  • HTML: 172
  • PDF: 55
  • XML: 2
  • Total: 229
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 28 Oct 2019)
Cumulative views and downloads (calculated since 28 Oct 2019)
Viewed (geographical distribution)  
Total article views: 132 (including HTML, PDF, and XML) Thereof 132 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 18 Nov 2019
Publications Copernicus
Download
Short summary
In this study we intercompare different deep learning topologies for statistical downscaling purposes. As compared to the top-ranked methods in the largest-to-date downscaling intercomparison study, our results better predict the local climate variability. Moreover, deep learning approaches can be suitably applied to large regions (e.g. continents), which can therefore foster the use of statistical downscaling in flagship initiatives such as CORDEX.
In this study we intercompare different deep learning topologies for statistical downscaling...
Citation