Bridge backwater estimation: A comparison between artificial intelligence models and explicit equations

Document Type : Article

Authors

1 School of Engineering, Department of Civil and Environmental Engineering, Shiraz University, Zand Blvd., Shiraz, Iran

2 School of Engineering, Department of Civil and Environmental Engineering, Shiraz University, Zand Blvd., Shiraz, Iran.

Abstract

Estimation of bridge backwater has been one of practical challenges in hydraulic engineering for decades. In this study, Genetic Programming (GP) has been applied for estimating bridge backwater for the first time based on the conducted literature review. Furthermore, two new explicit equations are developed for predicting bridge afflux using Genetic Algorithm (GA) and hybrid MHBMO-GRG algorithm. The performances of these models are compared with Artificial Neural Network (ANN) and several explicit equations available in the literature considering both laboratory and field data. Based on five considered performance evaluation criteria, the two new explicit equations outperform the ones available in the literature. Furthermore, GP and ANN achieve the best results in favor of four out of five considered criteria for train and test data, respectively. To be more specific, ANN improves the MSE and R2 values of the explicit equation developed using GA by 44% and 12% for the test data while GP enhances the corresponding values by 62% and 9% for the train data. Finally, the results demonstrate that not only artificial intelligence models considerably improve bridge afflux estimation than the explicit equations but also the suggested equations significantly improve the accuracy of the available explicit ones.

Keywords


References
1. Hunt, J., Brunner, G.W., and Larock, B.E. Flow
transitions in bridge backwater analysis", J. Hydraul.
Eng., 125(9), pp. 981{983 (1999).
M. Niazkar et al./Scientia Iranica, Transactions A: Civil Engineering 28 (2021) 573{585 583
2. Biery, P. and Delleur, J. Hydraulics of single span
arch bridge construction", J. Hydraul. Eng., 88(2), pp.
75{108 (1962).
3. Mamak, M., Seckin, G., Cobaner, M., et al. Bridge
aux analysis through arched bridge constrictions using
arti cial intelligence methods", Civ. Eng. Environ.
Syst., 26(3), pp. 279{293 (2009).
4. Pinar, E., Paydas, K., Seckin, G., et al. Arti cial
neural network approaches for prediction of backwater
through arched bridge constrictions", Adv. Eng.
Softw., 41(4), pp. 627{635 (2010).
5. Biglari, B. and Sturm, T.W. Numerical modeling of

ow around bridge abutments in compound channel",
J. Hydraul. Eng., 124(2), pp. 156{164 (1998).
6. Seckin, G., Haktanir, T., and Knight, D. A simple
method for estimating
ood
ow around bridges", P.
I. Civil Eng-Wat. M., 160, pp. 195{202 (2007).
7. Seckin, G., Yurtal, R., and Haktanir, T. Contraction
and expansion losses through bridge constrictions", J.
Hydraul. Eng., 124(5), pp. 546{549 (1998).
8. Seckin, G. and Atabay, S. Experimental backwater
analysis around bridge waterways", Can. J. Civil Eng.,
32(6), pp. 1015{1029 (2005).
9. Seckin, G., Akoz, M.S., Cobaner, M., et al. Application
of ANN techniques for estimating backwater
through bridge constrictions in Mississippi river
basin", Adv. Eng. Softw., 40(10), pp. 1039{1046
(2009).
10. Pinar, E., Seckin, G., Sahin, B., et al. ANN approaches
for the prediction of bridge backwater using
both eld and experimental data", Int. J. of River
Basin Manag., 9(1), pp. 53{62 (2011).
11. Seckin, G., Cobaner. M., Ozmen-Cagatay, H., et al.
Bridge aux estimation using arti cial intelligence
systems", P. I. Civil Eng-Wat. M., 164, pp. 283{293
(2011).
12. Schneider, V. and Arcement, G. Guide for selecting
manning's roughness coecients for natural channels
and
ood plains", Available from the US Geological
Survey, Books and Open-File Reports Section, Box
25425, Federal Center, Denver, CO 80225-0425.Water-
Supply Paper 2339, 1989. 38 p, 22 g, 4 tab, 23 ref
(1989).
13. Hydrologic Engineering Center, HEC-2 Water Surface
Pro les User's Manual, Hydrologic Eng. Ctr., Davis,
CA: US Army Corps of Engineers (1991).
14. Hydrologic Engineering Center, HEC-RAS River Analysis
System, Hydrologic Eng. Ctr., Davis, CA: US
Army Corps of Engineers, version 3.1, beta Edn.
(2002).
15. Hydrologic Engineering Center, HEC-RAS River Analysis
System, Hydrologic Eng. Ctr., Davis, CA: US
Army Corps of Engineers, version 1.0, Edn. (1995)
16. Sherman, J. User's manual for WSPRO. A computer
model for water surface pro le computation", US
Geological Survey, Reston, Va. Report No. FHWA-IP-
89-027 (1990).
17. Yarnell, D.L., Bridge Piers as Channel Obstructions,
(No. 442), US Dept. of Agriculture (1934).
18. Brown, P. Aux at arch bridges", Tech. Rep. Report
SR 182, HR Wallingford (1988).
19. Bradley, J.N., Hydraulics of Bridge Waterways, 2nd
Edn., Series No. 1, Washington DC: Oce of Engineering,
US Department of Transportation, Federal
Highway Administration (1978).
20. Hallcrow, S.W. and Wallingford, H.R., ISIS Flow User
Manual, Version 2.1., Sir William Halcrow & Partners
and HR Wallingford Ltd., Wallingford, UK (2002).
21. Niazkar, M. and Afzali, S.H. Developing a new
accuracy-improved model for estimating scour depth
around piers using a hybrid method", IJST-T Civ.
Eng., 43(2), pp. 179{189 (2018).
22. Niazkar, M., Rakhshandehroo, G., and Afzali, S.H.
Deriving explicit equations for optimum design of a
circular channel incorporating a variable roughness",
IJST-T Civ. Eng., 42(2), pp. 133{142 (2018). DOI
10.1007/s40996-017-0091-y
23. Niazkar, M. Revisiting the estimation of colebrook
friction factor: A comparison between arti cial intelligence
models and C-W based explicit equations",
KSCE J. Civ. Eng., 23(10), pp. 4311{4326 (2019).
24. Niazkar, M., Talebbeydokhti, N., and Afzali, S.H.
Relationship between Hazen-William coecient and
Colebrook-White friction factor: Application in water
network analysis", European Water, 58, pp. 513{520
(2017).
25. Niazkar, M. and Talebbeydokhti, N. Comparison
of explicit relations for calculating Colebrook friction
factor in pipe network analysis using h-based
methods", Iranian Journal of Science and Technology,
Transactions of Civil Engineering, 44(1), pp. 231{249
(2020). DOI: 10.1007/s40996-019-00343-2
26. Sivapragasam, C., Maheswaran, R., and Venkatesh, V.
Genetic programming approach for
ood routing in
natural channels", Hydrol. Process, 22(5), pp. 623{628
(2008).
27. Niazkar, M., Talebbeydokhti, N., and Afzali, S.H.
Novel grain and form roughness estimator scheme
incorporating arti cial intelligence models", Water
Resour. Manag., 33(2), pp. 757{773 (2019).
28. Niazkar, M. and Afzali, S.H. Application of new hybrid
optimization technique for parameter estimation
of new improved version of Muskingum model", Water
Resour. Manag., 30(13), pp. 4713{4730 (2016).
29. Niazkar, M. and Afzali, S.H. Parameter estimation of
an improved nonlinear Muskingum model using a new
hybrid method", Hydrol. Res., 48(4), pp. 1253{1267
(2017).
30. Niazkar, M. and Afzali, S.H. Application of new
hybrid method in developing a new semicircular-weir
discharge model", Alexandria Eng. J., 57(3), pp. 1741{
1747 (2017).
584 M. Niazkar et al./Scientia Iranica, Transactions A: Civil Engineering 28 (2021) 573{585
31. Cobaner, M., Seckin, G., and Kisi, O. Initial assessment
of bridge backwater using an arti cial neural
network approach", Can. J. Civil Eng., 35(5), pp. 500{
510 (2008).
32. Govindaraju, R.S. Arti cial neural networks in hydrology.
I: Preliminary concepts", Journal of Hydrologic
Engineering, 5(2), pp. 115{123 (2000).
33. Samet, K., Hoseini, K., Karami, H., et al. Comparison
between soft computing methods for prediction of
sediment load in rivers: Maku dam case study", IJSTT
Civ. Eng., 43(1), pp. 93{103 (2019).
34. Vaghe , M., Mahmoodi, K., and Akbari, M. Detection
of outlier in 3D
ow velocity collection in an openchannel
bend using various data mining techniques",
IJST-T Civ. Eng., 43(2), pp. 197{214 (2019).
35. Koza, J.R., Bennett, F.H., and Sti elman, O. Genetic
programming as a Darwinian invention machine", In:
European Conference on Genetic Programming, pp.
93{108. Springer (1999).
36. Francone, F.D. Discipulus owner's manual", Machine
Learning Technologies, Inc., Littleton, Colorado
(1998).
37. Afzali, S.H., Darabi, A., and Niazkar, M. Steel frame
optimal design using MHBMO algorithm", Int. J. Steel
Struct., 16(2), pp. 455{465 (2016).
38. Niazkar, M. and Afzali, S.H. New nonlinear variableparameter
Muskingum models", KSCE J. Civ. Eng.,
21(7), pp. 2958{2967 (2017).
39. Niazkar, M. and Afzali, S.H. Closure to assessment
of modi ed honey bee mating optimization for parameter
estimation of nonlinear Muskingum models", J.
Hydrol. Eng., 23(4), 07018003 (2018).
40. Niazkar, M. and Afzali, S.H. Assessment of modi ed
honey bee mating optimization for parameter estimation
of nonlinear Muskingum models", J. Hydrol. Eng.,
20(4), 04014055 (2015).
41. Niazkar, M. and Afzali, S.H. Optimum design of lined
channel sections", Water Resour. Manag., 29(6), pp.
1921{1932 (2015).
42. Niazkar, M. and Afzali, S.H. Streamline performance
of Excel in stepwise implementation of numerical
solutions", Comput. Appl. Eng. Educ., 24(4), pp. 555{
566 (2016).
43. Niazkar, M. and Afzali, S.H. Analysis of water distribution
networks using MATLAB and Excel spreadsheet:
h-based methods", Comput. Appl. Eng. Educ.,
25(1), pp. 129{141 (2017).
44. Niazkar, M. and Afzali, S.H. Analysis of water distribution
networks using MATLAB and Excel spreadsheet:
Q-based methods", Comput. Appl. Eng. Educ.,
25(2), pp. 277{289 (2017).
45. Niazkar, M., Talebbeydokhti, N., and Afzali, S.H.
Development of a new
ow-dependent scheme for
calculating grain and form roughness coecients",
KSCE J. Civ. Eng., 23(5), pp. 2108{2116 (2019).
46. Motaman, F., Rakhshandehroo, G.R., Hashemi, M.R.,
et al. Application of RBF-DQ method to timedependent
analysis of unsaturated seepage", Transport
in Porous Media, 125(3), pp. 543{564 (2018).
47. Niazkar, M., Talebbeydokhti, N., and Afzali, S.H.
One dimensional hydraulic
ow routing incorporating
a variable grain roughness coecient", Water Resour.
Manag., 33(13), pp. 4599{4620 (2019).