Learning physics-based reduced-order models from data using nonlinear manifolds

TL;DR

This paper introduces a new data-driven approach for creating reduced-order models of dynamical systems using learned nonlinear manifolds, which improves accuracy over traditional linear methods.

Contribution

The paper proposes a novel method combining nonlinear manifold learning with operator inference for more accurate reduced-order modeling.

Findings

Demonstrates improved accuracy over linear subspace methods

Shows generalizability across various nonlinear problems

Validates approach through numerical experiments

Abstract

We present a novel method for learning reduced-order models of dynamical systems using nonlinear manifolds. First, we learn the manifold by identifying nonlinear structure in the data through a general representation learning problem. The proposed approach is driven by embeddings of low-order polynomial form. A projection onto the nonlinear manifold reveals the algebraic structure of the reduced-space system that governs the problem of interest. The matrix operators of the reduced-order model are then inferred from the data using operator inference. Numerical experiments on a number of nonlinear problems demonstrate the generalizability of the methodology and the increase in accuracy that can be obtained over reduced-order modeling methods that employ a linear subspace approximation.