arXiv Analytics

Sign in

arXiv:2312.03496 [math.NA]AbstractReferencesReviewsResources

Variational Formulations of the Strong Formulation -- Forward and Inverse Modeling using Isogeometric Analysis and Physics-Informed Networks

Kent-Andre Mardal, Jarle Sogn, Marius Zeinhofer

Published 2023-12-06Version 1

The recently introduced Physics-Informed Neural Networks (PINNs) have popularized least squares formulations of both forward and inverse problems involving partial differential equations (PDEs) in strong form. We employ both Isogeometric Analysis and Physics-Informed Networks.

Categories: math.NA, cs.NA
Related articles: Most relevant | Search more
arXiv:2012.13003 [math.NA] (Published 2020-12-23)
Robust preconditioning and error estimates for optimal control of the convection-diffusion-reaction equation with limited observation in Isogeometric analysis
arXiv:2107.05337 [math.NA] (Published 2021-07-12)
Combining p-multigrid and multigrid reduced in time methods to obtain a scalable solver for Isogeometric Analysis
arXiv:2408.17273 [math.NA] (Published 2024-08-30)
Overlapping subspaces and singular systems with application to Isogeometric Analysis

Links

Toolbox