Weak SINDy: Galerkin-Based Data-Driven Model Selection

We present a weak formulation and discretization of the system discovery problem from noisy measurement data. This method of learning differential equations from data fits into a new class of algorithms that replace pointwise derivative approximations with linear transformations and a variance reduction technique. Our approach improves on the standard SINDy algorithm by orders of magnitude. We first show that in the noise-free regime, this so-called Weak SINDy (WSINDy) framework is capable of recovering the dynamic coefficients to very high accuracy, with the number of significant digits equal to the tolerance of the data simulation scheme. Next we show that the weak form naturally accounts for white noise by identifying the correct nonlinearities with coefficient error scaling favorably with the signal-to-noise ratio while significantly reducing the size of linear systems in the algorithm. In doing so, we combine the ease of implementation of the SINDy algorithm with the natural noise-reduction of integration to arrive at a more robust and user-friendly method of sparse recovery that correctly identifies systems in both small-noise and large-noise regimes.

[1]  Erica M. Rutter,et al.  Learning partial differential equations for biological transport models from noisy spatio-temporal data , 2019, Proceedings of the Royal Society A.

[2]  Paris Perdikaris,et al.  Machine learning of linear differential equations using Gaussian processes , 2017, J. Comput. Phys..

[3]  Guang Lin,et al.  Robust data-driven discovery of governing physical laws with error bars , 2018, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[4]  Hirotugu Akaike,et al.  On entropy maximization principle , 1977 .

[5]  David Welch,et al.  Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems , 2009, Journal of The Royal Society Interface.

[6]  Wen-Xu Wang,et al.  Predicting catastrophes in nonlinear dynamical systems by compressive sensing. , 2011, Physical review letters.

[7]  Germund Dahlquist,et al.  Numerical Methods in Scientific Computing: Volume 1 , 2008 .

[8]  Guang Lin,et al.  Robust subsampling-based sparse Bayesian inference to tackle four challenges (large noise, outliers, data integration, and extrapolation) in the discovery of physical laws from data , 2019, ArXiv.

[9]  Kailiang Wu,et al.  Numerical Aspects for Approximating Governing Equations Using Data , 2018, J. Comput. Phys..

[10]  Ruth E. Baker,et al.  Using Experimental Data and Information Criteria to Guide Model Selection for Reaction–Diffusion Problems in Mathematical Biology , 2018, Bulletin of Mathematical Biology.

[11]  Mustafa Khammash,et al.  Parameter Estimation and Model Selection in Computational Biology , 2010, PLoS Comput. Biol..

[12]  Steven L. Brunton,et al.  Deep learning of dynamics and signal-noise decomposition with time-stepping constraints , 2018, J. Comput. Phys..

[13]  Yingjie Liu,et al.  IDENT: Identifying Differential Equations with Numerical Time Evolution , 2019, Journal of Scientific Computing.

[14]  Linan Zhang,et al.  On the Convergence of the SINDy Algorithm , 2018, Multiscale Model. Simul..

[15]  Hulin Wu,et al.  Identification of significant host factors for HIV dynamics modelled by non‐linear mixed‐effects models , 2002, Statistics in medicine.

[16]  H. Akaike.  A new look at the statistical model identification , 1974 .

[17]  D M Bortz,et al.  Model Selection and Mixed-Effects Modeling of HIV Infection Dynamics , 2006, Bulletin of mathematical biology.

[18]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.

[19]  Matthew J Simpson,et al.  Using Experimental Data and Information Criteria to Guide Model Selection for Reaction–Diffusion Problems in Mathematical Biology , 2018, bioRxiv.

[20]  Guang Lin,et al.  SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations , 2021, J. Comput. Phys..

[21]  Hayden Schaeffer,et al.  Sparse model selection via integral terms. , 2017, Physical review. E.

[22]  Alireza Doostan,et al.  Sparse Identification of Nonlinear Dynamical Systems via Reweighted 𝓁s1-regularized Least Squares , 2020, Computer Methods in Applied Mechanics and Engineering.

[23]  Qiang Du,et al.  Discovery of Dynamics Using Linear Multistep Methods , 2019, SIAM J. Numer. Anal..