% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Higashida:1026510,
author = {Higashida, Aito and Ando, Kazuto and Rüttgers, Mario and
Lintermann, Andreas and Tsubokura, Makoto},
title = {{R}obustness evaluation of large-scale machine
learning-based reduced order models for reproducing flow
fields},
journal = {Future generation computer systems},
volume = {159},
issn = {0167-739X},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {FZJ-2024-03447},
pages = {243 - 254},
year = {2024},
abstract = {The robustness of an artificial neural network that
performs model order reduction for flow field data is
studied. The network is trained with a large-scale
distributed learning approach using up to 6,259 nodes of the
supercomputer Fugaku. Flow around two square cylinders with
a varying distance between their centers is investigated.
The network is trained and tested with data from numerical
simulations. First, the capability to reproduce flow fields
with 2, 12, and 24 modes is investigated by comparing the
reconstructed flow data to simulated data. It is shown, that
reconstructions based on 2 modes cannot capture both, low-
and high-frequency flow structures correctly, whereas
predictions based on 12 and 24 modes yield improved flow
fields, especially in the case of high-frequency waves in
the vicinity of the square cylinders. Reconstructions with
24 modes provide smooth velocity fields that reproduce all
relevant low- and high-frequency waves for all variations of
the distance between the two square cylinders. Second, the
performance of the machine learning-based reconstructions
are compared to proper orthogonal decomposition, which is a
commonly used reduced order model technique. The comparison
only includes flow fields based on 24 modes. For all
geometric variations, the mean squared errors of the
reconstructions by the conventional method are higher than
those of the machine learning model. This underlines the
advantage of artificial neural networks over linear methods
like proper orthogonal decomposition for tasks like
reconstructing flow fields that are characterized by
non-linear governing equations.},
cin = {JSC},
ddc = {004},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / RAISE - Research on
AI- and Simulation-Based Engineering at Exascale (951733) /
JLESC - Joint Laboratory for Extreme Scale Computing
(JLESC-20150708)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)951733 /
G:(DE-Juel1)JLESC-20150708},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001247468300001},
doi = {10.1016/j.future.2024.05.005},
url = {https://juser.fz-juelich.de/record/1026510},
}