English
Related papers

Related papers: Finding Closure Terms Directly from Coarse Data fo…

200 papers

From the simplest models to complex deep neural networks, modeling turbulence with machine learning techniques still offers multiple challenges. In this context, the present contribution proposes a robust strategy using patch-based training…

Fluid Dynamics · Physics 2021-10-27 Aakash Patil , Jonathan Viquerat , George El Haber , Elie Hachem

We present data driven kinematic models for the motion of bubbles in high-Re turbulent fluid flows based on recurrent neural networks with long-short term memory enhancements. The models extend empirical relations, such as Maxey-Riley (MR)…

Fluid Dynamics · Physics 2019-10-07 Zhong Yi Wan , Petr Karnakov , Petros Koumoutsakos , Themistoklis P. Sapsis

Simulations of turbulent fluid flow around long cylindrical structures are computationally expensive because of the vast range of length scales, requiring simplifications such as dimensional reduction. Current dimensionality reduction…

Fluid Dynamics · Physics 2021-02-25 Bernat Font , Gabriel D. Weymouth , Vinh-Tan Nguyen , Owen R. Tutty

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 study the statistical properties of stationary, isotropic and homogeneous turbulence in two-dimensional (2D) flows, focusing on the direct cascade, that is on wave-numbers large compared to the integral scale, where both energy and…

Statistical Mechanics · Physics 2024-08-29 Malo Tarpin , Léonie Canet , Carlo Pagani , Nicolás Wschebor

Machine-learning (ML) techniques provide a new and encouraging perspective for constructing turbulence models for Reynolds-averaged Navier--Stokes (RANS) simulations. In this study, an iterative ML-RANS computational framework is proposed…

Fluid Dynamics · Physics 2021-07-27 Weishuo Liu , Jian Fang , Stefano Rolfo , Charles Moulinec , David R Emerson

Super-resolution of turbulence is a term used to describe the prediction of high-resolution snapshots of a flow from coarse-grained observations. This is typically accomplished with a deep neural network and training usually requires a…

Fluid Dynamics · Physics 2024-10-29 Jacob Page

We propose a physics-constrained machine learning method-based on reservoir computing- to time-accurately predict extreme events and long-term velocity statistics in a model of turbulent shear flow. The method leverages the strengths of two…

Fluid Dynamics · Physics 2021-04-14 Nguyen Anh Khoa Doan , Wolfgang Polifke , Luca Magri

Standard kernel methods for machine learning usually struggle when dealing with large datasets. We review a recently introduced Structured Deep Kernel Network (SDKN) approach that is capable of dealing with high-dimensional and huge…

Machine Learning · Computer Science 2022-10-31 Tizian Wenzel , Marius Kurz , Andrea Beck , Gabriele Santin , Bernard Haasdonk

We investigate the application of artificial neural networks to stabilize proper orthogonal decomposition based reduced order models for quasi-stationary geophysical turbulent flows. An extreme learning machine concept is introduced for…

Fluid Dynamics · Physics 2018-05-09 Omer San , Romit Maulik

We parameterize sub-grid scale (SGS) fluxes in sinusoidally forced two-dimensional turbulence on the $\beta$-plane at high Reynolds numbers (Re$\sim$25000) using simple 2-layer Convolutional Neural Networks (CNN) having only…

Fluid Dynamics · Physics 2023-04-12 Kaushik Srinivasan , Mickael D. Chekroun , James C. McWilliams

A convolutional encoder-decoder-based transformer model is proposed for autoregressively training on spatio-temporal data of turbulent flows. The prediction of future fluid flow fields is based on the previously predicted fluid flow field…

Fluid Dynamics · Physics 2023-03-31 Aakash Patil , Jonathan Viquerat , Elie Hachem

The question of whether significant sub-volumes of a turbulent flow can be identified by automatic means, independently of a-priori assumptions, is addressed using the example of two-dimensional decaying turbulence. Significance is defined…

Fluid Dynamics · Physics 2018-09-10 Javier Jimenez

This work determines the inaccuracy of using Reynolds averaged Navier Stokes (RANS) turbulence models in transition to turbulent flow regimes by predicting the model-based discrepancies between RANS and large eddy simulation (LES) models…

Fluid Dynamics · Physics 2019-01-21 Mustafa Usta , Ali Tosyali

A rapid predictive tool based on the linearised Reynolds-averaged Navier-Stokes equations is proposed in this work to investigate secondary currents generated by streamwise-independent surface topography modulations in turbulent channel…

Fluid Dynamics · Physics 2022-07-13 Gerardo Zampino , Davide Lasagna , Bharathram Ganapathisubramani

A framework for deriving probabilistic data-driven closure models is proposed for coarse-grained numerical simulations of turbulence in statistically stationary state. The approach unites the ideal large-eddy simulation model and data…

Fluid Dynamics · Physics 2025-03-25 Sagy Ephrati

The sudden arrest of flow by formation of a stable arch over an outlet is a unique and characteristic feature of granular materials. Previous work suggests that grains near the outlet randomly sample configurational flow microstates until a…

Soft Condensed Matter · Physics 2024-07-09 Jesse M. Hanlan , Sam Dillavou , Andrea J. Liu , Douglas J. Durian

We present a new turbulent data reconstruction method with supervised machine learning techniques inspired by super resolution and inbetweening, which can recover high-resolution turbulent flows from grossly coarse flow data in space and…

Fluid Dynamics · Physics 2021-01-25 Kai Fukami , Koji Fukagata , Kunihiko Taira

A probabilistic machine learning model is introduced to augment the $k-\omega\ SST$ turbulence model in order to improve the modelling of separated flows and the generalisability of learnt corrections. Increasingly, machine learning methods…

Computational Engineering, Finance, and Science · Computer Science 2023-01-24 Joel Ho , Nick Pepper , Tim Dodwell

This proposed work introduces a data-assimilation-assisted approach to train neural networks, aimed at effectively reducing epistemic uncertainty in state estimates of separated flows. This method, referred to as model-consistent training,…

Fluid Dynamics · Physics 2024-08-02 Minghan Chu