Towards a Machine Learning Pipeline in Reduced Order Modelling for Inverse Problems: Neural Networks for Boundary Parametrization, Dimensionality Reduction and Solution Manifold Approximation

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.

Automated summary

In this work, a model order reduction framework is proposed for dealing with inverse problems in a non-intrusive setting. The computational load of inverse problems, especially in a partial differential equation context, is huge due to the iterative optimization process. To accelerate this procedure, a numerical pipeline involving artificial neural networks is applied to parametrize the boundary conditions, compress the dimensionality of snapshots, and approximate the parametric solution manifold. This approach provides a general framework capable of ad-hoc parametrization of the inlet boundary and quickly converges to the optimal solution thanks to model order reduction. The results obtained by applying these methods to two different CFD test cases are presented in this contribution.