Enhancing geophysical flow machine learning performance via scale separation

Davide Faranda (1) , Mathieu Vrac (1) , Pascal Yiou (1) , Flavio Maria Emanuele Pons (2) , Adnane Hamid (2) , Giulia Carella (2) , Cedric Ngoungue Langue (2) , Soulivanh Thao (2) , Valerie Gautard (3)

1 ESTIMR - Extrèmes : Statistiques, Impacts et Régionalisation
2 LSCE - Laboratoire des Sciences du Climat et de l'Environnement [Gif-sur-Yvette]
3 DEDIP - Département d'Electronique, des Détecteurs et d'Informatique pour la Physique (ex SEDI)

Recent advances in statistical and machine learning have opened the possibility of forecasting the behaviour of chaotic systems using recurrent neural networks. In this article we investigate the applicability of such a framework to geophysical flows, known to involve multiple scales in length, time and energy and to feature intermittency. We show that both multiscale dynamics and intermittency introduce severe limitations to the applicability of recurrent neural networks, both for short-term forecasts as well as for the reconstruction of the underlying attractor. We suggest that possible strategies to overcome such limitations should be based on separating the smooth large-scale dynamics from the intermittent/small-scale features. We test these ideas on global sea-level pressure data for the past 40 years, a proxy of the atmospheric circulation dynamics. Better short-and longterm forecasts of sea-level pressure data can be obtained with an optimal choice of spatial coarse graining and time filtering.

Domaines: Océan, Atmosphère; Apprentissage [cs.LG]

Davide Faranda, Mathieu Vrac, Pascal Yiou, Flavio Maria Emanuele Pons, Adnane Hamid, et al.. Enhancing geophysical flow machine learning performance via scale separation. Nonlinear Processes in Geophysics, 2021, 28 (3), pp.423 - 443. ⟨10.5194/npg-28-423-2021⟩. ⟨hal-03341712v3⟩