Reduced-order modeling of fluid flows with transformers
Physics of Fluids · 01.05.2023 · 35 (5)
DOI: 10.1063/5.0151515 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 22.05.2023. Verfasst von AmirPouya Hemmasian und 1 weiteren Autor:innen. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Reduced-order modeling (ROM) of fluid flows has been an active area of research for several decades. The huge computational cost of direct numerical simulations has motivated researchers to develop more efficient alternative methods, such as ROMs and other surrogate models. Similar to many application areas, such as computer vision and language modeling, machine learning and data-driven methods have played an important role in the development of novel models for fluid dynamics. The transformer is one of the state-of-the-art deep learning architectures that has made several breakthroughs in many application areas of artificial intelligence in recent years, including but not limited to natural language processing, image processing, and video processing. In this work, we investigate the capability of this architecture in learning the dynamics of fluid flows in a ROM framework. We use a convolutional autoencoder as a dimensionality reduction mechanism and train a transformer model to learn the system's dynamics in the encoded state space. The model shows competitive results even for turbulent datasets.
Förderung
- National Science Foundation
Zitieren
APA
Hemmasian, A., & Farimani, A. B. (2023). Reduced-order modeling of fluid flows with transformers. Physics of Fluids, 35(5). https://doi.org/10.1063/5.0151515
Vancouver
Hemmasian A, Farimani AB. Reduced-order modeling of fluid flows with transformers. Physics of Fluids. 2023;35(5). doi:10.1063/5.0151515
BibTeX
@article{Hemmasian2023,
author = {Hemmasian, AmirPouya and Farimani, Amir Barati},
title = {Reduced-order modeling of fluid flows with transformers},
journal = {Physics of Fluids},
year = {2023},
volume = {35},
number = {5},
doi = {10.1063/5.0151515}
}
EUVIMED