Home > Publications database > Sub-Grid Scale Modelling at Scale with Deep Learning and up to 60 Billion Degrees of Freedom |
Contribution to a conference proceedings/Contribution to a book | FZJ-2020-01507 |
; ; ;
2020
Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag
Jülich
Please use a persistent id in citations: http://hdl.handle.net/2128/24572
Abstract: This work presents fully resolved direct numerical simulations (DNSs) of a turbulent reactive planar temporally non-premixed jet configuration with up to 60 billion degrees of freedom. As scalar mixing is of utmost importance for this kind of configuration, a novel deep learning (DL) approach in the context of large-eddy simulation is presented which results in predictive mixing statistics on underresolved grids. The usability of the mixing model is approved by applying it to the DNS data. Furthermore, node performance measurements for the training of the DL networks are shown for different computing clusters.
The record appears in these collections: |
Book/Proceedings
NIC Symposium 2020: proceedings
NIC Symposium, JülichJülich, Germany, 27 Feb 2020 - 28 Feb 2020
Jülich : Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag, NIC Series 50, v, 424 S. (2020)
Files Fulltext by OpenAccess repository
BibTeX |
EndNote:
XML,
Text |
RIS