Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

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

Carlos Granero-Belinchon 1, 2, 3 
1 ODYSSEY - Océan Dynamique Observations Analyse
UBO UFR ST - Université de Bretagne Occidentale - UFR Sciences et Techniques, UR1 - Université de Rennes 1, IFREMER - Institut Français de Recherche pour l'Exploitation de la Mer, Inria Rennes – Bretagne Atlantique , IMT Atlantique - IMT Atlantique
3 Lab-STICC_OSE - Equipe Observations Signal & Environnement
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
Abstract : We define and study a fully-convolutional neural network stochastic model, NN-Turb, which generates 1-dimensional fields with turbulent velocity statistics. Thus, 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. 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03861273
Contributor : Carlos Granero Belinchon Connect in order to contact the contributor
Submitted on : Saturday, November 19, 2022 - 4:46:12 PM
Last modification on : Wednesday, November 23, 2022 - 4:07:27 AM

Files

TurbNNGen_HAL_18112022.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03861273, version 1
  • ARXIV : 2211.11580

Citation

Carlos Granero-Belinchon. Neural network based generation of 1-dimensional stochastic fields with turbulent velocity statistics. {date}. ⟨hal-03861273⟩

Share

Metrics

Record views

0

Files downloads

0