Neural network based generation of a 1-dimensional stochastic field with turbulent velocity statistics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Physica D: Nonlinear Phenomena Year : 2023

Neural network based generation of a 1-dimensional stochastic field with turbulent velocity statistics

Abstract

We define and study a fully-convolutional neural network stochastic model, NN-Turb, which generates a 1-dimensional field with some turbulent velocity statistics. In particular, the generated process satisfies the Kolmogorov 2/3 law for second order structure function. It also presents negative skewness across scales (i.e. Kolmogorov 4/5 law) and exhibits intermittency as characterized by skewness and flatness. Furthermore, our model is never in contact with turbulent data and only needs the desired statistical behavior of the structure functions across scales for training.
Fichier principal
Vignette du fichier
TurbNNGen_HAL.pdf (941.78 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03861273 , version 1 (19-11-2022)
hal-03861273 , version 2 (12-04-2023)
hal-03861273 , version 3 (06-12-2023)

Identifiers

Cite

Carlos Granero-Belinchon. Neural network based generation of a 1-dimensional stochastic field with turbulent velocity statistics. Physica D: Nonlinear Phenomena, 2023, 458, pp.133997. ⟨10.1016/j.physd.2023.133997⟩. ⟨hal-03861273v3⟩
92 View
56 Download

Altmetric

Share

Gmail Facebook X LinkedIn More