Machine learning strategies for systems with invariance properties

DOI10.1016/j.jcp.2016.05.003zbMath1349.76124OpenAlexW2345737627MaRDI QIDQ726815

Julia Ling, Jeremy Templeton, Reese E. Jones

Publication date: 5 December 2016

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcp.2016.05.003

zbMATH Keywords

machine learning turbulence models tensor invariants constitutive models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Direct numerical and large eddy simulation of turbulence (76F65)

Related Items

Surrogate modeling of hydrodynamic forces between multiple floating bodies through a hierarchical interaction decomposition ⋮ DPM: a deep learning PDE augmentation method with application to large-eddy simulation ⋮ Symplectic neural networks in Taylor series form for Hamiltonian systems ⋮ Learning constitutive relations using symmetric positive definite neural networks ⋮ Solving inverse-PDE problems with physics-aware neural networks ⋮ Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows ⋮ On obtaining sparse semantic solutions for inverse problems, control, and neural network training ⋮ Multi-objective CFD-driven development of coupled turbulence closure models ⋮ Simple computational strategies for more effective physics-informed neural networks modeling of turbulent natural convection ⋮ Anisotropic yield models for lattice unit cell structures exploiting orthotropic symmetry ⋮ RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors ⋮ Mean Field Analysis of Deep Neural Networks ⋮ Data-Driven Filtered Reduced Order Modeling of Fluid Flows ⋮ Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data ⋮ Nonlinear multiscale simulation of elastic beam lattices with anisotropic homogenized constitutive models based on artificial neural networks ⋮ Data-driven modelling of the Reynolds stress tensor using random forests with invariance ⋮ High Reynolds number airfoil turbulence modeling method based on machine learning technique ⋮ Machine learning constitutive models of elastomeric foams ⋮ Comparison of different data-assimilation approaches to augment RANS turbulence models ⋮ Material modeling for parametric, anisotropic finite strain hyperelasticity based on machine learning with application in optimization of metamaterials ⋮ Advanced discretization techniques for hyperelastic physics-augmented neural networks ⋮ Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials ⋮ Frame Invariance and Scalability of Neural Operators for Partial Differential Equations ⋮ Exact conservation laws for neural network integrators of dynamical systems ⋮ Deep learning closure models for large-eddy simulation of flows around bluff bodies ⋮ A highly accurate strategy for data-driven turbulence modeling ⋮ Data-driven wall modeling for turbulent separated flows ⋮ Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification ⋮ Reynolds averaged turbulence modelling using deep neural networks with embedded invariance ⋮ Normalization effects on deep neural networks ⋮ An artificial neural network framework for reduced order modeling of transient flows ⋮ PDE-constrained models with neural network terms: optimization and global convergence ⋮ Learning invariance preserving moment closure model for Boltzmann-BGK equation ⋮ Sharp interface approaches and deep learning techniques for multiphase flows ⋮ Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks ⋮ Sub-grid scale model classification and blending through deep learning ⋮ Using machine learning to detect the turbulent region in flow past a circular cylinder ⋮ Coercing machine learning to output physically accurate results ⋮ Turbulence theories and statistical closure approaches ⋮ Set-to-Sequence Methods in Machine Learning: A Review ⋮ Representation of stress tensor perturbations with application in machine-learning-assisted turbulence modeling ⋮ A bi-fidelity ensemble Kalman method for PDE-constrained inverse problems in computational mechanics ⋮ Machine learning materials physics: integrable deep neural networks enable scale bridging by learning free energy functions ⋮ Determining \textit{a priori} a RANS model's applicable range via global epistemic uncertainty quantification ⋮ A physics-informed operator regression framework for extracting data-driven continuum models ⋮ Finite element solver for data-driven finite strain elasticity ⋮ Anisotropic hyperelastic constitutive models for finite deformations combining material theory and data-driven approaches with application to cubic lattice metamaterials ⋮ Effect of flow topology on the kinetic energy flux in compressible isotropic turbulence ⋮ Mean Field Analysis of Neural Networks: A Law of Large Numbers ⋮ Prediction of turbulent heat transfer using convolutional neural networks ⋮ A data-driven artificial neural network model for predicting wind load of buildings using GSM-CFD solver ⋮ Conditioning and accurate solutions of Reynolds average Navier–Stokes equations with data-driven turbulence closures ⋮ Gaussian process regression constrained by boundary value problems ⋮ Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids ⋮ A physics-constrained data-driven approach based on locally convex reconstruction for noisy database ⋮ A neural network approach for the blind deconvolution of turbulent flows ⋮ Normalization effects on shallow neural networks and related asymptotic expansions ⋮ Learning constitutive relations from indirect observations using deep neural networks ⋮ Finite electro-elasticity with physics-augmented neural networks ⋮ The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling ⋮ Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network ⋮ Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks

Uses Software

Cites Work