Benutzer: Gast  Login
Mehr Felder
Einfache Suche
Titel:

Latent-Space Physics: Towards learning the temporal evolution of fluid flow. Liquid 2D data set with 1000 scenes.

Dokumenttyp:
Forschungsdaten
Verantwortlich:
Thuerey, Nils
Autorinnen / Autoren:
Wiewel, Steffen; Thuerey, Nils
Institutionszugehörigkeit:
TUM
Herausgeber:
TUM
Enddatum der Datenerzeugung:
28.03.2019
Fachgebiet:
DAT Datenverarbeitung, Informatik
Quellen der Daten:
Simulationen / simulations
Datentyp:
Datenbanken / data bases
Beschreibung:
This archive contains a 2D data set of liquid simulations with resolution 64. It contains 1000 scenes, each with 100 frames of data over time. The data can be used to train the autoencoder and LSTM networks of the paper “Latent-space physics: Towards learning the temporal evolution of fluid flow”.
Links:

Project & Source-Code

Schlagworte:
Fluid Simulation; Physics-based Deep Learning; Navier-Stokes
Technische Hinweise:
Data format: numpy .npz file format, resolution per temporal frame: 64x64. Contained fields: velocity, surface position as levelset, and 3 pressure fields (full, dynamic, static).
View and download (1 file, 8GB)
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1483096):
rsync rsync://m1483096@dataserv.ub.tum.de/m1483096/
Sprache:
en
Rechte:
by-sa, http://creativecommons.org/licenses/by-sa/4.0
Horizon 2020:
ERC StG 637014
 BibTeX