Learned turbulence modelling with differentiable fluid solvers: physics-based loss functions and optimisation horizons
From MaRDI portal
Publication:5038552
Abstract: In this paper, we train turbulence models based on convolutional neural networks. These learned turbulence models improve under-resolved low resolution solutions to the incompressible Navier-Stokes equations at simulation time. Our study involves the development of a differentiable numerical solver that supports the propagation of optimisation gradients through multiple solver steps. The significance of this property is demonstrated by the superior stability and accuracy of those models that unroll more solver steps during training. Furthermore, we introduce loss terms based on turbulence physics that further improve the model accuracy. This approach is applied to three two-dimensional turbulence flow scenarios, a homogeneous decaying turbulence case, a temporally evolving mixing layer, and a spatially evolving mixing layer. Our models achieve significant improvements of long-term a-posteriori statistics when compared to no-model simulations, without requiring these statistics to be directly included in the learning targets. At inference time, our proposed method also gains substantial performance improvements over similarly accurate, purely numerical methods.
Recommendations
- Physics-guided deep learning for generating turbulent inflow conditions
- Deep learning observables in computational fluid dynamics
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Learning by neural networks under physical constraints for simulation in fluid mechanics
- Physics-Driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
- Physics-informed neural networks for the Reynolds-averaged Navier-Stokes modeling of Rayleigh-Taylor turbulent mixing
- Deep reinforcement learning of viscous incompressible flow
- Operator inference and physics-informed learning of low-dimensional models for incompressible flows
- Deep learning of the spanwise-averaged Navier-Stokes equations
Cites work
- scientific article; zbMATH DE number 1172030 (Why is no real title available?)
- A dynamic eddy-viscosity closure model for large eddy simulations of two-dimensional decaying turbulence
- Comparison of the SMAC, PISO and iterative time-advancing schemes for unsteady flows
- DPM: a deep learning PDE augmentation method with application to large-eddy simulation
- Direct simulation of a self-similar turbulent mixing layer
- High-Re solutions for incompressible flow using the Navier-Stokes equations and a multigrid method
- High-order methods for decaying two-dimensional homogeneous isotropic turbulence
- Neural networks based subgrid scale modeling in large eddy simulations
- Numerical simulation of developing and decaying two-dimensional turbulence
- On the inviscid instability of the hyperbolictangent velocity profile
- Prediction of aerodynamic flow fields using convolutional neural networks
- Recent advances on the numerical modelling of turbulent flows
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Sensitivity of two-dimensional spatially developing mixing layers with respect to uncertain inflow conditions
- Solution of the implicitly discretized fluid flow equations by operator- splitting
- Split energy-helicity cascades in three-dimensional homogeneous and isotropic turbulence
- Subgrid modelling for two-dimensional turbulence using neural networks
- Toward neural-network-based large eddy simulation: application to turbulent channel flow
- Turbulence modeling in the age of data
- Turbulent Flows
Cited in
(16)- Turbulence scaling from deep learning diffusion generative models
- A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
- Unsupervised deep learning for super-resolution reconstruction of turbulence
- Combining direct and indirect sparse data for learning generalizable turbulence models
- A transformer-based convolutional method to model inverse cascade in forced two-dimensional turbulence
- JAX-fluids: a fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flows
- Dynamic calibration of differential equations using machine learning, with application to turbulence models
- Ensemble Gradient for Learning Turbulence Models from Indirect Observations
- Towards high-accuracy deep learning inference of compressible flows over aerofoils
- Comparison of neural closure models for discretised PDEs
- A multifidelity deep operator network approach to closure for multiscale systems
- Differentiable hybrid neural modeling for fluid-structure interaction
- Differentiability in unrolled training of neural physics simulators on transient dynamics
- Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence
- A physics-informed learning approach to Bernoulli-type free boundary problems
- Super-resolution of turbulence with dynamics in the loss
This page was built for publication: Learned turbulence modelling with differentiable fluid solvers: physics-based loss functions and optimisation horizons
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5038552)
