Volume 56, pp. 28-51, 2022.

Operator inference and physics-informed learning of low-dimensional models for incompressible flows

Peter Benner, Pawan Goyal, Jan Heiland, and Igor Pontes Duff


Reduced-order modeling has a long tradition in computational fluid dynamics. The ever-increasing significance of data for the synthesis of low-order models is well reflected in the recent successes of data-driven approaches such as Dynamic Mode Decomposition and Operator Inference. With this work, we discuss an approach to learning structured low-order models for incompressible flow from data that can be used for engineering studies such as control, optimization, and simulation. To that end, we utilize the intrinsic structure of the Navier-Stokes equations for incompressible flows and show that learning dynamics of the velocity and pressure can be decoupled, thus, leading to an efficient operator inference approach for learning the underlying dynamics of incompressible flows. Furthermore, we demonstrate the performance of the operator inference in learning low-order models using two benchmark problems and compare with an intrusive method, namely proper orthogonal decomposition, and other data-driven approaches.

Full Text (PDF) [1 MB], BibTeX

Key words

Computational fluid dynamics, scientific machine learning, incompressible flow, Navier-Stokes equations, operator inference

AMS subject classifications

37N10, 68T05, 76D05, 65F22, 93A15, 93C10

< Back