☆ 4.3 Article

Toward learning Lattice Boltzmann collision operators

EUROPEAN PHYSICAL JOURNAL E (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Interdisciplinary Applications

Neural-network based collision operators for the Boltzmann equation

Sean T. Miller et al.

Summary: In this work, a data-driven neural network model is developed to enhance a simple and inexpensive BGK collision operator through a machine-learned correction term, improving the accuracy of the operator with minimal increase in overall runtime.

JOURNAL OF COMPUTATIONAL PHYSICS (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Numerical proof of shell model turbulence closure

Giulio Ortali et al.

Summary: The development of turbulence closure models is a challenging task with significant practical relevance. We propose a closure model based on deep recurrent neural networks that accurately reproduces the statistical characteristics of turbulence. This approach could be applied to three-dimensional Navier-Stokes turbulence.

PHYSICAL REVIEW FLUIDS (2022)

Add to Collection

Review Engineering, Mechanical

Applying machine learning to study fluid mechanics

Steven L. Brunton

Summary: This paper provides a short overview of using machine learning to build data-driven models in fluid mechanics, breaking down the process into five stages and discussing embedding prior physical knowledge into each stage with specific examples.

ACTA MECHANICA SINICA (2021)

Add to Collection

Article Engineering, Chemical

ML-LBM: Predicting and Accelerating Steady State Flow Simulation in Porous Media with Convolutional Neural Networks

Ying Da Wang et al.

Summary: This study proposes an integrated method that combines fast fluid flow predictions with accurate but time-consuming direct flow simulation to reduce computation time without sacrificing accuracy. By training a convolutional neural network, accurate permeability estimation can be achieved in steady state flow simulations in porous media, while the velocity fields themselves are prone to errors and unsuitable for further transport studies.

TRANSPORT IN POROUS MEDIA (2021)

Add to Collection

Article Multidisciplinary Sciences

Deep learning velocity signals allow quantifying turbulence intensity

Alessandro Corbetta et al.

Summary: The study demonstrates that deep neural networks can accurately estimate Reynolds number with higher precision in small sample sizes, compared to conventional physics-based statistical estimators.

SCIENCE ADVANCES (2021)

Add to Collection

Article Physics, Fluids & Plasmas

Physics-informed machine learning of the Lagrangian dynamics of velocity gradient tensor

Yifeng Tian et al.

Summary: This study develops reduced models for the Lagrangian dynamics of the velocity gradient tensor (VGT) in homogeneous isotropic turbulence using the physics-informed machine learning (PIML) framework, trained and validated on Lagrangian data from high-Reynolds number direct numerical simulation (DNS). The PIML models provide an improved representation for the small-scale pressure Hessian contributions, with good agreement with DNS data, but challenges in modeling inertial range dynamics suggest a need for a richer strategy.

PHYSICAL REVIEW FLUIDS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Lettuce: PyTorch-Based Lattice Boltzmann Framework

Mario Christopher Bedrunka et al.

Summary: The lattice Boltzmann method (LBM) is an efficient simulation technique for computational fluid mechanics that is easily compatible with modern machine learning architectures. Lettuce, a PyTorch-based LBM code, enables GPU accelerated calculations, rapid prototyping of models, and integration with deep learning. Researchers explore the possible connections between machine learning and LBM through the development of neural collision models and demonstration of PyTorch's automatic differentiation benefits in flow control and optimization.

HIGH PERFORMANCE COMPUTING - ISC HIGH PERFORMANCE DIGITAL 2021 INTERNATIONAL WORKSHOPS (2021)

Add to Collection

Review Physics, Applied

Physics-informed machine learning

George Em Karniadakis et al.

Summary: Physics-informed learning seamlessly integrates data and mathematical models through neural networks or kernel-based regression networks for accurate inference of realistic and high-dimensional multiphysics problems. Challenges remain in incorporating noisy data seamlessly, complex mesh generation, and addressing high-dimensional problems.

NATURE REVIEWS PHYSICS (2021)

Add to Collection

Article Mechanics

Controlling Rayleigh-Benard convection via reinforcement learning

Gerben Beintema et al.

JOURNAL OF TURBULENCE (2020)

Add to Collection

Article Multidisciplinary Sciences

Efficient supersonic flow simulations using lattice Boltzmann methods based on numerical equilibria

Jonas Latt et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2020)

Add to Collection

Review Physics, Multidisciplinary

Relativistic lattice Boltzmann methods: Theory and applications

A. Gabbana et al.

PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS (2020)

Add to Collection

Article Mechanics

Spatio-temporal deep learning models of 3D turbulence with physics informed diagnostics

Arvind T. Mohan et al.

JOURNAL OF TURBULENCE (2020)

Add to Collection

Review Mechanics

Turbulence Modeling in the Age of Data

Karthik Duraisamy et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 51 (2019)

Add to Collection

Review Computer Science, Interdisciplinary Applications

Towards Exascale Lattice Boltzmann computing

S. Succi et al.

COMPUTERS & FLUIDS (2019)

Add to Collection

Article Mechanics

Super-resolution reconstruction of turbulent flows with machine learning

Kai Fukami et al.

JOURNAL OF FLUID MECHANICS (2019)

Add to Collection

Article Computer Science, Software Engineering

Deep Fluids: A Generative Network for Parameterized Fluid Simulations

Byungsoo Kim et al.

COMPUTER GRAPHICS FORUM (2019)

Add to Collection

Article Physics, Fluids & Plasmas

Comprehensive comparison of collision models in the lattice Boltzmann framework: Theoretical investigations

Christophe Coreixas et al.

PHYSICAL REVIEW E (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Lattice Boltzmann method for semiclassical fluids

Rodrigo C. V. Coelho et al.

COMPUTERS & FLUIDS (2018)

Add to Collection

Article Physics, Fluids & Plasmas

Half-range lattice Boltzmann models for the simulation of Couette flow using the Shakhov collision term

Victor E. Ambrus et al.

PHYSICAL REVIEW E (2018)

Add to Collection

Article Mechanics

High-order regularization in lattice-Boltzmann equations

Keijo K. Mattila et al.

PHYSICS OF FLUIDS (2017)

Add to Collection

Article Physics, Fluids & Plasmas

Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data

Jian-Xun Wang et al.

PHYSICAL REVIEW FLUIDS (2017)

Add to Collection

Article Mechanics

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

Julia Ling et al.

JOURNAL OF FLUID MECHANICS (2016)

Add to Collection

Article Computer Science, Interdisciplinary Applications

The mathematical structure of the lattices of the lattice Boltzmann method

Xiaowen Shan

JOURNAL OF COMPUTATIONAL SCIENCE (2016)

Add to Collection

Article Mechanics

Lattice ellipsoidal statistical BGK model for thermal non-equilibrium flows

Jianping Meng et al.

JOURNAL OF FLUID MECHANICS (2013)

Add to Collection

Article Thermodynamics

A Lattice Boltzmann Formulation for the Analysis of Radiative Heat Transfer Problems in a Participating Medium

Pietro Asinari et al.

NUMERICAL HEAT TRANSFER PART B-FUNDAMENTALS (2010)

Add to Collection

Article Physics, Fluids & Plasmas

General solution of lattices for Cartesian lattice Bhatanagar-Gross-Krook models

Xiaowen Shan

PHYSICAL REVIEW E (2010)

Add to Collection

Article Mechanics

Lattice Boltzmann methods for thermal flows: Continuum limit and applications to compressible Rayleigh-Taylor systems

A. Scagliarini et al.

PHYSICS OF FLUIDS (2010)

Add to Collection

Article Physics, Fluids & Plasmas

Generalized lattice Boltzmann method with multirange pseudopotential

M. Sbragaglia et al.

PHYSICAL REVIEW E (2007)

Add to Collection

Article Physics, Fluids & Plasmas

Efficient kinetic method for fluid simulation beyond the Navier-Stokes equation

Raoyang Zhang et al.

PHYSICAL REVIEW E (2006)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Lattice Boltzmann method with regularized pre-collision distribution functions

Jonas Latt et al.

MATHEMATICS AND COMPUTERS IN SIMULATION (2006)

Add to Collection

Article Physics, Fluids & Plasmas

Lattice Boltzmann method for non-Newtonian (power-law) fluids

S Gabbanelli et al.

PHYSICAL REVIEW E (2005)

Add to Collection

Article Multidisciplinary Sciences

Extended Boltzmann kinetic equation for turbulent flows

HD Chen et al.

SCIENCE (2003)

Add to Collection

Article Physics, Fluids & Plasmas

Theory of the lattice Boltzmann method: Dispersion, dissipation, isotropy, Galilean invariance, and stability

P Lallemand et al.

PHYSICAL REVIEW E (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.