The success of deep learning models in fluid dynamics applications will depend on their ability to handle sparse and noisy data accurately. This paper concerns the development of a deep learning model for reconstructing turbulent flow images from low-resolution counterparts encompassing noise. The flow is incompressible through a symmetric, sudden expansion featuring bifurcation, instabilities, and turbulence. The deep learning model is based on convolutional neural networks, in a high-performance, lightweight architecture. The training is performed by finding correlations between high- and low-resolution two-dimensional images. The study also investigates how to remove noise from flow images after training the model with high-resolution and noisy images. In such flow images, the turbulent velocity field is represented by significant color variations. The model's peak signal-to-noise ratio is 45, one of the largest achieved for such problems. Fine-grained resolution can be achieved using sparse data at a fraction of the time required by large-eddy and direct numerical simulation methods. Considering its accuracy and lightweight architecture, the proposed model provides an alternative when repetitive experiments are complex and only a small amount of noisy data is available.

1.
J.
Salvador
,
Example-Based Super Resolution
(
Academic Press
,
2016
).
2.
K.
Fukami
,
K.
Fukagata
, and
K.
Taira
, “
Super-resolution analysis via machine learning: A survey for fluid flows
,”
Theor. Comput. Fluid Dyn.
37
,
421
444
(
2023
).
3.
H.
Gao
,
L.
Sun
, and
J.-X.
Wang
, “
Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
,”
Phys. Fluids
33
,
073603
(
2021
).
4.
M. F.
Fathi
,
I.
Perez-Raya
,
A.
Baghaie
,
P.
Berg
,
G.
Janiga
,
A.
Arzani
, and
R. M.
D'Souza
, “
Super-resolution and denoising of 4D-flow MRI using physics-informed deep neural nets
,”
Comput. Methods Prog. Biomed.
197
,
105729
(
2020
).
5.
A.
Pradhan
and
K.
Duraisamy
, “
Variational multiscale super-resolution: A data-driven approach for reconstruction and predictive modeling of unresolved physics
,”
Numer. Methods Eng.
124
,
4339
4370
(
2023
).
6.
F.
Sofos
,
D.
Drikakis
,
I. W.
Kokkinakis
, and
S. M.
Spottswood
, “
Convolutional neural networks for compressible turbulent flow reconstruction
,”
Phys. Fluids
35
,
116120
(
2023
).
7.
T.
Corpetti
,
E.
Memin
, and
P.
Perez
, “
Dense estimation of fluid flows
,”
IEEE Trans. Pattern Anal. Mach. Intell.
24
,
365
380
(
2002
).
8.
L.
Zhu
,
W.
Zhang
,
J.
Kou
, and
Y.
Liu
, “
Machine learning methods for turbulence modeling in subsonic flows around airfoils
,”
Phys. Fluids
31
,
015105
(
2019
).
9.
M. Z.
Yousif
,
M.
Zhang
,
L.
Yu
,
R.
Vinuesa
, and
H.
Lim
, “
A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers
,”
J. Fluid Mech.
957
,
A6
(
2023
).
10.
B.
Liu
,
J.
Tang
,
H.
Huang
, and
X.-Y.
Lu
, “
Deep learning methods for super-resolution reconstruction of turbulent flows
,”
Phys. Fluids
32
,
025105
(
2020
).
11.
H.
Kim
,
J.
Kim
,
S.
Won
, and
C.
Lee
, “
Unsupervised deep learning for super-resolution reconstruction of turbulence
,”
J. Fluid Mech.
910
,
A29
(
2021
).
12.
A.
Guemes
,
S.
Discetti
,
A.
Ianiro
,
B.
Sirmacek
,
H.
Azizpour
, and
R.
Vinuesa
, “
From coarse wall measurements to turbulent velocity fields through deep learning
,”
Phys. Fluids
33
,
075121
(
2021
).
13.
K.
Fukami
,
B.
jin An
,
M.
Nohmi
,
M.
Obuchi
, and
K.
Taira
, “
Machine-learning-based reconstruction of turbulent vortices from sparse pressure sensors in a pump sump
,”
J. Fluids Eng.
144
,
121501
(
2022
).
14.
A.
Kashefi
,
D.
Rempe
, and
L. J.
Guibas
, “
A point-cloud deep learning framework for prediction of fluid flow fields on irregular geometries
,”
Phys. Fluids
33
,
027104
(
2021
).
15.
C. R.
Qi
,
H.
Su
,
K.
Mo
, and
L. J.
Guibas
, “
Pointnet: Deep learning on point sets for 3D classification and segmentation
,” in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
(IEEE,
2017
) pp.
652
660
.
16.
Y.
Du
,
M.
Wang
, and
T. A.
Zaki
, “
State estimation in minimal turbulent channel flow: A comparative study of 4DVaR and PINN
,”
Int. J. Heat Fluid Flow
99
,
109073
(
2023
).
17.
S.
Schluter
,
A.
Sheppard
,
K.
Brown
, and
D.
Wildenschild
, “
Image processing of multiphase images obtained via x-ray microtomography: A review
,”
Water Resour. Res.
50
,
3615
3639
, https://doi.org/10.1002/2014WR015256 (
2014
).
18.
K.
Poulinakis
,
D.
Drikakis
,
I. W.
Kokkinakis
, and
S. M.
Spottswood
, “
Machine-learning methods on noisy and sparse data
,”
Mathematics
11
,
236
(
2023
).
19.
J. L.
Callaham
,
K.
Maeda
, and
S. L.
Brunton
, “
Robust flow reconstruction from limited measurements via sparse representation
,”
Phys. Rev. Fluids
4
,
103907
(
2019
).
20.
Z.
Luo
,
L.
Wang
,
J.
Xu
,
M.
Chen
,
J.
Yuan
, and
A. C. C.
Tan
, “
Flow reconstruction from sparse sensors based on reduced-order autoencoder state estimation
,”
Phys. Fluids
35
,
075127
(
2023
).
21.
S.
Xu
,
Z.
Sun
,
R.
Huang
,
D.
Guo
,
G.
Yang
, and
S.
Ju
, “
A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network
,”
Acta Mech. Sin.
39
,
322302
(
2023
).
22.
M.
Abadi
,
A.
Agarwal
,
P.
Barham
,
E.
Brevdo
,
Z.
Chen
,
C.
Citro
,
G. S.
Corrado
,
A.
Davis
,
J.
Dean
,
M.
Devin
et al, “
Tensorflow: A system for large-scale machine learning
,” arXiv:1603.04467 (
2016
).
23.
F.
Chollet
et al, see https://keras.io for “
Keras
(
2015
).”
24.
A.
Paszke
,
S.
Gross
,
F.
Massa
,
A.
Lerer
,
J.
Bradbury
,
G.
Chanan
,
T.
Killeen
,
Z.
Lin
,
N.
Gimelshein
,
L.
Antiga
et al, “
Pytorch: An imperative style, high-performance deep learning library
,”
Adv. Neural Inf. Process. Syst.
32
,
8024
8035
(
2019
).
25.
S.
Anwar
,
S.
Khan
, and
N.
Barnes
, “
A deep journey into super-resolution: A survey
,”
ACM Comput. Surv.
53
,
1
34
(
2021
).
26.
Z.
Wang
,
J.
Chen
, and
S. C. H.
Hoi
, “
Deep learning for image super-resolution: A survey
,”
IEEE Trans. Pattern Anal. Mach. Intell.
43
,
3365
3387
(
2021
).
27.
T.
Falk
,
D.
Mai
,
R.
Bensch
,
O.
Cicek
,
A.
Abdulkadir
,
Y.
Marrakchi
,
A.
Bohm
,
J.
Deubner
,
Z.
Jackel
,
K.
Seiwald
,
A.
Dovzhenko
,
O.
Tietz
,
C.
Dal Bosco
,
S.
Walsh
,
D.
Saltukoglu
,
T. L.
Tay
,
M.
Prinz
,
K.
Palme
,
M.
Simons
,
I.
Diester
,
T.
Brox
, and
O.
Ronneberger
, “
U-Net: Deep learning for cell counting, detection, and morphometry
,”
Nat. Methods
16
,
67
70
(
2019
).
28.
V.
Himthani
,
V. S.
Dhaka
,
M.
Kaur
,
G.
Rani
,
M.
Oza
, and
H.-N.
Lee
, “
Comparative performance assessment of deep learning based image steganography techniques
,”
Sci. Rep.
12
,
16895
(
2022
).
29.
K.
He
,
X.
Zhang
,
S.
Ren
, and
J.
Sun
, “
Deep residual learning for image recognition
,” in
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(IEEE,
2016
) pp.
770
778
.
30.
A.
Krizhevsky
,
I.
Sutskever
, and
G. E.
Hinton
, “
Imagenet classification with deep convolutional neural networks
,” in
Advances in Neural Information Processing Systems
edited by
F.
Pereira
,
C.
Burges
,
L.
Bottou
, and
K.
Weinberger
(
Curran Associates, Inc
.,
2012
), Vol.
25
.
31.
C.
Farabet
,
C.
Couprie
,
L.
Najman
, and
Y.
LeCun
, “
Learning hierarchical features for scene labeling
,”
IEEE Trans. Pattern Anal. Mach. Intell.
35
,
1915
1929
(
2013
).
32.
C.
Szegedy
,
W.
Liu
,
Y.
Jia
,
P.
Sermanet
,
S.
Reed
,
D.
Anguelov
,
D.
Erhan
,
V.
Vanhoucke
, and
A.
Rabinovich
, “
Going deeper with convolutions
,” in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
,
2015
.
33.
G.
Hinton
,
L.
Deng
,
D.
Yu
,
G. E.
Dahl
,
A-r
Mohamed
,
N.
Jaitly
,
A.
Senior
,
V.
Vanhoucke
,
P.
Nguyen
,
T. N.
Sainath
, and
B.
Kingsbury
, “
Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
,”
IEEE Signal Process. Mag.
29
,
82
97
(
2012
).
34.
K.
Fukami
,
R.
Maulik
,
N.
Ramachandra
,
K.
Fukagata
, and
K.
Taira
, “
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
,”
Nat. Mach. Intell.
3
,
945
951
(
2021
).
35.
Z.
Deng
,
C.
He
,
Y.
Liu
, and
K. C.
Kim
, “
Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework
,”
Phys. Fluids
31
,
125111
(
2019
).
36.
D.
Drikakis
and
F.
Sofos
, “
Can artificial intelligence accelerate fluid mechanics research?
,”
Fluids
8
,
212
(
2023
).
37.
X.
Wang
,
K.
Yu
,
S.
Wu
,
J.
Gu
,
Y.
Liu
,
C.
Dong
,
Y.
Qiao
, and
C.
Change Loy
, “
Esrgan: Enhanced super-resolution generative adversarial networks
,” in
Proceedings of the European Conference on Computer Vision (ECCV) Workshops
,
2018
.
38.
J.
Kim
and
C.
Lee
, “
Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
,”
J. Comput. Phys.
406
,
109216
(
2020
).
39.
E.
Ajuria Illarramendi
,
M.
Bauerheim
, and
B.
Cuenot
, “
Performance and accuracy assessments of an incompressible fluid solver coupled with a deep convolutional neural network
,”
Data-Centric Eng.
3
,
e2
(
2022
).
40.
L.
Kong
,
F.
Wang
,
F.
Yang
,
L.
Leng
, and
H.
Zhang
, “
Fisrcn: A single small-sized image super-resolution convolutional neural network by using edge detection
,”
Multimedia Tools Appl.
83
,
19609
(
2023
).
41.
D.
Nouri
,
M.
Pasandideh-Fard
,
M.
Javad Oboodi
,
O.
Mahian
, and
A. Z.
Sahin
, “
Entropy generation analysis of nanofluid flow over a spherical heat source inside a channel with sudden expansion and contraction
,”
Int. J. Heat Mass Transfer
116
,
1036
1043
(
2018
).
42.
W. H.
Ahmed
,
C. Y.
Ching
, and
M.
Shoukri
, “
Pressure recovery of two-phase flow across sudden expansions
,”
Int. J. Multiphase Flow
33
,
575
594
(
2007
).
43.
F.
Aloui
,
L.
Doubliez
,
J.
Legrand
, and
M.
Souhar
, “
Bubbly flow in an axisymmetric sudden expansion: Pressure drop, void fraction, wall shear stress, bubble velocities and sizes
,”
Exp. Therm. Fluid Sci.
19
,
118
130
(
1999
).
44.
F.
Aloui
and
M.
Souhar
, “
Experimental study of turbulent asymmetric flow in a flat duct symmetric sudden expansion
,”
J. Fluids Eng.
122
,
174
177
(
2000
).
45.
D.
Drikakis
, “
Bifurcation phenomena in incompressible sudden expansion flows
,”
Phys. Fluids
9
,
76
87
(
1997
).
46.
R.
Wille
and
H.
Fernholz
, “
Report on the first European mechanics colloquium, on the Coanda effect
,”
J. Fluid Mech.
23
,
801
819
(
1965
).
47.
F.
Durst
,
A.
Melling
, and
J.
Whitelaw
, “
Low Reynolds number flow over a plane symmetric sudden expansion
,”
J. Fluid Mech.
64
,
111
128
(
1974
).
48.
R.
Fearn
,
T.
Mullin
, and
K.
Cliffe
, “
Nonlinear flow phenomena in a symmetric sudden expansion
,”
J. Fluid Mech.
211
,
595
608
(
1990
).
49.
N.
Moallemi
and
J.
Brinkerhoff
, “
Numerical analysis of laminar and transitional flow in a planar sudden expansion
,”
Comput. Fluids
140
,
209
221
(
2016
).
50.
K.
Karantonis
,
I. W.
Kokkinakis
,
B.
Thornber
, and
D.
Drikakis
, “
Compressibility in suddenly expanded subsonic flows
,”
Phys. Fluids
33
,
105106
(
2021
).
51.
L.
Casarsa
and
P.
Giannattasio
, “
Three-dimensional features of the turbulent flow through a planar sudden expansion
,”
Phys. Fluids
20
,
015103
(
2008
).
52.
I. W.
Kokkinakis
,
D.
Drikakis
,
K.
Ritos
, and
S. M.
Spottswood
, “
Direct numerical simulation of supersonic flow and acoustics over a compression ramp
,”
Phys. Fluids
32
,
066107
(
2020
).
53.
E. F.
Toro
,
M.
Spruce
, and
W.
Speares
, “
Restoration of the contact surface in the HLL-Riemann solver
,”
Shock Waves
4
,
25
34
(
1994
).
54.
R.
Spiteri
and
S.
Ruuth
, “
A new class of optimal high-order strong-stability-preserving time discretization methods
,”
SIAM J. Numer. Anal.
40
,
469
491
(
2002
).
55.
I.
Kokkinakis
and
D.
Drikakis
, “
Implicit large eddy simulation of weakly-compressible turbulent channel flow
,”
Comput. Methods Appl. Mech. Eng.
287
,
229
261
(
2015
).
56.
M.
Klein
,
A.
Sadiki
, and
J.
Janicka
, “
A digital filter based generation of inflow data for spatially developing direct numerical or large eddy simulations
,”
J. Comput. Phys.
186
,
652
665
(
2003
).
57.
E.
Touber
and
N. D.
Sandham
, “
Large-eddy simulation of low-frequency unsteadiness in a turbulent shock-induced separation bubble
,”
Theor. Comput. Fluid Dyn.
23
,
79
107
(
2009
).
58.
J.
Hinze
,
Turbulence
(
McGraw-Hill
,
1975
).
59.
N. J.
Georgiadis
,
D. P.
Rizzetta
, and
C.
Fureby
, “
Large-eddy simulation: Current capabilities, recommended practices, and future research
,”
AIAA J.
48
,
1772
1784
(
2010
).
60.
H.
Choi
and
P.
Moin
, “
Grid-point requirements for large eddy simulation: Chapman's estimates revisited
,”
Phys. Fluids
24
,
011702
(
2012
).
61.
J.
Poggie
,
N. J.
Bisek
, and
R.
Gosse
, “
Resolution effects in compressible, turbulent boundary layer simulations
,”
Comput. Fluids
120
,
57
69
(
2015
).
62.
A.
Khan
,
A.
Sohail
,
U.
Zahoora
, and
A. S.
Qureshi
, “
A survey of the recent architectures of deep convolutional neural networks
,”
Artif. Intell. Rev.
53
,
5455
5516
(
2020
).
63.
M.
Morimoto
,
K.
Fukami
,
K.
Zhang
,
A. G.
Nair
, and
K.
Fukagata
, “
Convolutional neural networks for fluid flow analysis: Toward effective metamodeling and low dimensionalization
,”
Theor. Comput. Fluid Dyn.
35
,
633
658
(
2021
).
64.
S.
Albawi
,
T. A.
Mohammed
, and
S.
Al-Zawi
, “
Understanding of a convolutional neural network
,” in
International Conference on Engineering and Technology (ICET)
,
2017
.
65.
R. F.
Cerqueira
and
E. E.
Paladino
, “
Development of a deep learning-based image processing technique for bubble pattern recognition and shape reconstruction in dense bubbly flows
,”
Chem. Eng. Sci.
230
,
116163
(
2021
).
66.
J.
Kim
,
J. K.
Lee
, and
K. M.
Lee
, “
Accurate image super-resolution using very deep convolutional networks
,” in
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(IEEE,
2016
) pp.
1646
1654
.
67.
V.
Nair
and
G. E.
Hinton
, “
Rectified linear units improve restricted Boltzmann machines
,” in
Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML'10)
(
OmniPress
,
Madison, WI
,
2010
), pp.
807
814
.
68.
T.
Dai
,
J.
Cai
,
Y.
Zhang
,
S.-T.
Xia
, and
L.
Zhang
, “
Second-order attention network for single image super-resolution
,” in
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
,
2019
.
69.
Y.
Tai
,
J.
Yang
, and
X.
Liu
, “
Image super-resolution via deep recursive residual network
,” in
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(IEEE,
2017
) pp.
2790
2798
.
70.
J.
Gu
,
X.
Sun
,
Y.
Zhang
,
K.
Fu
, and
L.
Wang
, “
Deep residual squeeze and excitation network for remote sensing image super-resolution
,”
Remote Sens.
11
,
1817
(
2019
).
71.
E.
López-Rubio
, “
Restoration of images corrupted by Gaussian and uniform impulsive noise
,”
Pattern Recogni.
43
,
1835
1846
(
2010
).
72.
C. G.
Boncelet
, “
Chapter 7—Image noise models
,” in
The Essential Guide to Image Processing
, edited by
A.
Bovik
(
Academic Press
,
2009
), pp.
143
167
.
73.
H.
Qu
,
T.
Feng
,
Y.
Zhang
, and
Y.
Wang
, “
Ensemble learning with stochastic configuration network for noisy optical fiber vibration signal recognition
,”
Sensors
19
,
3293
(
2019
).
74.
D.
Abbott
and
S.
Kline
, “
Experimental investigation of subsonic turbulent flow over single and double backward facing steps
,”
J. Basic Eng.
84
,
317
325
(
1962
).
75.
P. R.
Mehta
, “
Separated flow through large sudden expansions
,”
J. Hydr. Div.
107
,
451
460
(
1981
).
76.
S.
De Zilwa
,
L.
Khezzar
, and
J.
Whitelaw
, “
Flows through plane sudden-expansions
,”
Int. J. Numer. Methods Fluids
32
,
313
329
(
2000
).
77.
M.
Escudier
,
P.
Oliveira
, and
R.
Poole
, “
Turbulent flow through a plane sudden expansion of modest aspect ratio
,”
Phys. Fluids
14
,
3641
3654
(
2002
).
78.
C.
Kong
,
J.-T.
Chang
,
Y.-F.
Li
, and
R.-Y.
Chen
, “
Deep learning methods for super-resolution reconstruction of temperature fields in a supersonic combustor
,”
AIP Adv.
10
,
115021
(
2020
).
79.
K.
Fukami
,
K.
Fukagata
, and
K.
Taira
, “
Super-resolution reconstruction of turbulent flows with machine learning
,”
J. Fluid Mech.
870
,
106
120
(
2019
).
80.
K.
Fukami
,
K.
Hasegawa
,
T.
Nakamura
,
M.
Morimoto
, and
K.
Fukagata
, “
Model order reduction with neural networks: Application to laminar and turbulent flows
,”
SN Comput. Sci.
2
,
467
(
2021
).
81.
K.
Bao
,
X.
Zhang
,
W.
Peng
, and
W.
Yao
, “
Deep learning method for super-resolution reconstruction of the spatio-temporal flow field
,”
Adv. Aerodyn.
5
,
19
(
2023
).
82.
C.
Kong
,
J.
Chang
,
Z.
Wang
,
Y.
Li
, and
W.
Bao
, “
Data-driven super-resolution reconstruction of supersonic flow field by convolutional neural networks
,”
AIP Adv.
11
,
065321
(
2021
).
83.
Y.
Jeon
and
D.
You
, “
Super-resolution reconstruction of transitional boundary layers using a deep neural network
,”
Int. J. Aeronaut. Space Sci.
24
,
1015
1031
(
2023
).
84.
C.
Dong
,
C. C.
Loy
,
K.
He
, and
X.
Tang
, “
Learning a deep convolutional network for image super-resolution
,” in
Computer Vision (ECCV 2014)
, edited by
D.
Fleet
,
T.
Pajdla
,
B.
Schiele
, and
T.
Tuytelaars
(
Springer International Publishing
,
Cham
,
2014
) pp.
184
199
.
85.
Z.
Wang
,
X.
Li
,
L.
Liu
,
X.
Wu
,
P.
Hao
,
X.
Zhang
, and
F.
He
, “
Deep-learning-based super-resolution reconstruction of high-speed imaging in fluids
,”
Phys. Fluids
34
,
037107
(
2022
).
86.
L.
Sun
and
J.-X.
Wang
, “
Physics-constrained bayesian neural network for fluid flow reconstruction with sparse and noisy data
,”
Theor. Appl. Mech. Lett.
10
,
161
169
(
2020
).
You do not currently have access to this content.