Sparse dynamical system identification with simultaneous structural parameters and initial condition estimation

TL;DR

This paper introduces ISINDy, a method that simultaneously identifies the structure, parameters, and initial conditions of nonlinear ODEs from noisy data, improving robustness and interpretability over existing approaches.

Contribution

The paper proposes an integral SINDy approach that estimates model structure, parameters, and initial conditions simultaneously from noisy data, enhancing robustness and interpretability.

Findings

Accurately recovers model structure and parameters from noisy data.

Demonstrates robustness to noise in various nonlinear systems.

Achieves parsimonious and interpretable models.

Abstract

Sparse Identification of Nonlinear Dynamics (SINDy) has been shown to successfully recover governing equations from data; however, this approach assumes the initial condition to be exactly known in advance and is sensitive to noise. In this work we propose an integral SINDy (ISINDy) method to simultaneously identify model structure and parameters of nonlinear ordinary differential equations (ODEs) from noisy time-series observations. First, the states are estimated via penalized spline smoothing and then substituted into the integral-form numerical discretization solver, leading to a pseudo-linear regression. The sequential threshold least squares is performed to extract the fewest active terms from the overdetermined set of candidate features, thereby estimating structural parameters and initial condition simultaneously and meanwhile, making the identified dynamics parsimonious and interpretable. Simulations detail the method's recovery accuracy and robustness to noise. Examples include a logistic equation, Lokta-Volterra system, and Lorenz system.