Reduced-order modeling of fluid flows with transformers

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 applicati...

Full description

Saved in:
Bibliographic Details
Published in:Physics of fluids (1994) 2023-05, Vol.35 (5)
Main Authors: Hemmasian, AmirPouya, Barati Farimani, Amir
Format: Article
Language:English
Subjects:
Artificial intelligence
Computer vision
Deep learning
Direct numerical simulation
Fluid dynamics
Fluid flow
Image processing
Machine learning
Mathematical models
Model reduction
Natural language processing
Reduced order models
Transformers
Video
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1070-6631
1089-7666
DOI:10.1063/5.0151515