Weak SINDy For Partial Differential Equations

Abstract

Sparse Identification of Nonlinear Dynamics (SINDy) is a method of system discovery that has been shown to successfully recover governing dynamical systems from data (Brunton et al., PNAS, '16; Rudy et al., Sci. Adv. '17). Recently, several groups have independently discovered that the weak formulation provides orders of magnitude better robustness to noise. Here we extend our Weak SINDy (WSINDy) framework introduced in (arXiv:2005.04339) to the setting of partial differential equations (PDEs). The elimination of pointwise derivative approximations via the weak form enables effective machine-precision recovery of model coefficients from noise-free data (i.e. below the tolerance of the simulation scheme) as well as robust identification of PDEs in the large noise regime (with signal-to-noise ratio approaching one in many well-known cases). This is accomplished by discretizing a convolutional weak form of the PDE and exploiting separability of test functions for efficient model identification using the Fast Fourier Transform. The resulting WSINDy algorithm for PDEs has a worst-case computational complexity of $\mathcal{O}(N^{D+1}\log (N))$ for datasets with $N$ points in each of $D+1$ dimensions (i.e. $\mathcal{O}(\log (N))$ operations per datapoint). Furthermore, our Fourier-based implementation reveals a connection between robustness to noise and the spectra of test functions, which we utilize in an \textit{a priori} selection algorithm for test functions. Finally, we introduce a learning algorithm for the threshold in sequential-thresholding least-squares (STLS) that enables model identification from large libraries, and we utilize scale-invariance at the continuum level to identify PDEs from poorly-scaled datasets. We demonstrate WSINDy's robustness, speed and accuracy on several challenging PDEs.

Code used in this manuscript is publicly available on GitHub at https://github.com/dm973/WSINDy PDE

References in corpus (12)

• Methods for Interpreting and Understanding Deep Neural Networks
• Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
• Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
• Weak SINDy: Galerkin-Based Data-Driven Model Selection
• Using Noisy or Incomplete Data to Discover Models of Spatiotemporal Dynamics
• DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
• Sparse Identification of Nonlinear Dynamical Systems via Reweighted ${\ell }_1$-regularized Least Squares
• Variational system identification of the partial differential equations governing microstructure evolution in materials: Inference over sparse and spatially unrelated data
• PySINDy: A Python package for the Sparse Identification of Nonlinear Dynamics from Data
• Detecting the maximum likelihood transition path from data of stochastic dynamic systems
• A Perspective on Regression and Bayesian Approaches for System Identification of Pattern Formation Dynamics
• Data-driven learning of non-autonomous systems

Cited by in corpus (41)

• Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
• PySINDy: A comprehensive Python package for robust sparse system identification
• Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
• Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
• Data-driven discovery of reduced plasma physics models from fully-kinetic simulations
• Derivative-based SINDy (DSINDy): Addressing the challenge of discovering governing equations from noisy data
• Learning Mean-Field Equations from Particle Data Using WSINDy
• EKF-SINDy: Empowering the extended Kalman filter with sparse identification of nonlinear dynamics
• Variational system identification of the partial differential equations governing microstructure evolution in materials: Inference over sparse and spatially unrelated data
• Direct Estimation of Parameters in ODE Models Using WENDy: Weak-form Estimation of Nonlinear Dynamics
• GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencoder
• Hypergraph reconstruction from dynamics
• Noise-aware Physics-informed Machine Learning for Robust PDE Discovery
• Discovery of partial differential equations from highly noisy and sparse data with physics-informed information criterion
• WeakIdent: Weak formulation for Identifying Differential Equations using Narrow-fit and Trimming
• Data-driven discovery and extrapolation of parameterized pattern-forming dynamics
• Model selection of chaotic systems from data with hidden variables using sparse data assimilation
• Learning Anisotropic Interaction Rules from Individual Trajectories in a Heterogeneous Cellular Population
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• Learning fluid physics from highly turbulent data using sparse physics-informed discovery of empirical relations (SPIDER)
• Auxiliary Functions as Koopman Observables: Data-Driven Analysis of Dynamical Systems via Polynomial Optimization
• SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
• Random Feature Models for Learning Interacting Dynamical Systems
• Adaptive Uncertainty-Guided Model Selection for Data-Driven PDE Discovery
• Influence of initial conditions on data-driven model identification and information entropy for ideal mhd problems
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Bayesian Learning of Coupled Biogeochemical-Physical Models
• Forecasting and predicting stochastic agent-based model data with biologically-informed neural networks
• Data-driven sparse modeling of oscillations in plasma space propulsion
• Robust discovery of partial differential equations in complex situations
• Online Weak-form Sparse Identification of Partial Differential Equations
• Constrained or Unconstrained? Neural-Network-Based Equation Discovery from Data
• BINDy -- Bayesian identification of nonlinear dynamics with reversible-jump Markov-chain Monte-Carlo
• Learning Hidden Physics and System Parameters with Deep Operator Networks
• Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
• Deriving thin-film averaged equations using computer algebra
• Model discovery in the sparse sampling regime
• OKRidge: Scalable Optimal k-Sparse Ridge Regression
• Sparse Identification for bifurcating phenomena in Computational Fluid Dynamics
• The Machine Learning Approach to Moment Closure Relations for Plasma: A Review
• Reaction-diffusion transport into core-shell geometry: Well-posedness and stability of stationary solutions