Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dang, Zhenhua, Zhang, Lei, Wang, Long, He, Guowei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908980572323840
author Dang, Zhenhua
Zhang, Lei
Wang, Long
He, Guowei
author_facet Dang, Zhenhua
Zhang, Lei
Wang, Long
He, Guowei
contents Data-driven discovery of governing equations has advanced significantly in recent years; however, existing methods often struggle in multiscale systems where dynamically significant terms may have small coefficients. Therefore, we propose Balance-Guided SINDy (BG-SINDy) inspired by the principle of dominant balance, which reformulates $\ell_0$-constrained sparse regression as a term-level $\ell_{2,0}$-regularized problem and solves it using a progressive pruning strategy. Terms are ranked according to their relative contributions to the governing equation balance rather than their absolute coefficient magnitudes. Based on this criterion, BG-SINDy alternates between least-squares regression and elimination of negligible terms, thereby preserving dynamically significant terms even when their coefficients are small. Numerical experiments on the Korteweg--de Vries equation with a small dispersion coefficient, a modified Burgers equation with vanishing hyperviscosity, a modified Kuramoto--Sivashinsky equation with multiple small-coefficient terms, and a two-dimensional reaction--diffusion system demonstrate the validity of BG-SINDy in discovering small-coefficient terms. The proposed method thus provides an efficient approach for discovering governing equations that contain small-coefficient terms.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18414
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms
Dang, Zhenhua
Zhang, Lei
Wang, Long
He, Guowei
Machine Learning
Numerical Analysis
Data-driven discovery of governing equations has advanced significantly in recent years; however, existing methods often struggle in multiscale systems where dynamically significant terms may have small coefficients. Therefore, we propose Balance-Guided SINDy (BG-SINDy) inspired by the principle of dominant balance, which reformulates $\ell_0$-constrained sparse regression as a term-level $\ell_{2,0}$-regularized problem and solves it using a progressive pruning strategy. Terms are ranked according to their relative contributions to the governing equation balance rather than their absolute coefficient magnitudes. Based on this criterion, BG-SINDy alternates between least-squares regression and elimination of negligible terms, thereby preserving dynamically significant terms even when their coefficients are small. Numerical experiments on the Korteweg--de Vries equation with a small dispersion coefficient, a modified Burgers equation with vanishing hyperviscosity, a modified Kuramoto--Sivashinsky equation with multiple small-coefficient terms, and a two-dimensional reaction--diffusion system demonstrate the validity of BG-SINDy in discovering small-coefficient terms. The proposed method thus provides an efficient approach for discovering governing equations that contain small-coefficient terms.
title Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2604.18414