Data-driven discovery of PDEs in complex datasets
From MaRDI portal
Abstract: Many processes in science and engineering can be described by partial differential equations (PDEs). Traditionally, PDEs are derived by considering first principles of physics to derive the relations between the involved physical quantities of interest. A different approach is to measure the quantities of interest and use deep learning to reverse engineer the PDEs which are describing the physical process. In this paper we use machine learning, and deep learning in particular, to discover PDEs hidden in complex data sets from measurement data. We include examples of data from a known model problem, and real data from weather station measurements. We show how necessary transformations of the input data amounts to coordinate transformations in the discovered PDE, and we elaborate on feature and model selection. It is shown that the dynamics of a non-linear, second order PDE can be accurately described by an ordinary differential equation which is automatically discovered by our deep learning algorithm. Even more interestingly, we show that similar results apply in the context of more complex simulations of the Swedish temperature distribution.
Recommendations
- Deep hidden physics models: deep learning of nonlinear partial differential equations
- PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network
- Data-driven identification of 2D partial differential equations using extracted physical features
- Hidden physics models: machine learning of nonlinear partial differential equations
- Learning partial differential equations via data discovery and sparse optimization
Cites work
- scientific article; zbMATH DE number 4105912 (Why is no real title available?)
- scientific article; zbMATH DE number 44386 (Why is no real title available?)
- scientific article; zbMATH DE number 1243473 (Why is no real title available?)
- scientific article; zbMATH DE number 827355 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Approximation by superpositions of a sigmoidal function
- Automated solution of differential equations by the finite element method. The FEniCS book
- Consistent feature selection for pattern recognition in polynomial time
- Deep hidden physics models: deep learning of nonlinear partial differential equations
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Gene selection for cancer classification using support vector machines
- Hidden physics models: machine learning of nonlinear partial differential equations
- Identification of partial differential equation models for a class of multiscale spatio-temporal dynamical systems
- Learning partial differential equations via data discovery and sparse optimization
- Learning representations by back-propagating errors
- Machine learning of linear differential equations using Gaussian processes
- 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
- 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
- Review of summation-by-parts schemes for initial-boundary-value problems
- Scikit-learn: machine learning in Python
- Sparse dynamics for partial differential equations
- Stability selection. With discussion and authors' reply
Cited in
(43)- Deep hidden physics models: deep learning of nonlinear partial differential equations
- A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations
- PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network
- NeuralPDE: modelling dynamical systems from data
- Structure preservation for the deep neural network multigrid solver
- Data-driven optimal prediction with control
- Long-time prediction of nonlinear parametrized dynamical systems by deep learning-based reduced order models
- Data-driven discovery of coarse-grained equations
- Integration of neural networks with numerical solution of PDEs for closure models development
- Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
- The robust physics-informed neural networks for a typical fourth-order phase field model
- Identification of physical processes via combined data-driven and data-assimilation methods
- Numerical solution of the parametric diffusion equation by deep neural networks
- System identification through Lipschitz regularized deep neural networks
- A robust framework for identification of PDEs from noisy data
- Mesh-Conv: convolution operator with mesh resolution independence for flow field modeling
- Discretizationnet: a machine-learning based solver for Navier-Stokes equations using finite volume discretization
- Deep learning in computational mechanics: a review
- Discovery of governing equations with recursive deep neural networks
- A neural network multigrid solver for the Navier-Stokes equations
- Data-driven discovery of governing equations for transient heat transfer analysis
- Data-driven identification of 2D partial differential equations using extracted physical features
- 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
- Deep neural network surrogates for nonsmooth quantities of interest in shape uncertainty quantification
- Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks
- A method for computing inverse parametric PDE problems with random-weight neural networks
- Predicting shallow water dynamics using echo-state networks with transfer learning
- Physics constrained learning for data-driven inverse modeling from sparse observations
- PDE-READ: human-readable partial differential equation discovery using deep learning
- Deep learning models for global coordinate transformations that linearise PDEs
- B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data
- Derivative-based SINDy (DSINDy): addressing the challenge of discovering governing equations from noisy data
- \texttt{Weak-PDE-LEARN}: a weak form based approach to discovering PDEs from noisy, limited data
- Learning time-dependent PDEs with a linear and nonlinear separate convolutional neural network
- DL-PDE: Deep-Learning Based Data-Driven Discovery of Partial Differential Equations from Discrete and Noisy Data
- Unsupervised discovery of interpretable hyperelastic constitutive laws
- Hidden physics models: machine learning of nonlinear partial differential equations
- Solving inverse-PDE problems with physics-aware neural networks
- Learning topological horseshoe via deep neural networks
- PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain
- Addressing discontinuous root-finding for subsequent differentiability in machine learning, inverse problems, and control
- Data-driven discovery of coordinates and governing equations
This page was built for publication: Data-driven discovery of PDEs in complex datasets
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2214651)
