Séminaire
Recent advances in statistical learning have opened the possibility to forecast the behavior of chaotic systems using recurrent neural network. 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 network 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 intemittent/turbulent features.
Authors: D. Faranda, A. Hamid, G. Carella, C.G. Ngoungue Langue, F.M.E. Pons, M. Vrac, S. Thao, M. Rabarivola, V. Gautard, P. Yiou
helene.rouby@ens.fr