Eprint first made available on ORBilu (E-prints, Working papers and Research blog)
Physics-informed Dynamic Graph Convolutional Neural Network with Curriculum Learning for Pore-scale Flow Simulations
RAJABI, Mohammadmahdi; LAVIGNE, Thomas; SUAREZ AFANADOR, Camilo Andrés et al.
2023
 

Files


Full Text
Physics Informed Graph Neural Network.pdf
Author postprint (2.6 MB)
Request a copy
Annexes
Graph-PINNs-Code.zip
(5.48 kB)
Request a copy
Data - Part 1.zip
(268.85 MB)
Request a copy
Data - Part 2.zip
(234.62 MB)
Request a copy
Data - Part 3.zip
(260.03 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Disciplines :
Mechanical engineering
Author, co-author :
RAJABI, Mohammadmahdi  ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
LAVIGNE, Thomas  ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE) ; Arts et Metiers Institute of Technology ; Arts et Metiers Institute of Technology, Univ. of Bordeaux
SUAREZ AFANADOR, Camilo Andrés  ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
BORDAS, Stéphane ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Sbalzarini, Ivo F.
OBEIDAT, Anas  ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Language :
English
Title :
Physics-informed Dynamic Graph Convolutional Neural Network with Curriculum Learning for Pore-scale Flow Simulations
Publication date :
2023
Available on ORBilu :
since 13 October 2023

Statistics


Number of views
239 (57 by Unilu)
Number of downloads
35 (17 by Unilu)

Bibliography


Similar publications



Contact ORBilu