Iserte, S.; Macías, A.; Martínez-Cuenca, R.; Chiva, S.; Paredes Palacios, R.; Quintana-Ortí, ES. (2022). Accelerating urban scale simulations leveraging local spatial 3D structure. Journal of Computational Science. 62:1-11. https://doi.org/10.1016/j.jocs.2022.101741
Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10251/196279
Title:
|
Accelerating urban scale simulations leveraging local spatial 3D structure
|
Author:
|
Iserte, Sergio
Macías, Aina
Martínez-Cuenca, Raúl
Chiva, Sergio
Paredes Palacios, Roberto
Quintana-Ortí, Enrique S.
|
UPV Unit:
|
Universitat Politècnica de València. Escola Tècnica Superior d'Enginyeria Informàtica
|
Issued date:
|
|
Abstract:
|
[EN]
This paper presents a hybrid methodology for accelerating Computational Fluid Dynamics (CFD) simulations intertwining inferences from deep neural networks (DNN). The strategy leverages the local spatial data of the ...[+]
[EN]
This paper presents a hybrid methodology for accelerating Computational Fluid Dynamics (CFD) simulations intertwining inferences from deep neural networks (DNN). The strategy leverages the local spatial data of the velocity field to leverage three-dimensional convolutional kernels within DNN. The hybrid workflow is composed of two-step cycles where CFD solvers calculations are utilized to feed predictive models, whose inferences, in turn, accelerate the simulation of the fluid evolution compared with traditional CFD. This approach has proved to reduce 30% time-to-solution in an urban scale study case, which leads to generating massive datasets at a fraction of the cost.
[-]
|
Subjects:
|
Computational fluid dynamics
,
Structured mesh
,
Convolutional neural network
,
High performance computing
,
Data-driven simulations
|
Copyrigths:
|
Reconocimiento (by)
|
Source:
|
Journal of Computational Science. (issn:
1877-7503
)
|
DOI:
|
10.1016/j.jocs.2022.101741
|
Publisher:
|
Elsevier
|
Publisher version:
|
https://doi.org/10.1016/j.jocs.2022.101741
|
Project ID:
|
info:eu-repo/grantAgreement/GVA//APOSTD%2F2020%2F026/
info:eu-repo/grantAgreement/GVA//FDGENT/
|
Thanks:
|
Researcher S. Iserte was supported by postdoctoral fellowship APOSTD/2020/026 from GVA-ESF. While researcher A. Macias was supported by predoctoral fellowship FDGENT from GVA. CTE-Power cluster of the Barcelona Supercomputing ...[+]
Researcher S. Iserte was supported by postdoctoral fellowship APOSTD/2020/026 from GVA-ESF. While researcher A. Macias was supported by predoctoral fellowship FDGENT from GVA. CTE-Power cluster of the Barcelona Supercomputing Center, and Tirant III cluster of the Servei d'Informatica of the University of Valencia were leveraged in this research. Authors want to thank the anonymous reviewers whose suggestions significantly improved the quality of this manuscript.
[-]
|
Type:
|
Artículo
|