Deep learning-based schemes for singularly perturbed convection-diffusion problems - Université Paris Cité Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Deep learning-based schemes for singularly perturbed convection-diffusion problems

Résumé

Deep learning-based numerical schemes such as Physically Informed Neural Networks (PINNs) have recently emerged as an alternative to classical numerical schemes for solving Partial Differential Equations (PDEs). They are very appealing at first sight because implementing vanilla versions of PINNs based on strong residual forms is easy, and neural networks offer very high approximation capabilities. However, when the PDE solutions are low regular, an expert insight is required to build deep learning formulations that do not incur in variational crimes. Optimization solvers are also significantly challenged, and can potentially spoil the final quality of the approximated solution due to the convergence to bad local minima, and bad generalization capabilities. In this paper, we present an exhaustive numerical study of the merits and limitations of these schemes when solutions exhibit low-regularity, and compare performance with respect to more benign cases when solutions are very smooth. As a support for our study, we consider singularly perturbed convection-diffusion problems where the regularity of solutions typically degrades as certain multiscale parameters go to zero.
Fichier principal
Vignette du fichier
Article_CEMRACS.pdf (1.58 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03664049 , version 1 (10-05-2022)

Identifiants

Citer

Adrien Beguinet, Virginie Ehrlacher, Roberta Flenghi, Maria Fuente-Ruiz, Olga Mula, et al.. Deep learning-based schemes for singularly perturbed convection-diffusion problems. 2022. ⟨hal-03664049⟩
178 Consultations
179 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More