Using Noisy or Incomplete Data to Discover Models of Spatiotemporal Dynamics

Abstract

Sparse regression has recently emerged as an attractive approach for discovering models of spatiotemporally complex dynamics directly from data. In many instances, such models are in the form of nonlinear partial differential equations (PDEs); hence sparse regression typically requires evaluation of various partial derivatives. However, accurate evaluation of derivatives, especially of high order, is infeasible when the data are noisy, which has a dramatic negative effect on the result of regression. We present a novel and rather general approach that addresses this difficulty by using a weak formulation of the problem. For instance, it allows accurate reconstruction of PDEs involving high-order derivatives, such as the Kuramoto-Sivashinsky equation, from data with a considerable amount of noise. The flexibility of our approach also allows reconstruction of PDE models that involve latent variables which cannot be measured directly with acceptable accuracy. This is illustrated by reconstructing a model for a weakly turbulent flow in a thin fluid layer, where neither the forcing nor the pressure field is known.

arXiv commentUnder review at Physical Review E

References in corpus (6)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Robust and optimal sparse regression for nonlinear PDE models
• Velocity Profile in a Two-Layer Kolmogorov-Like Flow
• Bifurcations in a Quasi-Two-Dimensional Kolmogorov-Like Flow
• Data-driven discovery of partial differential equation models with latent variables

Cited by in corpus (39)

• Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
• SINDy-PI: A Robust Algorithm for Parallel Implicit Sparse Identification of Nonlinear Dynamics
• Weak SINDy For Partial Differential Equations
• PySINDy: A comprehensive Python package for robust sparse system identification
• Robust learning from noisy, incomplete, high-dimensional experimental data via physically constrained symbolic regression
• Learning hydrodynamic equations for active matter from particle simulations and experiments
• Data-driven discovery of reduced plasma physics models from fully-kinetic simulations
• Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
• DySMHO: Data-Driven Discovery of Governing Equations for Dynamical Systems via Moving Horizon Optimization
• Sparse nonlinear models of chaotic electroconvection
• Derivative-based SINDy (DSINDy): Addressing the challenge of discovering governing equations from noisy data
• SINDy-BVP: Sparse Identification of Nonlinear Dynamics for Boundary Value Problems
• Variational system identification of the partial differential equations governing microstructure evolution in materials: Inference over sparse and spatially unrelated data
• Data-driven discovery of active nematic hydrodynamics
• Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
• Direct Estimation of Parameters in ODE Models Using WENDy: Weak-form Estimation of Nonlinear Dynamics
• PySINDy: A Python package for the Sparse Identification of Nonlinear Dynamics from Data
• Noise-aware Physics-informed Machine Learning for Robust PDE Discovery
• Finding nonlinear system equations and complex network structures from data: a sparse optimization approach
• WeakIdent: Weak formulation for Identifying Differential Equations using Narrow-fit and Trimming
• Learning physically consistent mathematical models from data using group sparsity
• Data-driven discovery and extrapolation of parameterized pattern-forming dynamics
• Learning developmental mode dynamics from single-cell trajectories
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• Sparse Identification of Slow Timescale Dynamics
• Learning fluid physics from highly turbulent data using sparse physics-informed discovery of empirical relations (SPIDER)
• Deeptime: a Python library for machine learning dynamical models from time series data
• Unraveling biochemical spatial patterns: machine learning approaches to the inverse problem of Turing patterns
• Data-driven model construction for anisotropic dynamics of active matter
• SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
• Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case
• Adaptive Uncertainty-Guided Model Selection for Data-Driven PDE Discovery
• Robust discovery of partial differential equations in complex situations
• Dynamics of tidal spiral arms: Machine learning-assisted identification of equations and application to the Milky Way
• CTSR: Cartesian tensor-based sparse regression for data-driven discovery of high-dimensional invariant governing equations
• Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
• The Machine Learning Approach to Moment Closure Relations for Plasma: A Review
• Data-driven detection of drifting system parameters
• Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization