Discovery of Partial Differential Equations from Highly Noisy and Sparse Data with Physics-Informed Information Criterion

Citations Over TimeTop 10% of 2023 papers

Abstract

Data-driven discovery of partial differential equations (PDEs) has recently made tremendous progress, and many canonical PDEs have been discovered successfully for proof of concept. However, determining the most proper PDE without prior references remains challenging in terms of practical applications. In this work, a physics-informed information criterion (PIC) is proposed to measure the parsimony and precision of the discovered PDE synthetically. The proposed PIC achieves satisfactory robustness to highly noisy and sparse data on 7 canonical PDEs from different physical scenes, which confirms its ability to handle difficult situations. The PIC is also employed to discover unrevealed macroscale governing equations from microscopic simulation data in an actual physical scene. The results show that the discovered macroscale PDE is precise and parsimonious and satisfies underlying symmetries, which facilitates understanding and simulation of the physical process. The proposition of the PIC enables practical applications of PDE discovery in discovering unrevealed governing equations in broader physical scenes.

Related Papers

• → Semicircle law and freeness for random matrices with symmetries or correlations(2005)56 cited
• → Performance analysis of localization algorithms(2002)23 cited
• → Rank 2 distributions of Monge equations: Symmetries, equivalences, extensions(2011)20 cited
• → Global Phase Portraits for the Abel Quadratic Polynomial Differential Equations of the Second Kind With Z₂-symmetries(2017)5 cited
• Research on Video Format Conversion Algorithms(2006)