Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Hojin, Shankar, Varun, Viswanathan, Venkatasubramanian, Maulik, Romit
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912699181432832
author Kim, Hojin
Shankar, Varun
Viswanathan, Venkatasubramanian
Maulik, Romit
author_facet Kim, Hojin
Shankar, Varun
Viswanathan, Venkatasubramanian
Maulik, Romit
contents Differentiable physical simulators are proving to be valuable tools for developing data-driven models for computational fluid dynamics (CFD). In particular, these simulators enable end-to-end training of machine learning (ML) models embedded within CFD solvers. This paradigm enables novel algorithms which combine the generalization power and low cost of physics-based simulations with the flexibility and automation of deep learning methods. In this study, we introduce a framework for embedding deep learning models within a finite element solver for incompressible Navier-Stokes equations, specifically applying this approach to learn a subgrid-scale (SGS) closure with a graph neural network (GNN). We first demonstrate the feasibility of the approach on flow over a two-dimensional backward-facing step, using it as a proof of concept to show that solver-consistent training produces stable and physically meaningful closures. Then, we extend this to a turbulent flow over a three-dimensional backward-facing step. In this setting, the GNN-based closure not only attains low prediction errors, but also recovers key turbulence statistics and preserves multiscale turbulent structures. We further demonstrate that the closure can be identified in data-limited learning scenarios as well. Overall, the proposed end-to-end learning paradigm offers a viable pathway toward physically consistent and generalizable data-driven SGS modeling on complex and unstructured domains.
format Preprint
id arxiv_https___arxiv_org_abs_2307_13533
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics
Kim, Hojin
Shankar, Varun
Viswanathan, Venkatasubramanian
Maulik, Romit
Fluid Dynamics
Machine Learning
Differentiable physical simulators are proving to be valuable tools for developing data-driven models for computational fluid dynamics (CFD). In particular, these simulators enable end-to-end training of machine learning (ML) models embedded within CFD solvers. This paradigm enables novel algorithms which combine the generalization power and low cost of physics-based simulations with the flexibility and automation of deep learning methods. In this study, we introduce a framework for embedding deep learning models within a finite element solver for incompressible Navier-Stokes equations, specifically applying this approach to learn a subgrid-scale (SGS) closure with a graph neural network (GNN). We first demonstrate the feasibility of the approach on flow over a two-dimensional backward-facing step, using it as a proof of concept to show that solver-consistent training produces stable and physically meaningful closures. Then, we extend this to a turbulent flow over a three-dimensional backward-facing step. In this setting, the GNN-based closure not only attains low prediction errors, but also recovers key turbulence statistics and preserves multiscale turbulent structures. We further demonstrate that the closure can be identified in data-limited learning scenarios as well. Overall, the proposed end-to-end learning paradigm offers a viable pathway toward physically consistent and generalizable data-driven SGS modeling on complex and unstructured domains.
title Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics
topic Fluid Dynamics
Machine Learning
url https://arxiv.org/abs/2307.13533