Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
Top Cited Papers
Open Access
- 1 July 2023
- journal article
- research article
- Published by AIP Publishing in Physics of Fluids
- Vol. 35 (7)
Abstract
Long-term predictions of nonlinear dynamics of three-dimensional (3D) turbulence are very challenging for machine learning approaches. In this paper, we propose an implicit U-Net enhanced Fourier neural operator (IU-FNO) for stable and efficient predictions on the long-term large-scale dynamics of turbulence. The IU-FNO model employs implicit recurrent Fourier layers for deeper network extension and incorporates the U-net network for the accurate prediction on small-scale flow structures. The model is systematically tested in large-eddy simulations of three types of 3D turbulence, including forced homogeneous isotropic turbulence, temporally evolving turbulent mixing layer, and decaying homogeneous isotropic turbulence. The numerical simulations demonstrate that the IU-FNO model is more accurate than other FNO-based models, including vanilla FNO, implicit FNO (IFNO), and U-Net enhanced FNO (U-FNO), and dynamic Smagorinsky model (DSM) in predicting a variety of statistics, including the velocity spectrum, probability density functions of vorticity and velocity increments, and instantaneous spatial structures of flow field. Moreover, IU-FNO improves long-term stable predictions, which has not been achieved by the previous versions of FNO. Moreover, the proposed model is much faster than traditional large-eddy simulation with the DSM model and can be well generalized to the situations of higher Taylor–Reynolds numbers and unseen flow regime of decaying turbulence.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (No.91952104, No.92052301, No.12172161, No.91752201)
- NSFC Basic Science Center Program (grant no.11988102)
- Shenzhen Science and Technology Program (Grants No.KQTD20180411143441009)
- Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Grants No.GML2019ZD0103)
- Department of Science and Technology of Guangdong Province (No.2020B1212030001)
This publication has 81 references indexed in Scilit:
- Study of High–Reynolds Number Isotropic Turbulence by Direct Numerical SimulationAnnual Review of Fluid Mechanics, 2009
- On coherent-vortex identification in turbulenceJournal of Turbulence, 2000
- Scale-Invariance and Turbulence Models for Large-Eddy SimulationAnnual Review of Fluid Mechanics, 2000
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- New Trends in Large-Eddy Simulations of TurbulenceAnnual Review of Fluid Mechanics, 1996
- On the properties of similarity subgrid-scale models as deduced from measurements in a turbulent jetJournal of Fluid Mechanics, 1994
- Turbulence: the filtering approachJournal of Fluid Mechanics, 1992
- A proposed modification of the Germano subgrid-scale closure methodPhysics of Fluids A: Fluid Dynamics, 1992
- Spectral Methods in Fluid DynamicsAnnual Review of Fluid Mechanics, 1987
- Evaluation of subgrid-scale models using an accurately simulated turbulent flowJournal of Fluid Mechanics, 1979