A DeepONet multi-fidelity approach for residual learning in reduced order modeling

Abstract

In the present work, we introduce a novel approach to enhance the precision of reduced order models by exploiting a multi-fidelity perspective and DeepONets. Reduced models provide a real-time numerical approximation by simplifying the original model. The error introduced by the such operation is usually neglected and sacrificed in order to reach a fast computation. We propose to couple the model reduction to a machine learning residual learning, such that the above-mentioned error can be learned by a neural network and inferred for new predictions. We emphasize that the framework maximizes the exploitation of high-fidelity information, using it for building the reduced order model and for learning the residual. In this work, we explore the integration of proper orthogonal decomposition (POD), and gappy POD for sensors data, with the recent DeepONet architecture. Numerical investigations for a parametric benchmark function and a nonlinear parametric Navier-Stokes problem are presented.

References in corpus (23)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• Data-Driven Sparse Sensor Placement for Reconstruction
• Inferring solutions of differential equations using noisy multi-fidelity data
• Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems
• Multi-fidelity Bayesian Neural Networks: Algorithms and Applications
• Nonlinear Model Order Reduction via Lifting Transformations and Proper Orthogonal Decomposition
• Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantities
• Compressive sensing and low-rank libraries for classification of bifurcation regimes in nonlinear dynamical systems
• Operator inference for non-intrusive model reduction with quadratic manifolds
• Leveraging reduced-order models for state estimation using deep learning
• The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations
• A non-intrusive approach for the reconstruction of POD modal coefficients through active subspaces
• Hull shape design optimization with parameter space and model reductions, and self-learning mesh morphing
• Dimension reduction in heterogeneous parametric spaces with application to naval engineering shape design problems
• A multi-fidelity approach coupling parameter space reduction and non-intrusive POD with application to structural optimization of passenger ship hulls
• A supervised learning approach involving active subspaces for an efficient genetic algorithm in high-dimensional optimization problems
• Enhancing CFD predictions in shape design problems by model and parameter space reduction
• On the comparison of LES data-driven reduced order approaches for hydroacoustic analysis
• Model Order Reduction in Neuroscience
• Inadequacy of Linear Methods for Minimal Sensor Placement and Feature Selection in Nonlinear Systems; a New Approach Using Secants
• Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation
• Hyper-differential sensitivity analysis with respect to model discrepancy: Optimal solution updating

Cited by in corpus (2)

• A Latent Variable Approach for Non-Hierarchical Multi-Fidelity Adaptive Sampling
• Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification