Abstract
Due to the effects of climate change, coastal engineering structures are more vulnerable to the wave forces caused by natural hazards, especially for low-lying bridges. To facilitate the structural design and risk assessment of coastal bridges under extreme events, it is imperative to efficiently predict the wave-induced forces with high accuracy. In this study, a novel predictive model for wave-induced forces is established using the ensemble learning technique. Specifically, four state-of-the-art surrogate models, namely the support vector regression (SVR), Kriging (KRG), polynomial chaos expansion (PCE), and decision tree (DT) are employed to construct a weighted predictive model, where the weights of individual models are implicitly determined by the artificial neural network (ANN). Depending on the architecture of the ANN model, e.g., with or without a hidden layer, these four surrogate models can be ensembled nonlinearly (ANN1) or linearly (ANN2). Four benchmark functions and two ocean engineering cases are utilized to validate the performance of the established ensemble models. The coefficient of determination R2, maximum absolute error (MAE), and root mean square error (RMSE) are used as the error metrics. The results show that the proposed ANN-based ensemble strategy is capable of providing robust and accurate approximation for different force components; it can effectively reduce the adverse effect of poorly behaved candidate surrogates by wisely assigning weights to the individual models, which is beneficial to protect against the use of the worst surrogate model. It is envisioned that the proposed ensemble models can be extended to predict wave forces of unstable wave conditions, thus facilitating the associated risk assessment and structural design of ocean infrastructure assets.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig16_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig17_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig18_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig19_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig20_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig21_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig22_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig23_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00366-022-01745-z/MediaObjects/366_2022_1745_Fig24_HTML.png)
Similar content being viewed by others
References
Acar E (2010) Various approaches for constructing an ensemble of metamodels using local measures. Struct Multidiscip Optim 42:879–896
Acar E, Rais-Rohani M (2009) Ensemble of metamodels with optimized weight factors. Struct Multidiscip Optim 37:279–294
Ataei N, Padgett JE (2015) Fragility surrogate models for coastal bridges in hurricane prone zones. Eng Struct 103:203–213
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Chapman & Hall/CRC, Boca Raton
Brunton SL, Noack BR, Koumoutsakos P (2020) Machine learning for fluid mechanics. Annu Rev Fluid Mech 52:477–508
Cha YJ, Choi W, Büyüköztürk O (2017) Deep learning-based crack damage detection using convolutional neural networks. Comput Aided Civ Infrastruct Eng 32:361–378
Chen X, Chen Z, Xu G, Zhuo X, Deng Q (2021) Review of wave forces on bridge decks with experimental and numerical methods. Adv Bridge Eng 2:1
Davis SE, Cremaschi S, Eden MR (2018) Efficient surrogate model development: impact of sample size and underlying model dimensions. Comput Aided Chem Eng 44:979–984
De’ath G, Fabricius KE (2000) Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology 81:3178–3192
Douglass SL, Hughes SA, Rogers S, Chen Q (2004) The impact of Hurricane Ivan on the coastal roads of Florida and Alabama: a preliminary report. Rep. to Coastal Transportation Engineering Research and Education Center, Univ. of South Alabama, Mobile, Ala, pp 1–19
Géron A (2019) Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media, Newton
Goel T, Haftka RT, Shyy W, Queipo NV (2007) Ensemble of surrogates. Struct Multidiscip Optim 33:199–216
Huang B, Duan L, Yang Z, Zhang J, Kang A, Zhu B (2019) Tsunami forces on a coastal bridge deck with a box girder. J Bridge Eng 24:04019091
Huang B, Yang Z, Zhu B, Zhang J, Kang A, Pan L (2019) Vulnerability assessment of coastal bridge superstructure with box girder under solitary wave forces through experimental study. Ocean Eng 189:106337
Hu X, Zhang H, Mei H, ** using the stacking ensemble machine learning method in Lushui, Southwest China. Appl Sci 10(11):4016
** J, Meng B (2011) Computation of wave loads on the superstructures of coastal highway bridges. Ocean Eng 38:2185–2200
Jörges C, Berkenbrink C, Stumpe B (2021) Prediction and reconstruction of ocean wave heights based on bathymetric data using LSTM neural networks. Ocean Eng 232:109046
Jamei M, Karbasi M, Olumegbon IA, Mosharaf-Dehkordi M, Ahmadianfar I, Asadi A (2021) Specific heat capacity of molten salt-based nanofluids in solar thermal applications: a paradigm of two modern ensemble machine learning methods. J Mol Liq 335:116434
Lataniotis C, Wicaksono D, Marelli S, Sudret B (2021) UQLab user manual–Kriging (Gaussian process modelling). In: Report UQLab-V14-105. Chair of Risk, Safety and Uncertainty Quantification, ETH Zurich, Zurich
Lay T, Kanamori H, Ammon Charles J, Nettles M, Ward Steven N, Aster Richard C, Beck Susan L, Bilek Susan L, Brudzinski Michael R, Butler R et al (2005) The Great Sumatra–Andaman earthquake of 26 December 2004. Science 308:1127–1133
Liu H, Xu S, Wang X, Meng J, Yang S (2016) Optimal weighted pointwise ensemble of radial basis functions with different basis functions. AIAA J 54:3117–3133
Marelli S, Sudret B (2015) UQLab: a framework for uncertainty quantification in MATLAB. ETH-Zürich, Zürich
Marelli S, Sudret B (2021) UQLab user manual–Polynomial chaos expansions. In: Report UQLab-V14-104. Chair of Risk, Safety and Uncertainty Quantification, ETH Zurich, Zurich
Mazinani I, Ismail Z, Shamshirband S, Hashim A, Mansourvar M, Zalnezhad E (2016) Estimation of tsunami bore forces on a coastal bridge using an extreme learning machine. Entropy 18(5):167
McConnell K, Allsop W, Allsop NWH, Cruickshank I (2004) Piers, jetties and related structures exposed to waves: guidelines for hydraulic loadings. Thomas Telford, London
McPherson RL (2010) Hurricane induced wave and surge forces on bridge decks. Texas A&M University, College Station
Morgan JN, Sonquist JA (1963) Problems in the analysis of survey data, and a proposal. J Am Stat Assoc 58:415–434
Moustapha M, Lataniotis C, Marelli S, Sudret B (2021) UQLab user manual—support vector machines for regression. In: Report UQLab-V14-111. Chair of Risk, Safety and Uncertainty Quantification, ETH Zurich, Zurich
Okeil Ayman M, Cai CS (2008) Survey of short- and medium-span bridge damage induced by Hurricane Katrina. J Bridge Eng 13:377–387
Padgett J, DesRoches R, Nielson B, Yashinsky M, Kwon O-S, Burdette N, Tavera E (2008) Bridge damage and repair costs from Hurricane Katrina. J Bridge Eng 13:6–14
Pena B, Huang L (2021) Wave-GAN: a deep learning approach for the prediction of nonlinear regular wave loads and run-up on a fixed cylinder. Coast Eng 167:103902
Perrone MP, Cooper LN (1992) When networks disagree: ensemble methods for hybrid neural networks. Institute for Brain and Neural Systems, Brown University, Providence
Pourzangbar A, Brocchini M, Saber A, Mahjoobi J, Mirzaaghasi M, Barzegar M (2017) Prediction of scour depth at breakwaters due to non-breaking waves using machine learning approaches. Appl Ocean Res 63:120–128
Qu K, Wen BH, Ren XY, Kraatz S, Sun WY, Deng B, Jiang CB (2020) Numerical investigation on hydrodynamic load of coastal bridge deck under joint action of solitary wave and wind. Ocean Eng 217:108037
Quinlan JR (1986) Induction of decision trees. Mach Learn 1:81–106
Quinlan JR (1993) C 4.5: programs for machine learning. The Morgan Kaufmann Series in Machine Learning, San Mateo
Robertson Ian N, Riggs HR, Yim Solomon C, Young Yin L (2007) Lessons from Hurricane Katrina storm surge on bridges and buildings. J Waterw Port Coast Ocean Eng 133:463–483
Sacks J, Welch WJ, Mitchell TJ, Wynn HP (1989) Design and analysis of computer experiments. Stat Sci 4:409–423
Saeidpour A, Chorzepa MG, Christian J, Durham S (2018) Parameterized fragility assessment of bridges subjected to hurricane events using metamodels and multiple environmental parameters. J Infrastruct Syst 24(4):04018031
Vapnik V, Golowich S, Smola A (1997) Support vector method for function approximation, regression estimation, and signal processing. Adv Neural Inf Process Sys 9:281–287
Viana FAC, Haftka RT, Steffen V (2009) Multiple surrogates: how cross-validation errors can help us to obtain the best predictor. Struct Multidiscip Optim 39:439–457
Wang J, Li C, Xu G, Li Y, Kareem A (2021) Efficient structural reliability analysis based on adaptive Bayesian support vector regression. Comput Methods Appl Mech Eng 387:114172
Wang J, Xu G, Li Y, Kareem A (2022) AKSE: a novel adaptive Kriging method combining sampling region scheme and error-based stop** criterion for structural reliability analysis. Reliab Eng Syst Saf 219:108214
Wang J, Xue S, Xu G (2021) A hybrid surrogate model for the prediction of solitary wave forces on the coastal bridge decks. Infrastructures 6(12):170
**u D, Karniadakis GE (2002) The Wiener–Askey polynomial chaos for stochastic differential equations. SIAM J Sci Comput 24:619–644
Xu G, Cai C, Deng L (2016) Numerical prediction of solitary wave forces on a typical coastal bridge deck with girders. Struct Infrastruct Eng 13:254–272
Xu G, Cai CS, Chen Q (2017) Countermeasure of air venting holes in the bridge deck–wave interaction under solitary waves. J Perform Constr Facil 31:04016071
Xu G, Cai CS, Han Y (2016) Investigating the characteristics of the solitary wave-induced forces on coastal twin bridge decks. J Perform of Constr Fac 30(4):04015076
Xu G, Cai CS, Han Y, Wu C, Xue F (2017) Numerical assessment of the wave loads on coastal twin bridge decks under stokes waves. J Coast Res 34:628–639
Xu G, Cai CS, Hu P, Dong Z (2016) Component level-based assessment of the solitary wave forces on a typical coastal bridge deck and the countermeasure of air venting holes. Pract Period Struct Des Constr 21
Xu G, Chen Q, Chen J (2018) Prediction of solitary wave forces on coastal bridge decks using artificial neural networks. J Bridge Eng 23
Xu G, Kareem A, Shen L (2020) Surrogate modeling with sequential updating: applications to bridge deck–wave and bridge deck–wind interactions. J Comput Civ Eng 34(4):04020023
Xu G, ** Y, Xue S, Yuan P, Wang J (2022) Hydrodynamic shape optimization of an auxiliary structure proposed for circular bridge pier based on a developed adaptive surrogate model. Ocean Eng 259:111869
Zerpa LE, Queipo NV, Pintos S, Salager J-L (2005) An optimization methodology of alkaline–surfactant–polymer flooding processes using field scale numerical simulation and multiple surrogates. J Petrol Sci Eng 47:197–208
Acknowledgements
The financial support from NSFC (Grant no. 52078425) is highly appreciated. All the opinions presented here are those of the writers, not necessarily representing those of the sponsors.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xu, G., Ji, C., Wei, H. et al. A novel ensemble model using artificial neural network for predicting wave-induced forces on coastal bridge decks. Engineering with Computers 39, 3269–3292 (2023). https://doi.org/10.1007/s00366-022-01745-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00366-022-01745-z