Learning partial differential equations via data discovery and sparse optimization

DOI10.1098/rspa.2016.0446zbMath1404.35397OpenAlexW2573798107WikidataQ52384975 ScholiaQ52384975MaRDI QIDQ4646838

Hayden Schaeffer

Publication date: 28 December 2018

Published in: Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences (Search for Journal in Brave)

Full work available at URL: https://europepmc.org/articles/pmc5312119

zbMATH Keywords

parameter estimationpartial differential equationsmachine learningfeature selectionsparse optimization

Mathematics Subject Classification ID

KdV equations (Korteweg-de Vries equations) (35Q53) Shock waves and blast waves in fluid mechanics (76L05) Applications of statistics to physics (62P35) Turbulence (76Fxx) Free convection (76R10) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99) Approximation methods and numerical treatment of dynamical systems (37M99)

Related Items

Data-driven deep learning of partial differential equations in modal space, Peridynamics enabled learning partial differential equations, Data-driven discovery of coarse-grained equations, 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, On a multilevel Levenberg–Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations, SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations, Numerical Identification of Nonlocal Potentials in Aggregation, Solving inverse-PDE problems with physics-aware neural networks, Weak SINDy for partial differential equations, System identification through Lipschitz regularized deep neural networks, Extended dynamic mode decomposition for inhomogeneous problems, A robust framework for identification of PDEs from noisy data, Deep neural network modeling of unknown partial differential equations in nodal space, Discretization of parameter identification in PDEs using neural networks, Data-driven discovery of governing equations for transient heat transfer analysis, Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks, Subgrid modelling for two-dimensional turbulence using neural networks, Extracting Sparse High-Dimensional Dynamics from Limited Data, Robust Identification of Differential Equations by Numerical Techniques from a Single Set of Noisy Observation, Sparse reduced-order modelling: sensor-based dynamics to full-state estimation, Designing rotationally invariant neural networks from PDEs and variational methods, Asymptotic Theory of \(\boldsymbol \ell _1\) -Regularized PDE Identification from a Single Noisy Trajectory, Data-driven sparse identification of nonlinear dynamical systems using linear multistep methods, Physics-incorporated convolutional recurrent neural networks for source identification and forecasting of dynamical systems, Model selection via reweighted partial sparse recovery, Learning sparse nonlinear dynamics via mixed-integer optimization, Physics-informed regularization and structure preservation for learning stable reduced models from data with operator inference, Learning-informed parameter identification in nonlinear time-dependent PDEs, Bayesian operator inference for data-driven reduced-order modeling, Assessment of end-to-end and sequential data-driven learning for non-intrusive modeling of fluid flows, Group projected subspace pursuit for identification of variable coefficient differential equations (GP-IDENT), Deep-OSG: deep learning of operators in semigroup, DNN modeling of partial differential equations with incomplete data, Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems, Principled interpolation of Green's functions learned from data, A method for computing inverse parametric PDE problems with random-weight neural networks, Parsimony as the ultimate regularizer for physics-informed machine learning, Data-driven inference of low order representations of observable dynamics for an airfoil model, Discovering stochastic partial differential equations from limited data using variational Bayes inference, Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics, Phase-amplitude coordinate-based neural networks for inferring oscillatory dynamics, Data-driven identification of parametric governing equations of dynamical systems using the signed cumulative distribution transform, A Review of Data‐Driven Discovery for Dynamic Systems, Structured model selection via ℓ1−ℓ2 optimization, Learning the nonlinear flux function of a hidden scalar conservation law from data, Data-driven learning of differential equations: combining data and model uncertainty, Connections between numerical algorithms for PDEs and neural networks, Identification of the flux function of nonlinear conservation laws with variable parameters, Data driven discovery of systems of ordinary differential equations using nonconvex multitask learning, SPADE4: sparsity and delay embedding based forecasting of epidemics, Nonintrusive Reduced-Order Models for Parametric Partial Differential Equations via Data-Driven Operator Inference, Learning partial differential equations for biological transport models from noisy spatio-temporal data, Data-driven model identification using forcing-induced limit cycles, Learning the Dynamics for Unknown Hyperbolic Conservation Laws Using Deep Neural Networks, Discovering first principle of behavioural change in disease transmission dynamics by deep learning, On mathematical modeling in image reconstruction and beyond, Learning physics by data for the motion of a sphere falling in a non-Newtonian fluid, Learning elliptic partial differential equations with randomized linear algebra, WeakIdent: weak formulation for identifying differential equation using narrow-fit and trimming, Recovery guarantees for polynomial coefficients from weakly dependent data with outliers, Forecasting of nonlinear dynamics based on symbolic invariance, Methods to recover unknown processes in partial differential equations using data, Sparse learning of partial differential equations with structured dictionary matrix, Numerical aspects for approximating governing equations using data, Data-driven discovery of PDEs in complex datasets, Data-Driven Identification of Parametric Partial Differential Equations, Robust data-driven discovery of governing physical laws with error bars, Identification of physical processes via combined data-driven and data-assimilation methods, Data driven governing equations approximation using deep neural networks, Deep learning of dynamics and signal-noise decomposition with time-stepping constraints, PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network, Extracting Structured Dynamical Systems Using Sparse Optimization With Very Few Samples, Structure-Preserving Method for Reconstructing Unknown Hamiltonian Systems From Trajectory Data, Data-driven identification of 2D partial differential equations using extracted physical features, Unsupervised discovery of interpretable hyperelastic constitutive laws, Model selection for dynamical systems via sparse regression and information criteria, Unnamed Item, $l_p$ Regularization for Ensemble Kalman Inversion, Optimization algorithms for parameter identification in parabolic partial differential equations, SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics, Physics-Constrained, Data-Driven Discovery of Coarse-Grained Dynamics, DL-PDE: Deep-Learning Based Data-Driven Discovery of Partial Differential Equations from Discrete and Noisy Data, IDENT: identifying differential equations with numerical time evolution, Machine learning subsurface flow equations from data, On the Convergence of the SINDy Algorithm, Model selection for hybrid dynamical systems via sparse regression, Data-driven discovery of governing equations for fluid dynamics based on molecular simulation, Constrained sparse Galerkin regression, 9 From the POD-Galerkin method to sparse manifold models, Deep learning of conjugate mappings, Sparse methods for automatic relevance determination, Intrusive and data-driven reduced order modelling of the rotating thermal shallow water equation, Sparse identification of nonlinear dynamics for model predictive control in the low-data limit, Ensemble Kalman inversion for sparse learning of dynamical systems from time-averaged data, Robust modeling of unknown dynamical systems via ensemble averaged learning, Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers, Poincaré maps for multiscale physics discovery and nonlinear Floquet theory

Uses Software

• UNLocBoX

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Numerical differentiation of noisy, nonsmooth data
• Sparse + low-energy decomposition for viscous conservation laws
• PDEs with compressed solutions
• Introductory lectures on convex optimization. A basic course.
• A first-order primal-dual algorithm for convex problems with applications to imaging
• Proximal Splitting Methods in Signal Processing
• On the $O(1/n)$ Convergence Rate of the Douglas–Rachford Alternating Direction Method
• Compressive Sensing and Low-Rank Libraries for Classification of Bifurcation Regimes in Nonlinear Dynamical Systems
• Compressive sensing based machine learning strategy for characterizing the flow around a cylinder with limited pressure measurements
• Compressed plane waves yield a compactly supported multiresolution basis for the Laplace operator
• The Split Bregman Method for L1-Regularized Problems
• Spectral Methods for Time-Dependent Problems
• Automated reverse engineering of nonlinear dynamical systems
• Splitting Algorithms for the Sum of Two Nonlinear Operators
• Homogenization of Linear Transport Equations with Oscillatory Vector Fields
• De-noising by soft-thresholding
• Sparse dynamics for partial differential equations
• Compressed modes for variational problems in mathematics and physics
• On the Compressive Spectral Method
• An $L^1$ Penalty Method for General Obstacle Problems
• Sparsity and incoherence in compressive sampling
• Stable signal recovery from incomplete and inaccurate measurements