EGU2020-7569
https://doi.org/10.5194/egusphere-egu2020-7569
EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Boosting performance in Machine Learning of Turbulent and Geophysical Flows via scale separation

Davide Faranda1,2, Mathieu Vrac1, Pascal Yiou1, Flavio Maria Emanuele Pons1, Adnane Hamid1, Giulia Carella1, Cedric Gacial Ngoungue Langue1, Soulivanh Thao1, and Valerie Gautard3
Davide Faranda et al.
  • 1CNRS, Laboratoire de Science du Climat e de l'Environment, Gif sur Yvette, France
  • 2London Mathematical Laboratory, London, UK
  • 3DRF/IRFU/DEDIP//LILAS Departement d'Electronique des Detecteurs et d'Informatique pour la Physique, CEA Saclay l'Orme des Merisiers, 91191 Gif-sur-Yvette, France

Recent advances in statistical learning have opened the possibility to forecast the behavior of chaotic systems using recurrent neural networks. In this letter we investigate the applicability of this framework to geophysical flows, known to be intermittent and turbulent.  We show that both turbulence and intermittency introduce severe limitations on the applicability of recurrent neural networks, both for short term forecasts as well as for the reconstruction of the underlying attractor. We test these ideas on global sea-level pressure data for the past 40 years, issued from the NCEP reanalysis datase, a proxy of the atmospheric circulation dynamics.  The performance of recurrent neural network in predicting both short and long term behaviors rapidly drops when the systems are perturbed with noise. However, we found that a good predictability is partially recovered when scale separation is performed via a moving average filter. We suggest that possible strategies to overcome limitations  should be based on separating the smooth large-scale dynamics, from the intermittent/turbulent features. 

How to cite: Faranda, D., Vrac, M., Yiou, P., Pons, F. M. E., Hamid, A., Carella, G., Ngoungue Langue, C. G., Thao, S., and Gautard, V.: Boosting performance in Machine Learning of Turbulent and Geophysical Flows via scale separation, EGU General Assembly 2020, Online, 4–8 May 2020, https://doi.org/10.5194/egusphere-egu2020-7569, 2020

Comments on the presentation

AC: Author Comment | CC: Community Comment | Report abuse

Presentation version 1 – uploaded on 28 Apr 2020
  • CC1: Comment on EGU2020-7569, Paul Pukite, 06 May 2020

    The longest continuous sea-level pressure (SLR) time series may be the SOI differential between Tahiti and Darwin which characterizes ENSO.  This is not chaotic as it arises directly from tidal forcing patterns, which are similar to the pattern found in the earth's length-of-day variations but modulated by the ocean's fluid dynamic response.