Towards Optimally Weighted Physics-Informed Neural Networks in Ocean Modelling - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Towards Optimally Weighted Physics-Informed Neural Networks in Ocean Modelling

Taco de Wolff
  • Fonction : Auteur
  • PersonId : 1102079
Hugo Carrillo
Luis Martí
Nayat Sanchez-Pi
  • Fonction : Auteur
  • PersonId : 1102034

Résumé

The carbon pump of the world's ocean plays a vital role in the biosphere and climate of the earth, urging improved understanding of the functions and influences of the ocean for climate change analyses. State-of-the-art techniques are required to develop models that can capture the complexity of ocean currents and temperature flows. This work explores the benefits of using physics-informed neural networks (PINNs) for solving partial differential equations related to ocean modeling; such as the Burgers, wave, and advection-diffusion equations. We explore the trade-offs of using data vs. physical models in PINNs for solving partial differential equations. PINNs account for the deviation from physical laws in order to improve learning and generalization. We observed how the relative weight between the data and physical model in the loss function influence training results, where small data sets benefit more from the added physics information.
Fichier principal
Vignette du fichier
neurips_neural-based_solver.pdf (301.85 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03260357 , version 1 (14-06-2021)

Identifiants

Citer

Taco de Wolff, Hugo Carrillo, Luis Martí, Nayat Sanchez-Pi. Towards Optimally Weighted Physics-Informed Neural Networks in Ocean Modelling. 2021. ⟨hal-03260357⟩
161 Consultations
485 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More