Nonlinear model order reduction for problems with microstructure using mesh informed neural networks.

Many applications in computational physics involve approximating problems with microstructure, characterized by multiple spatial scales in their data. However, these numerical solutions are often computationally expensive due to the need to capture fine details at small scales. As a result, simulating such phenomena becomes unaffordable for many-query applications, such as parametrized systems with multiple scale-dependent features. Traditional projection-based reduced order models (ROMs) fail to resolve these issues, even for second-order elliptic PDEs commonly found in engineering applications. To address this, we propose an alternative nonintrusive strategy to build a ROM, that combines classical proper orthogonal decomposition (POD) with a suitable neural network (NN) model to account for the small scales. Specifically, we employ sparse mesh-informed neural networks (MINNs), which handle both spatial dependencies in the solutions and model parameters simultaneously. We evaluate the performance of this strategy on benchmark problems and then apply it to approximate a real-life problem involving the impact of microcirculation in transport phenomena through the tissue microenvironment. • Numerical solution of microstructured problems imply high computational costs • Linear reduced order models do not capture the high-frequency modes of the solution • Deep learning-based approaches can be exploited to retrieve these intricate patterns • Our novel approach combines a non-intrusive reduced order model with a closure model • High dimensional data are handled leveraging on mesh-informed neural networks [ABSTRACT FROM AUTHOR]