English
Related papers

Related papers: A machine learning framework for LES closure terms

200 papers

Numerical simulations of atmospheric circulation models are limited by their finite spatial resolution, and so large eddy simulation (LES) is the preferred approach to study these models. In LES a low-pass filter is applied to the flow…

Fluid Dynamics · Physics 2016-04-27 Leila N. Azadani , Anne E. Staples

Neural networks offer highly expressive turbulence closures, yet their complexity obscures the physical mechanisms they aim to model, and their computational cost can limit their tractability. To address these limitations, we introduce a…

Fluid Dynamics · Physics 2026-04-29 Samantha Friess , Aviral Prakash , John A. Evans

The spread of machine learning techniques coupled with the availability of high-quality experimental and numerical data has significantly advanced numerous applications in fluid mechanics. Notable among these are the development of data…

The explicit filtering method for large eddy simulation (LES,) which comprises integration of the governing equations without any added terms for sub-grid-scale modeling, and the application of a low-pass filter to transported fields, is…

Fluid Dynamics · Physics 2017-10-06 Joseph Mathew

Achievement of solutions in Navier-Stokes equation is one of challenging quests, especially for its closure problem. For achievement of particular solutions, there are variety of numerical simulations including Direct Numerical Simulation…

Computational Physics · Physics 2018-11-13 Jinu Lee , Sangseung Lee , Donghyun You

Gas-particle flows are commonly simulated through two-fluid model at industrial-scale. However, these simulations need very fine grid to have accurate flow predictions, which is prohibitively demanding in terms of computational resources.…

Deep learning is increasingly becoming a promising pathway to improving the accuracy of sub-grid scale (SGS) turbulence closure models for large eddy simulations (LES). We leverage the concept of differentiable turbulence, whereby an…

Deep learning approaches have shown remarkable promise in turbulence closure modeling for large eddy simulations (LES). The differentiable physics paradigm uses the so-called a-posteriori approach for learning by embedding a neural network…

Fluid Dynamics · Physics 2026-04-30 Ashwin Suriyanarayanan , Dibyajyoti Chakraborty , Romit Maulik

Deconvolutional artificial neural network (DANN) models are developed for subgrid-scale (SGS) stress in large eddy simulation (LES) of turbulence. The filtered velocities at different spatial points are used as input features of the DANN…

Fluid Dynamics · Physics 2020-12-02 Zelong Yuan , Chenyue Xie , Jianchun Wang

Despite the increasing availability of high-performance computational resources, Reynolds-Averaged Navier-Stokes (RANS) simulations remain the workhorse for the analysis of turbulent flows in real-world applications. Linear eddy viscosity…

Fluid Dynamics · Physics 2023-11-27 Leon Riccius , Atul Agrawal , Phaedon-Stelios Koutsourelakis

Despite well-known limitations of Reynolds-averaged Navier-Stokes (RANS) simulations, this methodology remains the most widely used tool for predicting many turbulent flows, due to computational efficiency. Machine learning is a promising…

Fluid Dynamics · Physics 2022-03-14 Ryley McConkey , Eugene Yee , Fue-Sang Lien

Extending gradient-type turbulence closures to turbulent premixed flames is challenging due to the significant influence of combustion heat release. We incorporate a deep neural network (DNN) into Reynolds-averaged Navier--Stokes (RANS)…

Fluid Dynamics · Physics 2025-06-18 Priyesh Kakka , Jonathan F. MacArt

Turbulence is ubiquitous in engineering and science, yet direct simulation is prohibitively expensive. The Reynolds-averaged Navier-Stokes (RANS) equations provide savings exceeding ten orders of magnitude but introduce unclosed terms (the…

Fluid Dynamics · Physics 2026-05-27 Daniel Dehtyriov , Jonathan F. MacArt , Justin Sirignano

This work presents a converged framework of Machine-Learning Assisted Turbulence Modeling (MLATM). Our objective is to develop a turbulence model directly learning from high fidelity data (DNS/LES) with eddy-viscosity hypothesis induced.…

Fluid Dynamics · Physics 2019-07-09 Weishuo Liu , Jian Fang , Stefano Rolfo , Lipeng Lu

Deep learning (DL) has demonstrated promise for accelerating and enhancing the accuracy of flow physics simulations, but progress is constrained by the scarcity of high-fidelity training data, which is costly to generate and inherently…

Fluid Dynamics · Physics 2025-10-06 Daniel Dehtyriov , Jonathan F. MacArt , Justin Sirignano

This work presents a methodology to predict a near-optimal spacing function, which defines the element sizes, suitable to perform steady RANS turbulent viscous flow simulations. The strategy aims at utilising existing high fidelity…

Computational Engineering, Finance, and Science · Computer Science 2024-06-25 Sergi Sanchez-Gamero , Oubay Hassan , Ruben Sevilla

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…

Fluid Dynamics · Physics 2025-11-12 Hojin Kim , Varun Shankar , Venkatasubramanian Viswanathan , Romit Maulik

We present two families of sub-grid scale (SGS) turbulence models developed for large-eddy simulation (LES) purposes. Their development required the formulation of physics-informed robust and efficient Deep Learning (DL) algorithms which,…

Fluid Dynamics · Physics 2023-07-20 Rikhi Bose , Arunabha M. Roy

Explicit filters play a pivotal role in the scale separation and numerical stability of advanced Large Eddy Simulation (LES) closures, such as dynamic eddy-viscosity or Approximate Deconvolution (AD) methods. In the present study, it is…

Fluid Dynamics · Physics 2026-02-25 Mohammad Bagher Molaei , Ehsan Amani , Morteza Ghorbani

Channel-configuration search, the optimization of layer specifications such as channel widths in deep neural networks, presents a combinatorial challenge constrained by tensor-shape compatibility and computational budgets. We investigate…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Tolgay Atinc Uzun , Dmitry Ignatov , Radu Timofte