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

Abstract

In this work, we propose a model order reduction framework to deal with inverse problems in a non-intrusive setting. Inverse problems, especially in a partial differential equation context, require a huge computational load due to the iterative optimization process. To accelerate such a procedure, we apply a numerical pipeline that involves artificial neural networks to parametrize the boundary conditions of the problem in hand, compress the dimensionality of the (full-order) snapshots, and approximate the parametric solution manifold. It derives a general framework capable to provide an ad-hoc parametrization of the inlet boundary and quickly converges to the optimal solution thanks to model order reduction. We present in this contribution the results obtained by applying such methods to two different CFD test cases.

References in corpus (9)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Adaptive construction of surrogates for the Bayesian solution of inverse problems
• The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations
• Hull shape design optimization with parameter space and model reductions, and self-learning mesh morphing
• A greedy non-intrusive reduced order model for shallow water equations
• Enhancing CFD predictions in shape design problems by model and parameter space reduction
• An efficient computational framework for naval shape design and optimization problems by means of data-driven reduced order modeling techniques
• Basic Ideas and Tools for Projection-Based Model Reduction of Parametric Partial Differential Equations
• A non-intrusive data-driven ROM framework for hemodynamics problems

Cited by in corpus (2)

• A DeepONet multi-fidelity approach for residual learning in reduced order modeling
• Stabilizing and Solving Unique Continuation Problems by Parameterizing Data and Learning Finite Element Solution Operators