Model Order Reduction

Model order reduction (MOR) aims to create simplified, computationally efficient representations of complex systems, such as those described by high-dimensional partial differential equations or large-scale circuits. Current research emphasizes data-driven approaches, employing neural networks (including autoencoders, graph neural networks, and DeepONets) and techniques like Proper Orthogonal Decomposition (POD) and kernel principal component analysis (KPCA) to learn low-dimensional representations that capture essential system dynamics. These advancements enable faster simulations, improved control design for high-dimensional systems (e.g., soft robots, aircraft), and efficient solutions to inverse problems, impacting fields ranging from computational fluid dynamics to microelectronics.

Papers

June 5, 2024

GFN: A graph feedforward network for resolution-invariant reduced operator learning in multifidelity applications
Oisín M. Morrison, Federico Pichi, Jan S. Hesthaven
Neural Network Graph Convolutional Network Operator Learning Model Order Reduction Multifidelity Estimator

May 30, 2024

Non-intrusive data-driven model order reduction for circuits based on Hammerstein architectures
Joshua Hanson, Biliana Paskaleva, Pavel Bochev
Data Driven Large Scale Circuit Parsimonious Machine Learning Non Intrusive Model Order Reduction

May 21, 2024

Soft Synergies: Model Order Reduction of Hybrid Soft-Rigid Robots via Optimal Strain Parameterization
Abdulaziz Y. Alkayas, Anup Teejo Mathew, Daniel Feliu-Talegon, Ping Deng, Thomas George Thuruthel, Federico Renda
Soft Robot Soft Manipulator Emerging Synergy Model Order Reduction Strain Generation Soft Rigid

March 27, 2024

Nonlinear model reduction for operator learning
Hamidreza Eivazi, Stefan Wittek, Andreas Rausch
Operator Learning Deep Operator Network Proper Orthogonal Decomposition Kernel Principal Component Analysis Model Order Reduction Nonlinear Model Reduction

March 21, 2024

Model order reduction of deep structured state-space models: A system-theoretic approach
Marco Forgione, Manas Mejari, Dario Piga
Parameter Identification Model Order Reduction System Theoretic

December 11, 2023

Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems
Marco Lepri, Davide Bacciu, Cosimo Della Santina
High Dimensional Control Design Underactuated System Model Order Reduction Based Reduced Order Model Preserving Loss Mass Damper

May 15, 2023

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs
Federico Pichi, Beatriz Moya, Jan S. Hesthaven
Graph Drawing Autoencoder Architecture Graph Autoencoders Proper Orthogonal Decomposition Model Order Reduction Nonlinear Model Reduction Data Driven Model Reduction

March 16, 2023

Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions
Jorio Cocola, John Tencer, Francesco Rizzi, Eric Parish, Patrick Blonigan
High Efficiency Surrogate Model Manifold Learning Reduced Order Dimensional Manifold Model Order Reduction Nonlinear Model Reduction

January 23, 2023

An iterative multi-fidelity approach for model order reduction of multi-dimensional input parametric PDE systems
Manisha Chetry, Domenico Borzacchiello, Lucas Lestandi, Luisa Rocha Da Silva
Large Scale Multi Fidelity Fidelity Model Parametric PDE Model Order Reduction Reduced Basis

October 26, 2022

Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation
Anna Ivagnes, Nicola Demo, Gianluigi Rozza
Neural Network Inverse Problem Dimensionality Reduction Boundary Prediction Model Order Reduction Manifold Approximation Parametric Solution

July 27, 2022

A Proper Orthogonal Decomposition approach for parameters reduction of Single Shot Detector networks
Laura Meneghetti, Nicola Demo, Gianluigi Rozza
Convolutional Neural Network Computer Vision Dimensionality Reduction Proper Orthogonal Decomposition Single Shot Detector Model Order Reduction Parameter Reduction

April 8, 2022

Active-learning-based non-intrusive Model Order Reduction
Qinyu Zhuang, Dirk Hartmann, Hans Joachim Bungartz, Juan Manuel Lorenzi
Active Learning State Space Reduced Order Order Model Compact Model Non Intrusive Model Order Reduction

February 22, 2022

CD-ROM: Complemented Deep-Reduced Order Model
Emmanuel Menier, Michele Alessandro Bucci, Mouadh Yagoubi, Lionel Mathelin, Marc Schoenauer
Reduced Order Computational Fluid Dynamic Navier Stokes Proper Orthogonal Decomposition Model Order Reduction Based Reduced Order Model

Model Order Reduction

Papers

GFN: A graph feedforward network for resolution-invariant reduced operator learning in multifidelity applications

Non-intrusive data-driven model order reduction for circuits based on Hammerstein architectures

Soft Synergies: Model Order Reduction of Hybrid Soft-Rigid Robots via Optimal Strain Parameterization

Nonlinear model reduction for operator learning

Model order reduction of deep structured state-space models: A system-theoretic approach

Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions

An iterative multi-fidelity approach for model order reduction of multi-dimensional input parametric PDE systems

Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation

A Proper Orthogonal Decomposition approach for parameters reduction of Single Shot Detector networks

Active-learning-based non-intrusive Model Order Reduction

CD-ROM: Complemented Deep-Reduced Order Model