% 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{Hassanian:1024403,
author = {Hassanian, Reza and Aach, Marcel and Lintermann, Andreas
and Helgadóttir, Ásdís and Riedel, Morris},
title = {{T}urbulent {F}low {P}rediction-{S}imulation: {S}trained
{F}low with {I}nitial {I}sotropic {C}ondition {U}sing a
{GRU} {M}odel {T}rained by an {E}xperimental {L}agrangian
{F}ramework, with {E}mphasis on {H}yperparameter
{O}ptimization},
journal = {Fluids},
volume = {9},
number = {4},
issn = {2311-5521},
address = {Belgrade},
publisher = {MDPI},
reportid = {FZJ-2024-02146},
pages = {84},
year = {2024},
note = {The paper is available open-access on the publisher
website.},
abstract = {This study presents a novel approach to using a gated
recurrent unit (GRU) model, a deep neural network, to
predict turbulent flows in a Lagrangian framework. The
emerging velocity field is predicted based on experimental
data from a strained turbulent flow, which was initially a
nearly homogeneous isotropic turbulent flow at the
measurement area. The distorted turbulent flow has a Taylor
microscale Reynolds number in the range of 100 < $Re_\lamda$
< 152 before creating the strain and is strained with a mean
strain rate of 4 $s^−1$ in the Y direction. The
measurement is conducted in the presence of gravity
consequent to the actual condition, an effect that is
usually neglected and has not been investigated in most
numerical studies. A Lagrangian particle tracking technique
is used to extract the flow characterizations. It is used to
assess the capability of the GRU model to forecast the
unknown turbulent flow pattern affected by distortion and
gravity using spatiotemporal input data. Using the flow
track’s location (spatial) and time (temporal) highlights
the model’s superiority. The suggested approach provides
the possibility to predict the emerging pattern of the
strained turbulent flow properties observed in many natural
and artificial phenomena. In order to optimize the consumed
computing, hyperparameter optimization (HPO) is used to
improve the GRU model performance by $14–20\%.$ Model
training and inference run on the high-performance computing
(HPC) JUWELS-BOOSTER and DEEP-DAM systems at the Jülich
Supercomputing Centre, and the code speed-up on these
machines is measured. The proposed model produces accurate
predictions for turbulent flows in the Lagrangian view with
a mean absolute error (MAE) of 0.001 and an $R^2$ score of
0.993.},
cin = {JSC},
ddc = {530},
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) /
EUROCC-2 (DEA02266)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)951733 /
G:(DE-Juel-1)DEA02266},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001211140400001},
doi = {10.3390/fluids9040084},
url = {https://juser.fz-juelich.de/record/1024403},
}