Toward learning Lattice Boltzmann collision operators

ABSTRACT: In this work, we explore the possibility of learning from data collision operators for the Lattice Boltzmann Method using a deep learning approach. We compare a hierarchy of designs of the neural network (NN) collision operator and evaluate the performance of the resulting LBM method in re...

Descripción completa

Detalles Bibliográficos
Autores principales: Corbetta, Alessandro, Gabbana, Alessandro, Gyrya, Vitaliy, Livescu, Daniel, Prins, Joost, Toschi, Federico
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Berlin Heidelberg 2023
Materias:
Regular Article - Flowing Matter
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9988764/
https://www.ncbi.nlm.nih.gov/pubmed/36877295
http://dx.doi.org/10.1140/epje/s10189-023-00267-w

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9988764/
https://www.ncbi.nlm.nih.gov/pubmed/36877295
http://dx.doi.org/10.1140/epje/s10189-023-00267-w

Ejemplares similares