Unrolled-SINDy: A Stable Explicit Method for Non linear PDE Discovery from Sparsely Sampled Data

TL;DR

Unrolled-SINDy introduces an unrolling scheme that enhances the stability and accuracy of PDE discovery from sparsely sampled data, overcoming limitations of traditional SINDy methods.

Contribution

It presents a novel unrolling approach that decouples time step size from data sampling rate, improving PDE parameter recovery in sparse data scenarios.

Findings

Enables PDE discovery with sparse temporal data.

Improves stability of explicit methods for PDE identification.

Applicable with various numerical schemes and noise robustness.

Abstract

Identifying from observation data the governing differential equations of a physical dynamics is a key challenge in machine learning. Although approaches based on SINDy have shown great promise in this area, they still fail to address a whole class of real world problems where the data is sparsely sampled in time. In this article, we introduce Unrolled-SINDy, a simple methodology that leverages an unrolling scheme to improve the stability of explicit methods for PDE discovery. By decorrelating the numerical time step size from the sampling rate of the available data, our approach enables the recovery of equation parameters that would not be the minimizers of the original SINDy optimization problem due to large local truncation errors. Our method can be exploited either through an iterative closed-form approach or by a gradient descent scheme. Experiments show the versatility of our method. On both traditional SINDy and state-of-the-art noise-robust iNeuralSINDy, with different numerical schemes (Euler, RK4), our proposed unrolling scheme allows to tackle problems not accessible to non-unrolled methods.