Hidden physics models: machine learning of nonlinear partial differential equations

DOI10.1016/J.JCP.2017.11.039zbMath1381.68248arXiv1708.00588OpenAlexW2745110207MaRDI QIDQ1699464

George Em. Karniadakis, Maziar Raissi

Publication date: 23 February 2018

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

Full work available at URL: https://arxiv.org/abs/1708.00588

zbMATH Keywords

system identificationsmall datauncertainty quantificationBayesian modelingfractional equationsprobabilistic machine learning

Mathematics Subject Classification ID

Gaussian processes (60G15) Learning and adaptive systems in artificial intelligence (68T05) Navier-Stokes equations (35Q30) Reasoning under uncertainty in the context of artificial intelligence (68T37) Fractional partial differential equations (35R11) Time-dependent Schrödinger equations and Dirac equations (35Q41) Systems of nonlinear higher-order PDEs (35G50)

Related Items (only showing first 100 items - show all)

A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems ⋮ On a multilevel Levenberg–Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations ⋮ Physics-Driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks ⋮ Generalization Error Analysis of Neural Networks with Gradient Based Regularization ⋮ A New Artificial Neural Network Method for Solving Schrödinger Equations on Unbounded Domains ⋮ Wide-Band Butterfly Network: Stable and Efficient Inversion Via Multi-Frequency Neural Networks ⋮ Blood and breath alcohol concentration from transdermal alcohol biosensor data: estimation and uncertainty quantification via forward and inverse filtering for a covariate-dependent, physics-informed, hidden Markov model* ⋮ Subgrid modelling for two-dimensional turbulence using neural networks ⋮ Robust Identification of Differential Equations by Numerical Techniques from a Single Set of Noisy Observation ⋮ Physics Informed Neural Networks (PINNs) For Approximating Nonlinear Dispersive PDEs ⋮ Robust topology optimization with low rank approximation using artificial neural networks ⋮ Low-rank statistical finite elements for scalable model-data synthesis ⋮ Structure preservation for the deep neural network multigrid solver ⋮ The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation ⋮ Scalable uncertainty quantification for deep operator networks using randomized priors ⋮ Improved deep neural networks with domain decomposition in solving partial differential equations ⋮ Machine learning based refinement strategies for polyhedral grids with applications to virtual element and polyhedral discontinuous Galerkin methods ⋮ A deep learning method for solving high-order nonlinear soliton equations ⋮ Data-driven sparse identification of nonlinear dynamical systems using linear multistep methods ⋮ Deep learning neural networks for the third-order nonlinear Schrödinger equation: bright solitons, breathers, and rogue waves ⋮ Solving second-order nonlinear evolution partial differential equations using deep learning ⋮ Learning theory for inferring interaction kernels in second-order interacting agent systems ⋮ Adaptive group Lasso neural network models for functions of few variables and time-dependent data ⋮ Implicit integration of nonlinear evolution equations on tensor manifolds ⋮ Deep learning-accelerated computational framework based on physics informed neural network for the solution of linear elasticity ⋮ On the approximation of functions by tanh neural networks ⋮ Physics-incorporated convolutional recurrent neural networks for source identification and forecasting of dynamical systems ⋮ A-WPINN algorithm for the data-driven vector-soliton solutions and parameter discovery of general coupled nonlinear equations ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ A perspective on machine learning methods in turbulence modeling ⋮ On the recovery of internal source for an elliptic system by neural network approximation ⋮ A nonlocal energy‐informed neural network for isotropic elastic solids with cracks under thermomechanical loads ⋮ Phase-field DeepONet: physics-informed deep operator neural network for fast simulations of pattern formation governed by gradient flows of free-energy functionals ⋮ Physics-agnostic and physics-infused machine learning for thin films flows: modelling, and predictions from small data ⋮ Determining the viscosity of the Navier–Stokes equations from observations of finitely many modes ⋮ A deep learning method for solving third-order nonlinear evolution equations ⋮ Single-track thermal analysis of laser powder bed fusion process: parametric solution through physics-informed neural networks ⋮ Fully probabilistic deep models for forward and inverse problems in parametric PDEs ⋮ Data-driven, multi-moment fluid modeling of Landau damping ⋮ Viscous damping of steady-state resonant sloshing in a clean rectangular tank ⋮ Neural vortex method: from finite Lagrangian particles to infinite dimensional Eulerian dynamics ⋮ Exponential ReLU neural network approximation rates for point and edge singularities ⋮ Principled interpolation of Green's functions learned from data ⋮ Learning high frequency data via the coupled frequency predictor-corrector triangular DNN ⋮ Physics-informed deep learning for melting heat transfer analysis with model-based transfer learning ⋮ A method for computing inverse parametric PDE problems with random-weight neural networks ⋮ Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation ⋮ Learning black- and gray-box chemotactic PDEs/closures from agent based Monte Carlo simulation data ⋮ Accelerating explicit time-stepping with spatially variable time steps through machine learning ⋮ Higher-order error estimates for physics-informed neural networks approximating the primitive equations ⋮ Addressing discontinuous root-finding for subsequent differentiability in machine learning, inverse problems, and control ⋮ Unnamed Item ⋮ Data-driven learning of differential equations: combining data and model uncertainty ⋮ QBoost for regression problems: solving partial differential equations ⋮ Data-driven control of agent-based models: an equation/variable-free machine learning approach ⋮ Local parameter identification with neural ordinary differential equations ⋮ Microstructure-informed probability-driven point-particle model for hydrodynamic forces and torques in particle-laden flows ⋮ Thermodynamics-informed neural networks for physically realistic mixed reality ⋮ Physics-informed neural networks based on adaptive weighted loss functions for Hamilton-Jacobi equations ⋮ Learning elliptic partial differential equations with randomized linear algebra ⋮ A comparative study of learning techniques for the compressible aerodynamics over a transonic RAE2822 airfoil ⋮ WeakIdent: weak formulation for identifying differential equation using narrow-fit and trimming ⋮ Solving traveltime tomography with deep learning ⋮ Data-Driven Identification of Parametric Partial Differential Equations ⋮ Extracting Structured Dynamical Systems Using Sparse Optimization With Very Few Samples ⋮ Data-driven identification of 2D partial differential equations using extracted physical features ⋮ A finite element approximation of a current-induced magnetization dynamics model ⋮ Unnamed Item ⋮ Deep learning of vortex-induced vibrations ⋮ Physics informed by deep learning: numerical solutions of modified Korteweg-de Vries equation ⋮ Optimization algorithms for parameter identification in parabolic partial differential equations ⋮ TONR: an exploration for a novel way combining neural network with topology optimization ⋮ Parametric deep energy approach for elasticity accounting for strain gradient effects ⋮ Shallow neural networks for fluid flow reconstruction with limited sensors ⋮ SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics ⋮ Bayesian differential programming for robust systems identification under uncertainty ⋮ Physics-Constrained, Data-Driven Discovery of Coarse-Grained Dynamics ⋮ Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations ⋮ On the Convergence of the SINDy Algorithm ⋮ Learning the tangent space of dynamical instabilities from data ⋮ A deep energy method for finite deformation hyperelasticity ⋮ Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations ⋮ Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks ⋮ A machine learning framework for data driven acceleration of computations of differential equations ⋮ A Multiscale Neural Network Based on Hierarchical Matrices ⋮ A physics-constrained data-driven approach based on locally convex reconstruction for noisy database ⋮ Bayesian Model and Dimension Reduction for Uncertainty Propagation: Applications in Random Media ⋮ Solving inverse problems using data-driven models ⋮ Machine Learning of Space-Fractional Differential Equations ⋮ fPINNs: Fractional Physics-Informed Neural Networks ⋮ A neural network approach for the blind deconvolution of turbulent flows ⋮ Transfer learning of deep material network for seamless structure-property predictions ⋮ Prediction of aerodynamic flow fields using convolutional neural networks ⋮ A multiscale neural network based on hierarchical nested bases ⋮ Tensor Decomposition Methods for High-dimensional Hamilton--Jacobi--Bellman Equations ⋮ Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences ⋮ The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling ⋮ Using machine learning to predict extreme events in complex systems ⋮ A multi-level procedure for enhancing accuracy of machine learning algorithms ⋮ A novel physics-informed deep learning strategy with local time-updating discrete scheme for multi-dimensional forward and inverse consolidation problems

Uses Software

• L-BFGS
• PMTK

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Detecting Causality in Complex Ecosystems
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• On the limited memory BFGS method for large scale optimization
• A fast immersed boundary method using a nullspace approach and multi-domain far-field boundary conditions
• Some global dynamical properties of the Kuramoto-Sivashinsky equations: nonlinear stability and attractors
• The Kuramoto-Sivashinsky equation: a bridge between PDE's and dynamical systems
• Spectral and finite difference solutions of the Burgers equations
• Inferring solutions of differential equations using noisy multi-fidelity data
• Machine learning of linear differential equations using Gaussian processes
• The immersed boundary method: a projection approach
• Spectral properties of dynamical systems, model reduction and decompositions
• Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
• Inverse problems: A Bayesian perspective
• Compressive Sensing and Low-Rank Libraries for Classification of Bifurcation Regimes in Nonlinear Dynamical Systems
• Applied Koopmanism
• Normal forms for reduced stochastic climate models
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Automated reverse engineering of nonlinear dynamical systems
• A Method for Simulating Stable Random Variables
• 10.1162/15324430152748236
• Nonlinear Laplacian spectral analysis for time series with intermittency and low-frequency variability
• Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
• Sparse dynamics for partial differential equations
• Compressed modes for variational problems in mathematics and physics
• On the Compressive Spectral Method
• Theory of Reproducing Kernels

This page was built for publication: Hidden physics models: machine learning of nonlinear partial differential equations