Comparative Study of Machine Learning Techniques for Prediction of Scour Depth around Spur Dikes
Publication: World Environmental and Water Resources Congress 2024
ABSTRACT
Spur dikes are hydraulic structures constructed within rivers to mitigate bank erosion, enhancing the stability of riverbanks. It has received considerable attention and is being adopted throughout the world. However, scouring around spur dikes affects their hydraulic performance and stability. Therefore, a precise prediction of scour depth fluctuations is essential for developing reliable and cost-effective designs for spur dikes. This study applies two types of regression-based techniques (linear and non-linear regression) and explicit expression (multivariate adaptive regression splines, M5P tree, and group method of data handling) based machine learning techniques to predict scour depth around spur dikes. For this purpose, a database of 154 experimental observations has been collected from existing literature, of which 80% and 20% of observations have been used for training and testing subsets, respectively. The root mean square error (RMSE), coefficient of determination (R-square), coefficient of correlation (CC), and mean absolute error (MAE) have been used to compare the performance and accuracy of these techniques. The multivariate adaptive regression splines (MARS) technique has shown the highest accuracy (RMSE = 0.0883, R-square = 0.9869, CC = 0.9934, and MAE = 0.0485). It is the best machine learning technique for predicting scour depth around spur dikes as compared to the M5P tree (M5P), group method of data handling (GMDH), non-linear regression (NLR), and linear regression (LR). In addition, two regression-based equations and three explicit expression-based equations are derived for predicting scour depth in any instance.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
REFERENCES
Aamir, M., and Ahmad, Z. (2019). Estimation of maximum scour depth downstream of an apron under submerged wall jets. Journal of Hydroinformatics, 21(4), 523–540.
Azamathulla, H. M., and Mohd. Yusoff, M. A. (2013). Soft computing for prediction of river pipeline scour depth. Neural Computing and Applications, pp. 23, 2465–2469.
Bhoria, S., Sihag, P., Singh, B., Ebtehaj, I., and Bonakdari, H. (2021). Evaluating Parshall flume aeration with experimental observations and advanced soft computing techniques. Neural Computing and Applications, 33, 17257–17271.
Breusers, H. N. C. (2020). Scour around spur dikes and abutments. In Scouring (pp. 51–59). CRC Press.
Elith, J., Leathwick, J. R., and Hastie, T. (2008). A working guide to boosted regression trees. Journal of animal ecology. Jul;77(4):802–13.
Ettema, R., and Muste, M. (2004). Scale effects in flume experiments on the flow around a spur dike in the flatbed channel. Journal of Hydraulic Engineering, 130(7), 635–646.
Ezzeldin, M. M., Saafan, T. O., Rage, O. F., Nejm, I. N., and Assistant, T. (2007). “Local scour around spur dikes.” In Proc., 11th Int. Water Technology Conf. London: International Water Technology Association.
Friedman, J. H. (1991). Multivariate adaptive regression splines. The annals of statistics. Mar;19(1):1–67.
Garde, R. J., Subramanya, K., and Nambudripad, K. D. (1961). Study of scour around spur-dikes. Journal of the Hydraulics Division, 87(6), 23–37.
Gill, M. A. (1972). Erosion of sand beds around spur dikes. Journal of the Hydraulics Division, 98(9), 1587–1602.
Gupta, L. K., Pandey, M., and Raj, P. A. (2023). Numerical modeling of scour and erosion processes around spur dike. CLEAN–Soil, Air, Water, 2300135.
Hoffmans, G. J. (2017). Scour manual. Routledge.
Ivakhnenko, A. G. (1971). Polynomial theory of complex systems. IEEE Transactions on Systems, Man, and Cybernetics, (4), 364–378.
Koken, M., and Gogus, M. (2015). Effect of spur dike length on the horseshoe vortex system and the bed shear stress distribution. Journal of Hydraulic Research, 53(2), 196–206.
Kothyari, U. C., Hager, W. H., and Oliveto, G. (2007). Generalized approach for clear-water scour at bridge foundation elements. Journal of Hydraulic Engineering, 133(11), 1229–1240.
Kuhnle, R. A., Alonso, C. V., and Shields, F. D., Jr. (2002). Local scour associated with angled spur dikes. Journal of Hydraulic Engineering, 128(12), 1087–1093.
Kumar, S., and Singh, K. K. (2021). Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques. Water Science and Technology, 84(9), 2366–2379.
Kumar, S., and Singh, K. K. Infiltration Rate Assessment of Experimental Rain Garden Using Conventional Models and Machine Learning Algorithms. In World Environmental and Water Resources Congress 2023 (pp. 697–710).
Lim, S. Y., and Cheng, N. S. (1998). Prediction of live-bed scour at bridge abutments. Journal of Hydraulic Engineering, 124(6), 635–638.
Madala, H. R. (2019). Inductive learning algorithms for complex systems modeling. CRC press.
Murrillo, J. A. (1987). The scourge of scour. Civil Engineering—ASCE, 57(7), 66–69.
Najafzadeh, M., Barani, G. A., and Hessami-Kermani, M. R. (2014). Group method of data handling to predict scour at downstream of a ski-jump bucket spillway. Earth Science Informatics, 7, 231–248.
Nasrollahi, A., Ghodsian, M., and Neyshabouri, S. A. A. (2008). Local scour at permeable spur dikes. Journal of Applied Sciences, 8(19), 3398–3406.
Pandey, M., Ahmad, Z., and Sharma, P. K. (2016). Estimation of maximum scour depth near a spur dike. Canadian Journal of Civil Engineering, 43(3), 270–278.
Pandey, M., Jamei, M., Karbasi, M., Ahmadianfar, I., and Chu, X. (2021). Prediction of maximum scour depth near spur dikes in uniform bed sediment using stacked generalization ensemble tree-based frameworks. Journal of Irrigation and Drainage Engineering, 147(11), 04021050.
Pourshahbaz, H., Abbasi, S., Pandey, M., Pu, J. H., Taghvaei, P., and Tofangdar, N. (2022). Morphology and hydrodynamics numerical simulation around groynes. ISH Journal of Hydraulic Engineering, 28(1), 53–61.
Quinlan, J. R. (1992, November). Learning with continuous classes. In 5th Australian joint conference on artificial intelligence (Vol. 92, pp. 343–348).
Radan, P., and Vaghefi, M. (2016). Flow and scour pattern around submerged and non-submerged T-shaped spur dikes in a 90° bend using the SSIIM model. International journal of river basin management, 14(2), 219–232.
Raudkivi, A. J., and Ettema, R. (1983). Clear-water scour at cylindrical piers. Journal of Hydraulic Engineering, 109(3), 338–350.
Safari, M. J. Hybridization of multivariate adaptive regression splines and random forest models with an empirical equation for sediment deposition prediction in open channel flow. Journal of Hydrology. 2020 Nov 1;590:125392.
Samui, P. Multivariate adaptive regression spline (Mars) for prediction of elastic modulus of jointed rock mass. Geotechnical and Geological Engineering. 2013 Feb;31(1):249–53.
Sepahvand, A., Singh, B., Sihag, P., Nazari Samani, A., Ahmadi, H., and Fiz Nia, S. (2021). Assessment of the various soft computing techniques to predict sodium absorption ratio (SAR). ISH Journal of Hydraulic Engineering, 27(sup1), 124–135.
Sihag, P., Singh, B., Said, M. A. B. M., and Azamathulla, H. M. (2022). Prediction of Manning’s coefficient of roughness for high-gradient streams using M5P. Water Supply, 22(3), 2707–2720.
Singh, B. (2020). Prediction of the sodium absorption ratio using data-driven models: a case study in Iran. Geology, Ecology, and Landscapes, 4(1), 1–10.
Singh, B., Ebtehaj, I., Sihag, P., and Bonakdari, H. (2022). An expert system for predicting the infiltration characteristics. Water Supply, 22(3), 2847–2862.
Singh, B., Sihag, P., and Singh, K. (2017). Modeling of the impact of water quality on infiltration rate of soil by random forest regression. Model Earth Syst Environ 3: 999–1004.
Singh, K., Singh, B., Sihag, P., Kumar, V., and Sharma, K. V. (2023). Development and application of modeling techniques to estimate the unsaturated hydraulic conductivity. Modeling Earth Systems and Environment, 1–15.
Tripathi, R. P., and Pandey, K. (2023). Gene-expression programming for scour around spur dike. International Journal of Hydrology Science and Technology, 15(3), 295–303.
Tsai, T. M., and Yen, P. H. (2017). GMDH algorithms applied to turbidity forecasting. Applied Water Science, 7, 1151–1160.
Vaghefi, M., Faraji, B., Akbari, M., and Eghbalzadeh, A. (2018). Numerical investigation of flow pattern around a T-shaped spur dike in the vicinity of attractive and repelling protective structures. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 40, 1–15.
Vongvisessomjai, N., Tingsanchali, T., and Babel, M. S. (2010). Non-deposition design criteria for sewers with part-full flow. Urban Water Journal, 7(1), 61–77.
Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., and Data, M. (2005, June). Practical machine learning tools and techniques. In Data mining (Vol. 2, No. 4, pp. 403-413). Amsterdam, The Netherlands: Elsevier.
Yilmaz, B., Aras, E., Nacar, S., and Kankal, M. Estimating suspended sediment load with multivariate adaptive regression spline, teaching-learning based optimization, and artificial bee colony models. Science of the Total Environment. 2018 Oct 15;639:826–40.
Zabihi, M., Pourghasemi, H. R., Pourtaghi, Z. S., and Behzadfar, M. GIS-based multivariate adaptive regression spline and random forest models for groundwater potential mapping in Iran. Environmental Earth Sciences. 2016 Apr;75(8):1–9.
Zaghloul, N. A. (1983). Local scour around spur-dikes. Journal of Hydrology, 60(1-4), 123–140.
Zha, W., and Chan, W. Y. (2005). Objective speech quality measurement using statistical data mining. EURASIP Journal on Advances in Signal Processing. Dec;2005(9):1–5.
Information & Authors
Information
Published In
History
Published online: May 16, 2024
ASCE Technical Topics:
- Analysis (by type)
- Artificial intelligence and machine learning
- Comparative studies
- Computer programming
- Computing in civil engineering
- Engineering fundamentals
- Hydraulic engineering
- Hydraulic structures
- Hydraulics
- Levees and dikes
- Methodology (by type)
- Regression analysis
- Research methods (by type)
- River bank stabilization
- River engineering
- Rivers and streams
- Scour
- Statistical analysis (by type)
- Water and water resources
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.