stat.MLNov 12, 2026

Multifidelity Operator Inference for Dynamical Systems

Authors: Vignesh Sella, Anirban Chaudhuri, Karen Willcox

Organizations: Oden Institute for Computational Engineering and Sciences · Oden Institute for Computational Engineering and Sciences, Department of Aerospace Engineering and Engineering Mechanics

Abstract

This paper presents a multifidelity (MF) formulation of Operator Inference (OpInf) for learning non-intrusive, physics-based reduced-order models (ROMs) of nonlinear dynamical systems. OpInf learns reduced operators from projections of snapshot data by solving a least squares regression problem. However, generating high-fidelity snapshots can be computationally expensive, limiting parameter coverage and the temporal extent of training trajectories for many aerospace applications, which can lead to inaccurate or unstable ROM predictions. This work proposes MF-OpInf, which combines limited high-fidelity snapshots with more plentiful low-fidelity snapshots through a control-variates-inspired MF least squares formulation to learn a single set of reduced operators across multiple trajectories. Low-fidelity trajectories provide additional parameter coverage and extend beyond the high-fidelity training time horizon. The low-fidelity snapshots are also used to construct an improved reduced basis through weighted proper orthogonal decomposition. We demonstrate MF-OpInf on a nonlinear reaction-diffusion problem with parametrized sinusoidal forcing and a two-dimensional incompressible flow past a cylinder with a parametrized inlet pulse. In these experiments, under an equal training simulation budget, MF-OpInf reduces the mean relative prediction error at unseen parameters by up to 87%87\% for the reaction-diffusion problem and 28%28\% for the cylinder flow problem over the test time regime, which extends beyond the high-fidelity training time horizon. These results demonstrate that MF-OpInf can improve temporal extrapolation and prediction at unseen parameters without increasing the training simulation budget.

Explore similar work

CardsList
  1. Multifidelity Operator Inference for Non-intrusive Model Reduction under Data Scarcity

    Nov 10, 2026Vivian Zhang, Tomoki Koike, Atticus Rex +1PDE Surrogate ModelingReduced-Order Modeling

  2. NN-OpInf: an operator inference approach using structure-preserving composable neural networks

    Mar 9, 2026Eric Parish, Anthony Gruber, Patrick Blonigan +1Structure-Preserving Neural NetworksReduced-Order Modeling

  3. In-Context Learning for Multi-Fidelity Multiscale Model Closure and Cross-Operator Out-Of-Distribution Generalization

    Oct 28, 2026Xinyuan Li, Matthew Zahr, Panos Stinis +1Multifidelity ModelingPDE Operator Learning