Data-driven discovery of PDEs in complex datasets

DOI10.1016/j.jcp.2019.01.036zbMath1451.68239arXiv1808.10788OpenAlexW2889523591WikidataQ114163522 ScholiaQ114163522MaRDI QIDQ2214651

Kaj Nyström, Jens Lindström

Publication date: 10 December 2020

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

Full work available at URL: https://arxiv.org/abs/1808.10788

zbMATH Keywords

neural networkspartial differential equationsmachine learningdeep learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Initial-boundary value problems for second-order hyperbolic equations (35L20) Meteorology and atmospheric physics (86A10)

Related Items

B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data, PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain, Solving inverse-PDE problems with physics-aware neural networks, System identification through Lipschitz regularized deep neural networks, Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data, A robust framework for identification of PDEs from noisy data, Mesh-Conv: convolution operator with mesh resolution independence for flow field modeling, Learning time-dependent PDEs with a linear and nonlinear separate convolutional neural network, Physics constrained learning for data-driven inverse modeling from sparse observations, A neural network multigrid solver for the Navier-Stokes equations, Structure preservation for the deep neural network multigrid solver, Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification, NeuralPDE: modelling dynamical systems from data, Predicting shallow water dynamics using echo-state networks with transfer learning, The robust physics-informed neural networks for a typical fourth-order phase field model, A method for computing inverse parametric PDE problems with random-weight neural networks, Addressing discontinuous root-finding for subsequent differentiability in machine learning, inverse problems, and control, Deep learning discovery of macroscopic governing equations for viscous gravity currents from microscopic simulation data, Adaptive activation functions accelerate convergence in deep and physics-informed neural networks, Integration of neural networks with numerical solution of PDEs for closure models development, Data-driven identification of 2D partial differential equations using extracted physical features, Unsupervised discovery of interpretable hyperelastic constitutive laws, DL-PDE: Deep-Learning Based Data-Driven Discovery of Partial Differential Equations from Discrete and Noisy Data, Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks, Discretizationnet: a machine-learning based solver for Navier-Stokes equations using finite volume discretization, A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations, Numerical solution of the parametric diffusion equation by deep neural networks

Uses Software

• L-BFGS
• COMSOL
• FEniCS
• SciPy
• Scikit
• TensorFlow
• PyTorch

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Review of summation-by-parts schemes for initial-boundary-value problems
• Automated solution of differential equations by the finite element method. The FEniCS book
• On the limited memory BFGS method for large scale optimization
• Parameter estimation for continuous-time models - a survey
• Review of summation-by-parts operators with simultaneous approximation terms for the numerical solution of partial differential equations
• Machine learning of linear differential equations using Gaussian processes
• Hidden physics models: machine learning of nonlinear partial differential equations
• Nonlinear black-box modeling in system identification: A unified overview
• Nonlinear black-box models in system identification: Mathematical foundations
• Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations
• Identification of partial differential equation models for a class of multiscale spatio-temporal dynamical systems
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Stability Selection
• Learning partial differential equations via data discovery and sparse optimization
• Sparse dynamics for partial differential equations
• Learning representations by back-propagating errors
• Approximation by superpositions of a sigmoidal function
• Gene selection for cancer classification using support vector machines