Work

Towards Model Discovery Using Domain Decomposition and PINNs

Year: 2025

Type: article

Abstract: We enhance machine learning algorithms for learning model parameters in complex systems represented by differential equations with domain decomposition methods. The study evaluates the performance of two approaches, namely (vanilla) Physics-Informed Neural Networks (PINNs) and Finite Basis Physics-Informed Neural Networks (FBPINNs), in learning the dynamics of test models with a quasi-stationary longtime behavior. We test the approaches for data sets in different dynamical regions and with varying noise level. As results, the FBPINN approach better captures the overall dynamical behavior compared to the vanilla PINN approach, even in cases with data only from a time domain with quasi-stationary dynamics.

Source: IFAC-PapersOnLine

DOI: 10.1016/j.ifacol.2025.03.008

Authors: Tirtho S. Saha, Alexander Heinlein, Cordula Reisch

Institutions: Leibniz University Hannover, Delft University of Technology, Technische Universität Braunschweig

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4408885654

FWCI:

Cites: 10

Cited by:

Related to: 10