Discovering governing equations from data by sparse identification of nonlinear dynamical systems
From MaRDI portal
Abstract: The ability to discover physical laws and governing equations from data is one of humankind's greatest intellectual achievements. A quantitative understanding of dynamic constraints and balances in nature has facilitated rapid development of knowledge and enabled advanced technological achievements, including aircraft, combustion engines, satellites, and electrical power. In this work, we combine sparsity-promoting techniques and machine learning with nonlinear dynamical systems to discover governing physical equations from measurement data. The only assumption about the structure of the model is that there are only a few important terms that govern the dynamics, so that the equations are sparse in the space of possible functions; this assumption holds for many physical systems. In particular, we use sparse regression to determine the fewest terms in the dynamic governing equations required to accurately represent the data. The resulting models are parsimonious, balancing model complexity with descriptive ability while avoiding overfitting. We demonstrate the algorithm on a wide range of problems, from simple canonical systems, including linear and nonlinear oscillators and the chaotic Lorenz system, to the fluid vortex shedding behind an obstacle. The fluid example illustrates the ability of this method to discover the underlying dynamics of a system that took experts in the community nearly 30 years to resolve. We also show that this method generalizes to parameterized, time-varying, or externally forced systems.
Recommendations
- Data-driven discovery of coordinates and governing equations
- Learning partial differential equations via data discovery and sparse optimization
- IDENT: identifying differential equations with numerical time evolution
- SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics
- Constrained sparse Galerkin regression
Cites work
- A fast immersed boundary method using a nullspace approach and multi-domain far-field boundary conditions
- A finite-element study of the onset of vortex shedding in flow past variously shaped bodies
- A hierarchy of low-dimensional models for the transient and post-transient cylinder wake
- An introduction to statistical learning. With applications in R
- Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
- Automated reverse engineering of nonlinear dynamical systems
- Compressed modes for variational problems in mathematics and physics
- Compressed sensing
- Compressive sensing and low-rank libraries for classification of bifurcation regimes in nonlinear dynamical systems
- Detecting causality in complex ecosystems
- Deterministic Nonperiodic Flow
- Dynamic mode decomposition of numerical and experimental data
- Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
- scientific article; zbMATH DE number 4105912 (Why is no real title available?)
- scientific article; zbMATH DE number 795587 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Information flow between subspaces of complex dynamical systems
- Machine learning: Trends, perspectives, and prospects
- Nonlinear oscillations, dynamical systems, and bifurcations of vector fields
- Nonlinear total variation based noise removal algorithms
- Normal forms for reduced stochastic climate models
- Numerical differentiation of noisy, nonsmooth data
- On the Compressive Spectral Method
- On the nature of turbulence
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
- Sparse dynamics for partial differential equations
- Spectral analysis of nonlinear flows
- Spectral compressive sensing
- Stable signal recovery from incomplete and inaccurate measurements
- The Hopf bifurcation and its applications. With contributions by P. Chernoff, G. Childs, S. Chow, J. R. Dorroh, J. Guckenheimer, L. Howard, N. Kopell, O. Lanford, J. Mallet-Paret, G. Oster, O. Ruiz, S. Schecter, D. Schmidt, and S. Smale
- The immersed boundary method: a projection approach
- The Optimal Hard Threshold for Singular Values is <inline-formula> <tex-math notation="TeX">\(4/\sqrt {3}\) </tex-math></inline-formula>
- Turbulence, coherent structures, dynamical systems and symmetry.
Cited in
(only showing first 100 items - show all)- sindyr
- Sparse principal component analysis via variable projection
- A manifold learning approach to data-driven computational elasticity and inelasticity
- Sparsity enabled cluster reduced-order models for control
- Reduced-space Gaussian process regression for data-driven probabilistic forecast of chaotic dynamical systems
- Machine learning of linear differential equations using Gaussian processes
- Hidden physics models: machine learning of nonlinear partial differential equations
- Reconstruction of a random phase dynamics network from observations
- A multidimensional data-driven sparse identification technique: the sparse proper generalized decomposition
- Applied Koopman theory for partial differential equations and data-driven modeling of spatio-temporal systems
- Projection-based model reduction: formulations for physics-based machine learning
- IDENT: identifying differential equations with numerical time evolution
- Reconstruction of ensembles of generalized van der Pol oscillators from vector time series
- Machine learning subsurface flow equations from data
- Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering
- A physics-informed operator regression framework for extracting data-driven continuum models
- Machine learning materials physics: multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
- Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
- Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms
- Sparse identification of nonlinear dynamical systems via reweighted \(\ell_1\)-regularized least squares
- Non-invasive inference of thrombus material properties with physics-informed neural networks
- Memory-based reduced modelling and data-based estimation of opinion spreading
- An efficient descent method for locally Lipschitz multiobjective optimization problems
- Inverse multiobjective optimization: inferring decision criteria from data
- Inferring switched nonlinear dynamical systems
- Operator inference of non-Markovian terms for learning reduced models from partially observed state trajectories
- Towards the automatic mathematician
- Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data
- Nonlinear normal modes in the \(\beta\)-Fermi-Pasta-Ulam-Tsingou chain
- Data-driven RANS closures for wind turbine wakes under neutral conditions
- Projection-based model reduction of dynamical systems using space-time subspace and machine learning
- Online learning of both state and dynamics using ensemble Kalman filters
- Interpretable machine learning: fundamental principles and 10 grand challenges
- Extracting governing laws from sample path data of non-Gaussian stochastic dynamical systems
- Surrogate parametric metamodel based on optimal transport
- Time-series learning of latent-space dynamics for reduced-order model closure
- Bayesian learning of stochastic dynamical models
- Deep learning of conjugate mappings
- Learning dynamical systems from data: a simple cross-validation perspective. I: Parametric kernel flows
- Supervised learning from noisy observations: combining machine-learning techniques with data assimilation
- Sparse methods for automatic relevance determination
- Intrusive and data-driven reduced order modelling of the rotating thermal shallow water equation
- Sparse parameter identification of stochastic dynamical systems
- Towards out of distribution generalization for problems in mechanics
- Ensemble Kalman inversion for sparse learning of dynamical systems from time-averaged data
- Learning Hamiltonians of constrained mechanical systems
- Synchronization of reservoir computing models via a nonlinear controller
- Full and reduced order model consistency of the nonlinearity discretization in incompressible flows
- Design of the monodomain model by artificial neural networks
- A Bayesian approach for data-driven dynamic equation discovery
- Finite-data error bounds for Koopman-based prediction and control
- One-shot learning of stochastic differential equations with data adapted kernels
- Data-driven reduced-order modeling for nonautonomous dynamical systems in multiscale media
- Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems
- Robust modeling of unknown dynamical systems via ensemble averaged learning
- Lift \& learn: physics-informed machine learning for large-scale nonlinear dynamical systems
- Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers
- Data-driven approximation of the Koopman generator: model reduction, system identification, and control
- Poincaré maps for multiscale physics discovery and nonlinear Floquet theory
- A data-driven approach for discovering stochastic dynamical systems with non-Gaussian Lévy noise
- Bridging the gap: machine learning to resolve improperly modeled dynamics
- Calibration of projection-based reduced-order models for unsteady compressible flows
- Shortcuts to thermodynamic computing: the cost of fast and faithful information processing
- Lagrangian dynamic mode decomposition for construction of reduced-order models of advection-dominated phenomena
- Data-driven deep learning of partial differential equations in modal space
- Non-intrusive reduced-order modeling using uncertainty-aware deep neural networks and proper orthogonal decomposition: application to flood modeling
- Peridynamics enabled learning partial differential equations
- Data-driven discovery of coarse-grained equations
- A data-driven physics-informed finite-volume scheme for nonclassical undercompressive shocks
- Symplectic neural networks in Taylor series form for Hamiltonian systems
- On generalized residual network for deep learning of unknown dynamical systems
- DLGA-PDE: discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
- Learning nonlinear turbulent dynamics from partial observations via analytically solvable conditional statistics
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- Transfer learning based multi-fidelity physics informed deep neural network
- Structure-preserving neural networks
- Data-driven discovery of emergent behaviors in collective dynamics
- SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations
- Learning non-Markovian physics from data
- A data-driven, physics-informed framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings
- Image inversion and uncertainty quantification for constitutive laws of pattern formation
- Using neural networks to accelerate the solution of the Boltzmann equation
- Weak SINDy for partial differential equations
- System identification through Lipschitz regularized deep neural networks
- Extended dynamic mode decomposition for inhomogeneous problems
- Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
- Hybrid FEM-NN models: combining artificial neural networks with the finite element method
- A robust framework for identification of PDEs from noisy data
- Data-driven discovery of multiscale chemical reactions governed by the law of mass action
- Machine learning moment closure models for the radiative transfer equation. I: Directly learning a gradient based closure
- CFD-driven symbolic identification of algebraic Reynolds-stress models
- Deep neural network modeling of unknown partial differential equations in nodal space
- Revealing hidden dynamics from time-series data by ODENet
- Learning biological dynamics from spatio-temporal data by Gaussian processes
- Interpolatory tensorial reduced order models for parametric dynamical systems
- tgEDMD: approximation of the Kolmogorov operator in tensor train format
- Data-driven discovery of governing equations for transient heat transfer analysis
- Computing the invariant distribution of randomly perturbed dynamical systems using deep learning
- Numerical bifurcation analysis of PDEs from lattice Boltzmann model simulations: a parsimonious machine learning approach
- Bayesian-EUCLID: discovering hyperelastic material laws with uncertainties
This page was built for publication: Discovering governing equations from data by sparse identification of nonlinear dynamical systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q137310)
