Reduced order fluid modeling with generative adversarial networks

Maarten Kemna, A. Heinlein, Cornelis Vuik

Research output: Contribution to journalConference articleScientific

8 Downloads (Pure)

Abstract

Surrogate models based on convolutional neural networks (CNNs) for computational fluid dynamics (CFD) simulations are investigated. In particular, the flow field inside two-dimensional channels with a sudden expansion and an obstacle is predicted using an image representation of the geometry as the input. Generative adversarial neural networks (GANs) have been shown to excel at such image-to-image translation tasks. This motivates the focus of this work on investigating the specific effect of adversarial training on model performance. Numerical results show that the overall accuracy of the GANs is generally lower compared to an identical generator model trained directly on the ground truth using an L1 data loss. On the other hand, GAN predictions are often visually more convincing and exhibit a lower continuity residual.
Original languageEnglish
Number of pages6
JournalProceedings in Applied Mathematics and Mechanics
Volume23
DOIs
Publication statusPublished - 2023
Event92nd Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM) - Aachen, Germany
Duration: 15 Aug 202219 Aug 2022

Fingerprint

Dive into the research topics of 'Reduced order fluid modeling with generative adversarial networks'. Together they form a unique fingerprint.

Cite this