Estimating pier scour depth under combined waves and current using boosting machine-learning models

• Autorzy: Kumar Lalit , Afzal Mohammad Saud

Identyfikatory

DOI

10.1007/s11600-023-01089-2

• Języki publikacji: EN

Abstrakty

EN

The development of pier scour in coastal environments severely affects the bridge’s stability. Therefore, estimating pier scour around the vertical cylinder is important for the safety of the bridge structure. The estimation of pier scour depth in combined wave-current conditions has become a challenging task for researchers in recent times. The existing empirical formulations that calculate scour in the combined action of current and wave are scarce and may not always provide accurate results. Machine-learning (ML) techniques have become increasingly popular for their prediction capabilities in the fields of hydraulics and coastal engineering in recent years. Therefore, the present study aims to develop Boosting ML techniques (i.e., AdaBoost, XGBoost, CatBoost, and LightGBM) of ML to estimate pier scour in combined wave-current conditions. The non-dimensional parameters, such as Keulegan-Carpenter (KC) number, Relative flow velocity (Ucw), and Absolute Froude number (Fra), are used as input parameters, whereas scour depth (S/D) is the output parameter in Boosting ML models. The sensitivity analysis has been performed to demonstrate the relative importance of the input parameter on S/D. The performance metrics show that the XGBoost model with the input combination of Fra, KC, and Ucw provides the highest accuracy of 92.47% and outperforms SVM, CatBoost, AdaBoost, and LightGBM models. The XGBoost model also outperforms the existing empirical formulations. Therefore, it can be concluded that the XGBoost techniques can be used as a reliable, accurate, and alternative tool to estimate pier scour depth in the combined action of current and wave.

Słowa kluczowe

EN

horseshoe vortex; combined wave-current flow; machine learning; pier scour; lee-wake vortex

PL

wir podkowiasty; połączony przepływ fal i prądu; uczenie maszynowe

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2024
• Tom: Vol. 72, no. 3
• Strony: 1895--1911
• Opis fizyczny: Bibliogr. 56 poz.

Twórcy

autor

Kumar Lalit

• Department of Civil Engineering, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India

• https://orcid.org/0000-0001-8792-4078

autor

Afzal Mohammad Saud

• Department of Civil Engineering, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India

Bibliografia

• 1. Afzal MS (2013) 3D numerical modelling of sediment transport under current and waves. Norwegian University of Science and Technology, Trondheim
• 2. Afzal MS, Kumar L (2021) Propagation of waves over a rugged topography. J Ocean Eng Sci 791:14-28
• 3. Afzal MS, Bihs H, Kamath A, Arntsen 0A (2015a) Three-dimensional numerical modeling of pier scour under current and waves using level-set method. J Offshore Mech Arct Eng 137:3
• 4. Afzal MS, Holmedal LE, Myrhaug D (2015b) Three-dimensional streaming in the seabed boundary layer beneath propagating waves with an angle of attack on the current. J Geophys Res Ocean 120:4370-4391
• 5. Afzal MS, Holmedal LE, Myrhaug D (2021) Sediment transport in combined wave-current seabed boundary layers due to streaming. J Hydraul Eng 147:4021007
• 6. Ahmad N, Afzal S, Bihs H, Arntsen 0A (2015) Three-dimensional numerical modeling of local scour around a non-slender cylinder under varying wave conditions. In: 36th IAHR world congress
• 7. Ahmadianfar I, Jamei M, Chu X (2021) Prediction of local scour around circular piles under waves using a novel artificial intelligence approach. Mar Georesour Geotechn 39(1):44-55
• 8. Azamathulla HM, Ghani AA, Zakaria NA, Guven A (2010) Genetic programming to predict bridge pier scour. J Hydraul Eng 136:165
• 9. Bui DT, Khosravi K, Tiefenbacher J et al (2020) Improving prediction of water quality indices using novel hybrid machine-learning algorithms. Sci Total Environ 721:137612
• 10. Chau MCL, Yen BP (2006) Lift scheduling: a machine learning approach. In: INFORMS international conference, INFORMS 2006
• 11. Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. pp 785-794
• 12. Chen B, Li S (2018) Experimental study of local scour around a vertical cylinder under wave-only and combined wave-current conditions in a large-scale flume. J Hydraul Eng 144:4018058
• 13. Chiew YM, Melville BW (1989) Local scour at bridge piers with nonuniform sediments. Proc Inst Civ Eng 87:215-224
• 14. Choi S-U, Cheong S (2006) Prediction of local scour around bridge piers using artificial neural networks 1. JAWRA J Am Water Resour Assoc 42:487-494
• 15. Deconinck E, Zhang MH, Coomans D, Vander HY (2007) Evaluation of boosted regression trees (BRTs) and two-step BRT procedures to model and predict blood-brain barrier passage. J Chemom A J Chemom Soc 21:280-291
• 16. Dey S (2014) Fluvial hydrodynamics. Springer, Berlin
• 17. Eadie RW, Herbich JB (1987) Scour about a single, cylindrical pile due to combined random waves and a current. Coast Eng 1986:1858-1870
• 18. Ettema R, Melville BW, Barkdoll B (1998) Scale effect in pier-scour experiments. J Hydraul Eng 124:639-642
• 19. Ettema R (1980) Scour at bridge piers. Dept. of Civil Engineering, University of Auckland, Auckland, New Zealand
• 20. Firat M, Gungor M (2009) Generalized regression neural networks and feed forward neural networks for prediction of scour depth around bridge piers. Adv Eng Softw 40:731-737
• 21. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55:119-139
• 22. Gautam S, Dutta D, Bihs H, Afzal MS (2021) Three-dimensional computational fluid dynamics modelling of scour around a single pile due to combined action of the waves and current using level-set method. Coast Eng 170:104002
• 23. Gazi AH, Afzal MS (2020) A new mathematical model to calculate the equilibrium scour depth around a pier. Acta Geophys 68:181-187
• 24. Gazi AH, Afzal MS, Dey S (2019) Scour around piers under waves: Current status of research and its future prospect. Water 11:2212
• 25. Gazi AH, Purkayastha S, Afzal MS (2020) The equilibrium scour depth around a pier under the action of collinear waves and current. J Mar Sci Eng 8(1):36
• 26. Hjorth P (1975) Studies on the nature of local scour, Inst, för Teknisk Vattenresurslära. Lunds Tekniska Högskola, Lunds Univ, Sweden
• 27. Huang G, Wu L, Ma X et al (2019) Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions. J Hydrol 574:1029-1041
• 28. Lillycrop WJ, Hughes SA (1993) Scour Hole Problems Experienced by the Corps of Engineers; Data Presentation and Summary. Miscellaneous papers. CERC-93-2, US Army Engineer Waterways Experiment Station. Coastal Engineering Research Center, Vicksburg, MS
• 29. Ibrahim B, Ewusi A, Ahenkorah I, Ziggah YY (2022) Modelling of arsenic concentration in multiple water sources: a comparison of different machine learning methods. Groundw Sustain Dev 17:100745
• 30. Jamei M, Ahmadianfar I (2020) Prediction of scour depth at piers with debris accumulation effects using linear genetic programming. Mar Georesour Geotechnol 38:468-479
• 31. Jamei M, Ahmadianfar I, Olumegbon IA, Asadi A, Karbasi M, Said Z, Meyer JP (2021) On the specific heat capacity estimation of metal oxide-based nanofluid for energy perspective-a comprehensive assessment of data analysis techniques. Int Commun Heat Mass Transf 123:105217
• 32. Ke G, Meng Q, Finley T et al (2017) LightGBM: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst 30:3147-3155
• 33. Khan MA, Sharma N, Pu J, Aamir M, Pandey M (2021) Two-dimensional turbulent burst examination and angle ratio utilization to detect scouring/sedimentation around mid-channel bar. Acta Geophys 69(4):1335-1348
• 34. Kumar L, Afzal MS, Afzal MM (2020) Mapping shoreline change using machine learning: a case study from the eastern Indian coast. Acta Geophys 68:1-17
• 35. Kumar L, Afzal MS, Ahmad A (2022) Prediction of water turbidity in a marine environment using machine learning: a case study of Hong Kong. Reg Stud Mar Sci 52:102260
• 36. Link O, Castillo C, Pizarro A et al (2017) A model of bridge pier scour during flood waves. J Hydraul Res 55:310-323
• 37. Melville BW, Chiew Y-M (1999) Time scale for local scour at bridge piers. J Hydraul Eng 125:59-65
• 38. Muzzammil M (2010) ANFIS approach to the scour depth prediction at a bridge abutment. J Hydroinform 12:474-485
• 39. Najafzadeh M (2015) Neuro-fuzzy GMDH systems based evolutionary algorithms to predict scour pile groups in clear water conditions. Ocean Eng 99:85-94
• 40. Oliveto G, Hager WH (2002) Temporal evolution of clear-water pier and abutment scour. J Hydraul Eng 128:811-820
• 41. Pal M, Singh NK, Tiwari NK (2011) Support vector regression based modeling of pier scour using field data. Eng Appl Artif Intell 24:911-916
• 42. Pal M, Singh NK, Tiwari NK (2012) M5 model tree for pier scour prediction using field dataset. KSCE J Civ Eng 16:1079-1084
• 43. Park JH, Kim KH (2010) The local scour around a slender pile in combined waves and current. J Korean Soc Coast Ocean Eng 22:405-414
• 44. Petersen TU, Sumer BM, Freds0e J (2012) Time scale of scour around a pile in combined waves and current. In: International conference on coastal engineering. p 8
• 45. Prokhorenkova L, Gusev G, Vorobev A, et al (2018) CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst 31
• 46. Qi W-G, Gao F-P (2014a) Physical modeling of local scour development around a large-diameter monopile in combined waves and current. Coast Eng 83:72-81
• 47. Qi W, Gao F (2014b) Equilibrium scour depth at offshore monopile foundation in combined waves and current. Sci China Technol Sci 57:1030-1039
• 48. Rao HD, Shi XZ, Rodrigue AK, Feng JJ, Xia YC, Elhoseny M, Yuan XH, Gu LC (2019) Feature selection based on artificial bee colony and gradient boosting decision tree. Appl Soft Comput 74:634-642
• 49. Ray S (2015) Quick introduction to boosting algorithms in machine learning. quick guid to boost algorithms mach learn https// www Anal com/blog/2015/11/quick-introduction-boosting-algorithms-machine-learning/(Sep 25, 2019)
• 50. Shakya D, Agarwal M, Deshpande V, Kumar B (2022) Estimating particle froude number of sewer pipes by boosting machine-learning models. J Pipeline Syst Eng Pract 13:4022012
• 51. Shivashankar M, Pandey M, Zakwan M (2022) Estimation of settling velocity using generalized reduced gradient (GRG) and hybrid generalized reduced gradient-genetic algorithm (hybrid GRG-GA). Acta Geophys 70(5):2487-2497
• 52. Sreedhara BM, Patil AP, Pushparaj J et al (2021) Application of gradient tree boosting regressor for the prediction of scour depth around bridge piers. J Hydroinformatics 23:849-863
• 53. Sumer BM, Freds0e J (2001) Scour around pile in combined waves and current. J Hydraul Eng 127:403-411
• 54. Sumer BM, Petersen TU, Locatelli L et al (2013) Backfilling of a scour hole around a pile in waves and current. J Waterw Port, Coastal, Ocean Eng 139:9-23
• 55. Vapnik V, Chervonenkis A (1974) Theory of pattern recognition. Nauka, Moscow
• 56. Wang RK, Herbich JB (1983) Combined Current and Wave-produced Scour Around a Single Pile. Texas Engineering Experiment Station