Data-driven identification of parametric partial differential equations
From MaRDI portal
Abstract: In this work we present a data-driven method for the discovery of parametric partial differential equations (PDEs), thus allowing one to disambiguate between the underlying evolution equations and their parametric dependencies. Group sparsity is used to ensure parsimonious representations of observed dynamics in the form of a parametric PDE, while also allowing the coefficients to have arbitrary time series, or spatial dependence. This work builds on previous methods for the identification of constant coefficient PDEs, expanding the field to include a new class of equations which until now have eluded machine learning based identification methods. We show that group sequentially thresholded ridge regression outperforms group LASSO in identifying the fewest terms in the PDE along with their parametric dependency. The method is demonstrated on four canonical models with and without the introduction of noise.
Recommendations
- Learning partial differential equations via data discovery and sparse optimization
- IDENT: identifying differential equations with numerical time evolution
- Data-driven identification of 2D partial differential equations using extracted physical features
- Sparse learning of partial differential equations with structured dictionary matrix
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
Cites work
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- A fast immersed boundary method using a nullspace approach and multi-domain far-field boundary conditions
- A new look at the statistical model identification
- A survey of projection-based model reduction methods for parametric dynamical systems
- An eigensystem realization algorithm for modal parameter identification and model reduction
- Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
- Applied Koopmanism
- Automated reverse engineering of nonlinear dynamical systems
- Certified reduced basis methods for parametrized partial differential equations
- Compressed sensing and dynamic mode decomposition
- Constrained sparse Galerkin regression
- Data-driven spectral decomposition and forecasting of ergodic dynamical systems
- Deep hidden physics models: deep learning of nonlinear partial differential equations
- Delay-coordinate maps and the spectra of Koopman operators
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Dynamic mode decomposition of numerical and experimental data
- Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
- Ergodic theory, dynamic mode decomposition, and computation of spectral properties of the Koopman operator
- Extracting Sparse High-Dimensional Dynamics from Limited Data
- Hidden physics models: machine learning of nonlinear partial differential equations
- scientific article; zbMATH DE number 6678650 (Why is no real title available?)
- scientific article; zbMATH DE number 4105912 (Why is no real title available?)
- Inferring solutions of differential equations using noisy multi-fidelity data
- Learning partial differential equations via data discovery and sparse optimization
- Linearly recurrent autoencoder networks for learning dynamics
- Machine learning of linear differential equations using Gaussian processes
- Model reduction of parametrized systems. Selected contributions based on the presentations at the MoRePaS conference, SISSA, Trieste, Italy, October 13--16, 2015
- Model selection for dynamical systems via sparse regression and information criteria
- Nonlinear Laplacian spectral analysis for time series with intermittency and low-frequency variability
- Numerical differentiation of approximated functions with limited order-of-accuracy deterioration
- Numerical Gaussian processes for time-dependent and nonlinear partial differential equations
- On dynamic mode decomposition: theory and applications
- On the Compressive Spectral Method
- PDEs with compressed solutions
- Reduced basis methods for partial differential equations. An introduction
- Representations of non-linear systems: the NARMAX model
- Sparse dynamics for partial differential equations
- Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
- Spectral analysis of nonlinear flows
- Spectral properties of dynamical systems, model reduction and decompositions
- Statistical modeling: The two cultures. (With comments and a rejoinder).
- The immersed boundary method: a projection approach
- Variable projection methods for an optimized dynamic mode decomposition
Cited in
(92)- IDENT: identifying differential equations with numerical time evolution
- SciANN: a Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
- A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
- Surrogate optimization of deep neural networks for groundwater predictions
- Extracting governing laws from sample path data of non-Gaussian stochastic dynamical systems
- Bayesian learning of stochastic dynamical models
- Sparse methods for automatic relevance determination
- Intrusive and data-driven reduced order modelling of the rotating thermal shallow water equation
- A Bayesian approach for data-driven dynamic equation discovery
- A data-driven approach for discovering stochastic dynamical systems with non-Gaussian Lévy noise
- Data-driven discovery of coarse-grained equations
- DLGA-PDE: discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
- SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations
- 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
- Learning time-dependent PDEs with a linear and nonlinear separate convolutional neural network
- A neural network multigrid solver for the Navier-Stokes equations
- Data-driven discovery of governing equations for transient heat transfer analysis
- Methods to recover unknown processes in partial differential equations using data
- From structured data to evolution linear partial differential equations
- Identification of physical processes via combined data-driven and data-assimilation methods
- Sparse identification of truncation errors
- Smoothing and parameter estimation by soft-adherence to governing equations
- Data-driven identification of 2D partial differential equations using extracted physical features
- Solving inverse problems in stochastic models using deep neural networks and adversarial training
- A nonlocal physics-informed deep learning framework using the peridynamic differential operator
- Optimization algorithms for parameter identification in parabolic partial differential equations
- Parameter determination in a partial differential equation from the overspecified data
- Structure preservation for the deep neural network multigrid solver
- A hybrid objective function for robustness of artificial neural networks -- estimation of parameters in a mechanical system
- LaSDI: parametric latent space dynamics identification
- PI-VAE: physics-informed variational auto-encoder for stochastic differential equations
- Sparse dynamical system identification with simultaneous structural parameters and initial condition estimation
- WeakIdent: weak formulation for identifying differential equation using narrow-fit and trimming
- Learning partial differential equations via data discovery and sparse optimization
- Concurrent multiparameter learning demonstrated on the Kuramoto-Sivashinsky equation
- Data-Driven Identification of Rayleigh-Damped Second-Order Systems
- Extracting stochastic dynamical systems with α-stable Lévy noise from data
- Detecting the maximum likelihood transition path from data of stochastic dynamical systems
- 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
- Data-driven discovery of governing equations for fluid dynamics based on molecular simulation
- Sparse learning of partial differential equations with structured dictionary matrix
- Data-driven sparse identification of nonlinear dynamical systems using linear multistep methods
- Seq-SVF: an unsupervised data-driven method for automatically identifying hidden governing equations
- Mitigating Model Error via a Multimodel Method and Application to Tropical Intraseasonal Oscillations
- Group projected subspace pursuit for identification of variable coefficient differential equations (GP-IDENT)
- Spiking recurrent neural networks for neuromorphic computing in nonlinear structural mechanics
- Inverse problems of inhomogeneous fracture toughness using phase-field models
- 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
- Data-driven identification of parametric governing equations of dynamical systems using the signed cumulative distribution transform
- Physics-based self-learning spiking neural network enhanced time-integration scheme for computing viscoplastic structural finite element response
- A Review of Data‐Driven Discovery for Dynamic Systems
- Structured model selection via ℓ1−ℓ2 optimization
- Stochastic dynamics and data science
- Data-driven method to extract mean exit time and escape probability for dynamical systems driven by Lévy noises
- \(\mathrm{U}^p\)-net: a generic deep learning-based time stepper for parameterized spatio-temporal dynamics
- Data driven discovery of systems of ordinary differential equations using nonconvex multitask learning
- Discovery of PDEs driven by data with sharp gradient or discontinuity
- Nonintrusive Reduced-Order Models for Parametric Partial Differential Equations via Data-Driven Operator Inference
- Deep learning discovery of macroscopic governing equations for viscous gravity currents from microscopic simulation data
- On mathematical modeling in image reconstruction and beyond
- Piecewise DMD for oscillatory and Turing spatio-temporal dynamics
- Inferring dynamical models from time-series biological data using an interpretable machine learning method based on weighted expression trees
- Online identification and control of PDEs via reinforcement learning methods
- Learning fluid physics from highly turbulent data using sparse physics-informed discovery of empirical relations (SPIDER)
- Learning in-between imagery dynamics via physical latent spaces
- Machine learning methods for reduced order modeling
- Forecasting and predicting stochastic agent-based model data with biologically-informed neural networks
- How much can one learn a partial differential equation from its solution?
- Identifying differential equations in Fourier domain (FourierIdent)
- Sparse identification of fractional chaotic systems based on the time-domain data
- Extraction and reconstruction of variable-coefficient governing equations using RES-KAN integrating sparse regression
- LES-SINDy: Laplace-enhanced sparse identification of nonlinear dynamical systems
- WG-IDENT: weak group identification of PDEs with varying coefficients
- Data-driven discovery of state-changes in underlying system from hidden change-points in partial differential equations with spatiotemporal varying coefficients
- Learning a water quality model with time dependent parameters by l^1-weighted regularization
- Physics-driven deep learning methods and numerically intractable ``bad Jaulent-Miodek equation
- Predictions based on pixel data: insights from PDEs and finite differences
- Data-driven localized wave solutions and parameters discovery of the (1+1)-dimensional Ito integro-differential equation
- A POD approach to identify and control PDEs online through state dependent Riccati equations
- Sparse identification of nonlocal interaction kernels in nonlinear gradient flow equations via partial inversion
- A Bayesian approach for spatio-temporal data-driven dynamic equation discovery
- A PINN approach for the online identification and control of unknown PDEs
- Data-driven approach for extracting the most probable exit trajectory of stochastic dynamical systems with non-Gaussian Lévy noise
- Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants
- Explorations of certain nonlinear waves of the Boussinesq and Camassa-Holm equations using physics-informed neural networks
- Discovering stochastic basin stability from data in a Filippov competition system with threshold control
- On the use of exponential basis functions in the PINN architecture: an enhanced solution approach for the Laplace, Helmholtz, and elasto-static equations
- Principal component flow map learning of PDEs from incomplete, limited, and noisy data
- System identification and landscape stability of stochastic competition ecosystem
This page was built for publication: Data-driven identification of parametric partial differential equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5383204)
