Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow

We propose a method for the data‐driven inference of temporal evolutions of physical functions with deep learning. More specifically, we target fluid flow problems, and we propose a novel LSTM‐based approach to predict the changes of the pressure field over time. The central challenge in this contex...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computer graphics forum Ročník 38; číslo 2; s. 71 - 82
Hlavní autori: Wiewel, S., Becher, M., Thuerey, N.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Oxford Blackwell Publishing Ltd 01.05.2019
Predmet:
Algorithms
CCS Concepts
Computer simulation
Computing methodologies → Neural networks
Fluid dynamics
Fluid flow
Machine learning
Neural networks
Physical simulation
Time functions
ISSN:0167-7055, 1467-8659
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We propose a method for the data‐driven inference of temporal evolutions of physical functions with deep learning. More specifically, we target fluid flow problems, and we propose a novel LSTM‐based approach to predict the changes of the pressure field over time. The central challenge in this context is the high dimensionality of Eulerian space‐time data sets. We demonstrate for the first time that dense 3D+time functions of physics system can be predicted within the latent spaces of neural networks, and we arrive at a neural‐network based simulation algorithm with significant practical speed‐ups. We highlight the capabilities of our method with a series of complex liquid simulations, and with a set of single‐phase buoyancy simulations. With a set of trained networks, our method is more than two orders of magnitudes faster than a traditional pressure solver. Additionally, we present and discuss a series of detailed evaluations for the different components of our algorithm.
Bibliografia:realFlow
This work was funded by the ERC Starting Grant
(StG‐2015‐637014).
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.13620