OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Producing realistic climate data with GANs

Besombes, Camille and Pannekoucke, Olivier and Lapeyre, Corentin and Sanderson, Benjamin and Thual, Olivier Producing realistic climate data with GANs. ( In Press: 2021) Nonlinear Processes in Geophysics. ISSN 1023-5809

[img] (Document in English)

PDF (Publisher's version) - Depositor and staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
12MB

Official URL: https://doi.org/10.5194/npg-2021-6

Abstract

This paper investigates the potential of a Wasserstein Generative Adversarial Networks to produce realistic weather situations when trained from the climate of a general circulation model (GCM). To do so, a convolutional neural network architecture is proposed for the generator and trained on a synthetic climate database, computed using a simple 3 dimensional climate model: PLASIM. The generator transforms a "latent space", defined by a 64 dimensional Gaussian distribution, into spatially defined anomalies on the same output grid as PLASIM. The analysis of the statistics in the leading empirical orthogonal functions shows that the generator is able to reproduce many aspects of the multivariate distribution of the synthetic climate. Moreover, generated states reproduce the leading geostrophic balance present in the atmosphere. The ability to represent the climate state in a compact, dense and potentially nonlinear latent space opens new perspectives in the analysis and the handling of the climate. This contribution discusses the exploration of the extremes close to a given state and how to connect two realistic weather situations with this approach.

Item Type:Article
Additional Information:Thanks to EGU publications. This article is available at: https://npg.copernicus.org. This is an open access article under the Creative Commons Attribution (CC BY 4.0) license, which permits others to distribute, remix,adapt and build upon this work, for commercial use, provided theoriginal work is properly cited.
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Other partners > Centre Européen de Recherche et Formation Avancées en Calcul Scientifique - CERFACS (FRANCE)
Other partners > Météo France (FRANCE)
Laboratory name:
Statistics:download
Deposited On:25 Mar 2021 10:25

Repository Staff Only: item control page