A physics-guided recurrent machine learning model for long-time prediction of nonlinear partial differential equation

Jean-Hughes Fournier Lupien; Frédéric Sirois; Christian Lacroix

Conference Papers Year : 2022

A physics-guided recurrent machine learning model for long-time prediction of nonlinear partial differential equation

(1) , (1) , (1)

1

Jean-Hughes Fournier Lupien

Function : Author
PersonId : 1168644

Département de génie physique [Montréal]

Frédéric Sirois

Function : Author
PersonId : 1168645

Département de génie physique [Montréal]

Christian Lacroix

Function : Author
PersonId : 1168646

Département de génie physique [Montréal]

Keywords

physics guided machine learning physics informed neural network nonlinear partial differential equation and deep learning

Domains

Electric power

Fichier principal

Conference_Abstract_HTS2022.pdf (279.24 Ko)

8_Frederic_Sirois.pdf (1.64 Mo)

Origin	Files produced by the author(s)

Format	Poster

CCSD Sciencesconf.org : Connect in order to contact the contributor

https://hal.science/hal-03791287

Submitted on : Thursday, September 29, 2022-10:19:20 AM

Last modification on : Wednesday, December 21, 2022-5:42:33 PM

Dates and versions

hal-03791287 , version 1 (29-09-2022)

Identifiers

HAL Id : hal-03791287 , version 1

Cite

Jean-Hughes Fournier Lupien, Frédéric Sirois, Christian Lacroix. A physics-guided recurrent machine learning model for long-time prediction of nonlinear partial differential equation. 8th International Workshop on Numerical Modelling of High Temperature Superconductors (HTS 2022), Kévin Berger (Université de Lorraine - GREEN), Jun 2022, Nancy, France. ⟨hal-03791287⟩

A physics-guided recurrent machine learning model for long-time prediction of nonlinear partial differential equation

Keywords

Domains

Dates and versions

Identifiers

Cite

Export

Collections

Share