Mesh-Informed Neural Networks for Operator Learning in Finite Element Spaces
Open Access
- 23 September 2023
- journal article
- research article
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 97 (2) , 1-41
Abstract
Thanks to their universal approximation properties and new efficient training strategies, Deep Neural Networks are becoming a valuable tool for the approximation of mathematical operators. In the present work, we introduce Mesh-Informed Neural Networks (MINNs), a class of architectures specifically tailored to handle mesh based functional data, and thus of particular interest for reduced order modeling of parametrized Partial Differential Equations (PDEs). The driving idea behind MINNs is to embed hidden layers into discrete functional spaces of increasing complexity, obtained through a sequence of meshes defined over the underlying spatial domain. The approach leads to a natural pruning strategy which enables the design of sparse architectures that are able to learn general nonlinear operators. We assess this strategy through an extensive set of numerical experiments, ranging from nonlocal operators to nonlinear diffusion PDEs, where MINNs are compared against more traditional architectures, such as classical fully connected Deep Neural Networks, but also more recent ones, such as DeepONets and Fourier Neural Operators. Our results show that MINNs can handle functional data defined on general domains of any shape, while ensuring reduced training times, lower computational costs, and better generalization capabilities, thus making MINNs very well-suited for demanding applications such as Reduced Order Modeling and Uncertainty Quantification for PDEs.Keywords
All Related Versions
Funding Information
- H2020 Health (ERAPERMED2018-244)
This publication has 40 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Gap geometry dictates epithelial closure efficiencyNature Communications, 2015
- Motion Segmentation of Truncated Signed Distance Function Based Volumetric Surfaces2015
- A computational model of drug delivery through microcirculation to compare different tumor treatmentsInternational Journal for Numerical Methods in Biomedical Engineering, 2014
- Assessing the ability of the 2D Fisher–KPP equation to model cell-sheet wound closureMathematical Biosciences, 2014
- Pruning algorithms of neural networks — a comparative studyOpen Computer Science, 2013
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Voronoi diagrams—a survey of a fundamental geometric data structureACM Computing Surveys, 1991
- Models of epidermal wound healingProceedings Of The Royal Society B-Biological Sciences, 1990
- Diffusion-Induced Chaos in Reaction SystemsProgress of Theoretical Physics Supplement, 1978