Mesh-free sparse identification of nonlinear dynamics

TL;DR

This paper introduces mesh-free SINDy, a neural network-based method for discovering governing equations of dynamical systems from irregular, noisy, and limited data without requiring structured grids.

Contribution

It presents a novel mesh-free algorithm leveraging neural networks and auto-differentiation for robust PDE identification from arbitrary sensor data.

Findings

Effective on multiple PDEs including Burgers', heat, KdV, and advection-diffusion.

Robust to high noise levels, up to 75%, with limited samples.

Computationally efficient, training under one minute.

Abstract

Identifying the governing equations of a dynamical system is one of the most important tasks for scientific modeling. However, this procedure often requires high-quality spatio-temporal data uniformly sampled on structured grids. In this paper, we propose mesh-free SINDy, a novel algorithm which leverages the power of neural network approximation as well as auto-differentiation to identify governing equations from arbitrary sensor placements and non-uniform temporal data sampling. We show that mesh-free SINDy is robust to high noise levels and limited data while remaining computationally efficient. In our implementation, the training procedure is straight-forward and nearly free of hyperparameter tuning, making mesh-free SINDy widely applicable to many scientific and engineering problems. In the experiments, we demonstrate its effectiveness on a series of PDEs including the Burgers' equation, the heat equation, the Korteweg-De Vries equation and the 2D advection-diffusion equation. We conduct detailed numerical experiments on all datasets, varying the noise levels and number of samples, and we also compare our approach to previous state-of-the-art methods. It is noteworthy that, even in high-noise and low-data scenarios, mesh-free SINDy demonstrates robust PDE discovery, achieving successful identification with up to 75% noise for the Burgers' equation using 5,000 samples and with as few as 100 samples and 1% noise. All of this is achieved within a training time of under one minute.