| Autor: |
Alessandro Corbetta, Alessandro Gabbana, Vitaliy Gyrya, Daniel Livescu, Joost Prins, Federico Toschi |
| Přispěvatelé: |
Fluids and Flows, Computational Multiscale Transport Phenomena (Toschi), AI for Complex and Traffic Flows (Corbetta) |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
European Physical Journal E : Soft Matter, 46(3):10. Springer |
| ISSN: |
1292-8941 |
| Popis: |
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 reproducing time dynamics of several canonical flows. In the current study, as a first attempt to address the learning problem, the data were generated by a single relaxation time BGK operator. We demonstrate that vanilla NN architecture has very limited accuracy. On the other hand, by embedding physical properties, such as conservation laws and symmetries, it is possible to dramatically increase the accuracy by several orders of magnitude and correctly reproduce the short and long time dynamics of standard fluid flows. Graphic abstract |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink