Structure-informed operator learning for parabolic Partial Differential Equations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Benth, Fred Espen, Detering, Nils, Galimberti, Luca
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909389526401024
author Benth, Fred Espen
Detering, Nils
Galimberti, Luca
author_facet Benth, Fred Espen
Detering, Nils
Galimberti, Luca
contents In this paper, we present a framework for learning the solution map of a backward parabolic Cauchy problem. The solution depends continuously but nonlinearly on the final data, source, and force terms, all residing in Banach spaces of functions. We utilize Fréchet space neural networks (Benth et al. (2023)) to address this operator learning problem. Our approach provides an alternative to Deep Operator Networks (DeepONets), using basis functions to span the relevant function spaces rather than relying on finite-dimensional approximations through censoring. With this method, structural information encoded in the basis coefficients is leveraged in the learning process. This results in a neural network designed to learn the mapping between infinite-dimensional function spaces. Our numerical proof-of-concept demonstrates the effectiveness of our method, highlighting some advantages over DeepONets.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Structure-informed operator learning for parabolic Partial Differential Equations
Benth, Fred Espen
Detering, Nils
Galimberti, Luca
Analysis of PDEs
Numerical Analysis
Probability
In this paper, we present a framework for learning the solution map of a backward parabolic Cauchy problem. The solution depends continuously but nonlinearly on the final data, source, and force terms, all residing in Banach spaces of functions. We utilize Fréchet space neural networks (Benth et al. (2023)) to address this operator learning problem. Our approach provides an alternative to Deep Operator Networks (DeepONets), using basis functions to span the relevant function spaces rather than relying on finite-dimensional approximations through censoring. With this method, structural information encoded in the basis coefficients is leveraged in the learning process. This results in a neural network designed to learn the mapping between infinite-dimensional function spaces. Our numerical proof-of-concept demonstrates the effectiveness of our method, highlighting some advantages over DeepONets.
title Structure-informed operator learning for parabolic Partial Differential Equations
topic Analysis of PDEs
Numerical Analysis
Probability
url https://arxiv.org/abs/2411.09511