Deep learning observables in computational fluid dynamics

DOI10.1016/j.jcp.2020.109339zbMath1436.76051arXiv1903.03040OpenAlexW2921773029MaRDI QIDQ777521

Deep Ray, Kjetil O. Lye, Siddhartha Mishra

Publication date: 7 July 2020

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

Full work available at URL: https://arxiv.org/abs/1903.03040

zbMATH Keywords

neural networksobservablesquasi-Monte CarloCFDdeep learningUQ

Mathematics Subject Classification ID

Diffusion (76R50) Shock waves and blast waves in fluid mechanics (76L05) Stochastic analysis applied to problems in fluid mechanics (76M35) Gas dynamics (general theory) (76N15) Reasoning under uncertainty in the context of artificial intelligence (68T37) Free convection (76R10)

Related Items

Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms, Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities, Approximations with deep neural networks in Sobolev time-space, Physics Informed Neural Networks (PINNs) For Approximating Nonlinear Dispersive PDEs, Physics-informed neural networks for high-speed flows, Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification, On the approximation of functions by tanh neural networks, Three ways to solve partial differential equations with neural networks — A review, Integrated finite element neural network (I-FENN) for non-local continuum damage mechanics, Continuous limits of residual neural networks in case of large input data, Neural vortex method: from finite Lagrangian particles to infinite dimensional Eulerian dynamics, Learning high frequency data via the coupled frequency predictor-corrector triangular DNN, NeuralUQ: A Comprehensive Library for Uncertainty Quantification in Neural Differential Equations and Operators, Data-driven control of agent-based models: an equation/variable-free machine learning approach, Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing, On the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysis, Discontinuity computing using physics-informed neural networks, Artificial neural network-augmented stabilized finite element method, wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws, Control of partial differential equations via physics-informed neural networks, An overview on deep learning-based approximation methods for partial differential equations, Unnamed Item, Numerical Simulations for Full History Recursive Multilevel Picard Approximations for Systems of High-Dimensional Partial Differential Equations, Statistical solutions of the incompressible Euler equations, Iterative surrogate model optimization (ISMO): an active learning algorithm for PDE constrained optimization with deep neural networks, Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations, Embedding data analytics and CFD into the digital twin concept, Deep Splitting Method for Parabolic PDEs, Statistical solutions of hyperbolic systems of conservation laws: Numerical approximation, Constructive deep ReLU neural network approximation, Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures, Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences, On the approximation of rough functions with deep neural networks, Error analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEs, A multi-level procedure for enhancing accuracy of machine learning algorithms, Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks, Generalized Cell Mapping Method with Deep Learning for Global Analysis and Response Prediction of Dynamical Systems, Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning

Uses Software

• Matlab
• TensorFlow
• Keras
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Uncertainty quantification in computational fluid dynamics
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Hidden physics models: machine learning of nonlinear partial differential equations
• Multilayer feedforward networks are universal approximators
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Model order reduction for parametrized nonlinear hyperbolic problems as an application to uncertainty quantification
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Error bounds for approximations with deep ReLU networks
• A machine learning framework for data driven acceleration of computations of differential equations
• An artificial neural network as a troubled-cell indicator
• Inverse problems: A Bayesian perspective
• Arbitrarily High-order Accurate Entropy Stable Essentially Nonoscillatory Schemes for Systems of Conservation Laws
• Handbook of Uncertainty Quantification
• Computational Optimization of Systems Governed by Partial Differential Equations
• Algorithms for the Assignment and Transportation Problems
• Universal approximation bounds for superpositions of a sigmoidal function
• Spectral Methods in MATLAB
• Numerical Methods for Conservation Laws
• Solving high-dimensional partial differential equations using deep learning
• Sparse grids
• Entropy Stable Scheme on Two-Dimensional Unstructured Grids for Euler Equations
• Understanding Machine Learning
• Approximation by superpositions of a sigmoidal function