From Deep to Physics-Informed Learning of Turbulence: Diagnostics

10/16/2018
by   Ryan King, et al.
0

We describe physical tests validating progress made toward acceleration and automation of hydrodynamic codes in the regime of developed turbulence by two Deep Learning (DL) Neural Network (NN) schemes trained on Direct Numerical Simulations of turbulence. Even the bare DL solutions, which do not take into account any physics of turbulence explicitly, are impressively good overall when it comes to qualitative description of important features of turbulence. However, the early tests have also uncovered some caveats of the DL approaches. We observe that the static DL scheme, implementing Convolutional GAN and trained on spatial snapshots of turbulence, fails to reproduce intermittency of turbulent fluctuations at small scales and details of the turbulence geometry at large scales. We show that the dynamic NN scheme, LAT-NET, trained on a temporal sequence of turbulence snapshots is capable to correct for the small-scale caveat of the static NN. We suggest a path forward towards improving reproducibility of the large-scale geometry of turbulence with NN.

READ FULL TEXT

page 4

page 8

research
02/12/2021

Physics-Informed Graphical Neural Network for Parameter State Estimations in Power Systems

Parameter Estimation (PE) and State Estimation (SE) are the most wide-sp...
research
05/08/2021

Improving Deep Learning Performance for Predicting Large-Scale Porous-Media Flow through Feature Coarsening

Physics-based simulation for fluid flow in porous media is a computation...
research
10/20/2021

Semi-supervised physics guided deep learning framework for predicting the I-V characteristics of GAN HEMT

This letter proposes a novel deep learning framework (DLF) that addresse...
research
08/09/2020

SEALing Neural Network Models in Secure Deep Learning Accelerators

Deep learning (DL) accelerators are increasingly deployed on edge device...
research
07/02/2022

On the modern deep learning approaches for precipitation downscaling

Deep Learning (DL) based downscaling has become a popular tool in earth ...
research
09/14/2023

Nonlinear model order reduction for problems with microstructure using mesh informed neural networks

Many applications in computational physics involve approximating problem...
research
01/20/2021

Can stable and accurate neural networks be computed? – On the barriers of deep learning and Smale's 18th problem

Deep learning (DL) has had unprecedented success and is now entering sci...

Please sign up or login with your details

Forgot password? Click here to reset