Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow

by   Steffen Wiewel, et al.

We propose an end-to-end trained neural networkarchitecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single-phase smoke simulations in 2D and 3D based on the incompressible Navier-Stokes (NS) equations, which are relevant for a wide range of practical problems. To achieve stable predictions for long-term flow sequences, a convolutional neural network (CNN) is trained for spatial compression in combination with a temporal prediction network that consists of stacked Long Short-Term Memory (LSTM) layers. Our core contribution is a novel latent space subdivision (LSS) to separate the respective input quantities into individual parts of the encoded latent space domain. This allows to distinctively alter the encoded quantities without interfering with the remaining latent space values and hence maximizes external control. By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long-term sequences of complex physics problems. In addition, we highlight the benefits of a recurrent training on the latent space creation, which is performed by the spatial compression network.



page 6

page 8

page 12


Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow

Our work explores methods for the data-driven inference of temporal evol...

Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations

This paper presents an approach to improve the forecast of computational...

Flow-based Autoregressive Structured Prediction of Human Motion

A new method is proposed for human motion predition by learning temporal...

Predicting Physics in Mesh-reduced Space with Temporal Attention

Graph-based next-step prediction models have recently been very successf...

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

We introduce Embed to Control (E2C), a method for model learning and con...

Deep Fluids: A Generative Network for Parameterized Fluid Simulations

This paper presents a novel generative model to synthesize fluid simulat...

A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence

In this study, we present a non-intrusive reduced order modeling (ROM) f...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.