Enregistré dans:
Détails bibliographiques
Auteurs principaux: Serrano, Louis, Wang, Thomas X, Naour, Etienne Le, Vittaut, Jean-Noël, Gallinari, Patrick
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.02176
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914979619274752
author Serrano, Louis
Wang, Thomas X
Naour, Etienne Le
Vittaut, Jean-Noël
Gallinari, Patrick
author_facet Serrano, Louis
Wang, Thomas X
Naour, Etienne Le
Vittaut, Jean-Noël
Gallinari, Patrick
contents We present AROMA (Attentive Reduced Order Model with Attention), a framework designed to enhance the modeling of partial differential equations (PDEs) using local neural fields. Our flexible encoder-decoder architecture can obtain smooth latent representations of spatial physical fields from a variety of data types, including irregular-grid inputs and point clouds. This versatility eliminates the need for patching and allows efficient processing of diverse geometries. The sequential nature of our latent representation can be interpreted spatially and permits the use of a conditional transformer for modeling the temporal dynamics of PDEs. By employing a diffusion-based formulation, we achieve greater stability and enable longer rollouts compared to conventional MSE training. AROMA's superior performance in simulating 1D and 2D equations underscores the efficacy of our approach in capturing complex dynamical behaviors.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02176
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
Serrano, Louis
Wang, Thomas X
Naour, Etienne Le
Vittaut, Jean-Noël
Gallinari, Patrick
Machine Learning
We present AROMA (Attentive Reduced Order Model with Attention), a framework designed to enhance the modeling of partial differential equations (PDEs) using local neural fields. Our flexible encoder-decoder architecture can obtain smooth latent representations of spatial physical fields from a variety of data types, including irregular-grid inputs and point clouds. This versatility eliminates the need for patching and allows efficient processing of diverse geometries. The sequential nature of our latent representation can be interpreted spatially and permits the use of a conditional transformer for modeling the temporal dynamics of PDEs. By employing a diffusion-based formulation, we achieve greater stability and enable longer rollouts compared to conventional MSE training. AROMA's superior performance in simulating 1D and 2D equations underscores the efficacy of our approach in capturing complex dynamical behaviors.
title AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
topic Machine Learning
url https://arxiv.org/abs/2406.02176