A wavelet-based three-dimensional convolutional neural network for superresolution of turbulent vorticity - Ecole Centrale de Marseille Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A wavelet-based three-dimensional convolutional neural network for superresolution of turbulent vorticity

Résumé

We develop a wavelet-based three-dimensional convolutional neural network (WCNN3d) for superresolution of coarse-grained data of homogeneous isotropic turbulence. The turbulent flow data are computed by high resolution direct numerical simulation (DNS), while the coarse-grained data are obtained by applying a Gaussian filter to the DNS data. The CNNs are trained with the DNS data and the coarse-grained data. We compare vorticity-and velocity-based approaches and assess the proposed WCNN3d method in terms of flow visualization, enstrophy spectra and probability density functions. We show that orthogonal wavelets enhance the efficiency of the learning of CNN.
Fichier principal
Vignette du fichier
ays_proceedings_wccm-xv2022.pdf (1.71 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03739056 , version 1 (26-07-2022)

Identifiants

  • HAL Id : hal-03739056 , version 1

Citer

Tomoki Asaka, Katsunori Yoshimatsu, Kai Schneider. A wavelet-based three-dimensional convolutional neural network for superresolution of turbulent vorticity. 15th World Congress on Computational Mechanics (WCCM-XV), Jul 2022, Yokohama, Japan. ⟨hal-03739056⟩
181 Consultations
45 Téléchargements

Partager

Gmail Facebook X LinkedIn More