Enregistré dans:
Détails bibliographiques
Auteurs principaux: Martínez-Esteban, Andrés, Calvo-Barlés, Pablo, Martín-Moreno, Luis, Rodrigo, Sergio G
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2507.21800
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915416909021184
author Martínez-Esteban, Andrés
Calvo-Barlés, Pablo
Martín-Moreno, Luis
Rodrigo, Sergio G
author_facet Martínez-Esteban, Andrés
Calvo-Barlés, Pablo
Martín-Moreno, Luis
Rodrigo, Sergio G
contents Physics-informed neural networks (PINNs) are numerical solvers that embed all the physical information of a system into the loss function of a neural network. In this way the learned solution accounts for data (if available), the governing differential equations, or any other constraint known of the physical problem. However, they face serious issues, notably their tendency to converge on trivial or misleading solutions. The latter occurs when, although the loss function reaches low values the model makes incorrect predictions. These difficulties become especially significant in differential equations involving multi-scale behavior, such as rapidly varying terms and solutions exhibiting strong oscillatory behavior. To address these challenges, we introduce the Dynamical Boundary Constraint (DBC) algorithm, which imposes restrictions on the loss function based on prior training of the PINN. To demonstrate its applicability, we tested this approach on examples of different areas of physics.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21800
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Informed Neural Networks with Dynamical Boundary Constraints
Martínez-Esteban, Andrés
Calvo-Barlés, Pablo
Martín-Moreno, Luis
Rodrigo, Sergio G
Computational Physics
Physics-informed neural networks (PINNs) are numerical solvers that embed all the physical information of a system into the loss function of a neural network. In this way the learned solution accounts for data (if available), the governing differential equations, or any other constraint known of the physical problem. However, they face serious issues, notably their tendency to converge on trivial or misleading solutions. The latter occurs when, although the loss function reaches low values the model makes incorrect predictions. These difficulties become especially significant in differential equations involving multi-scale behavior, such as rapidly varying terms and solutions exhibiting strong oscillatory behavior. To address these challenges, we introduce the Dynamical Boundary Constraint (DBC) algorithm, which imposes restrictions on the loss function based on prior training of the PINN. To demonstrate its applicability, we tested this approach on examples of different areas of physics.
title Physics-Informed Neural Networks with Dynamical Boundary Constraints
topic Computational Physics
url https://arxiv.org/abs/2507.21800