# Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction and Background—Scour Identification Approaches

## 2. Conventional Monitoring-Based and Machine Learning-Based Methods to Identify Scour

- Single-use devices;
- Pulse or radar devices;
- Fiber Bragg grating sensors;
- Buried or data-driven equipment;
- Sound wave appliances;
- Electrical conductivity devices.

- Sensors;
- Sensor data collection topologies;
- Wireless connection;
- Power supply;
- Synchronizing the data obtained from a set of sensors;
- Environmental effects and data;
- Collection and processing systems.

- Academic papers published in the recent years;
- Written in English;
- Aiming to detect bridge scour, not other types of damage;
- Scour detection methods were monitoring or ML-based.

#### 2.1. Methods, Properties, and Main Outcomes of Studies

#### 2.1.1. Cluster 1—Conventional Monitoring-Based Approaches to Detect Scour

Monitoring Type | Study Reference | Numerical Method and Sensor Technology | Presence of Experimental Cases /Field Tests |
---|---|---|---|

Direct | [42] | Mode Shape Ratio | None |

[43] | Vibration energy harvesting device | Yes | |

[44] | Hilbert Huang Transform | Yes | |

[45] | Fiber Optic Sensors | Yes | |

[46] | Eigen frequency | None | |

[47] | Frequency Domain Decomposition | None | |

[17] | |||

[23] | Decentralized modal analysis | Yes | |

[48] | Frequency analysis of piezoelectric rod sensors | ||

[49] | Yes | ||

[50] | |||

[51] | Unmanned Aerial Vehicle using smart rocks | Yes | |

[31] | Smart probes instrumented with electromagnetic sensors | ||

[52] | Yes | ||

[53] | Micro energy harvesters | None | |

[54] | Horizontally-displaced mode shapes and changes in dynamic flexibility | Yes | |

[55] | Unmanned Aerial Vehicle-based smart rock | Yes | |

Indirect | [56] | Wavelet transformation | None |

[37] | |||

[57] | |||

[18] | Eigen frequency | None | |

[19] | Closed-form mode shape derivation | Yes |

#### Direct Monitoring-Based Studies

#### Indirect Monitoring-Based Studies

#### 2.1.2. Cluster 2—Machine Learning-Based Research

Study Reference | Quantity of Data | Training/Validation Percentages | Base Algorithm | Assisting Approach/Algorithm | Compared Algorithms/Existing Formulas | Most Significant Parameters Considered | Target |
---|---|---|---|---|---|---|---|

[107] | Not provided | Not provided | Convolutional Neural Network | Not provided | Empirical Formulas: - 65-1, 65-2 of China - Melville-Sheppard -MBW - HEC-18 | Velocity of flow Depth of water Diameter of the sediment Pier width | Local scour depths around piers |

[108] | 11 sets of field and laboratory data (scour depth measurement-bathymetric data measured with point laser sensors) | Multiple linear regression method | The cost function for determination of the accuracy of the model | ||||

[109] | 99 examples of relative scour depths of a 0.7 m deep flume | 70% Training 30% Validation | Kstar model with five hybrid algorithms: - Weighted Instance Handler Wrapper-Kstar | Pearson correlation coefficient (to pick the most relevant input parameters) | Empirical equations of Dey and Barbhuiya, [6] and Muzammil [7]. | Relative Flow Depth Excess Abutment Froude number Relative Sediment Size Relative Submergence | Relative scour depth around abutments |

[110] | 122 laboratory datasets of scour depths. An experiment in a sand bed flume and measured with a vertical point gauge. | Reduced Error Pruning Tree base classifier | - Mean Absolute Error - Root Mean Squared Error - R (Correlation Coefficient) - Taylor diagram (For fitting and performance optimization) | - Artificial Neural Networks - Support Vector Machine - M5P - Reduced Error Pruning Tree algorithms and 2 empirical formulas of the Florida Department of Transportation and Hydraulic Engineering Circular No. 18 (HEC-18). | Pile cap width Thickness Column width | Local scour depth at complex piers | |

[111] | 476 field pier scour depth measurements for 4 different geometric shapes of piers. | 80% Training 20% Testing | - The Extreme Learning Machines regression method - The self-adaptive version of Differential Evolution | - Root Mean Squared Error - Mean Absolute Relative Error - Support Vector Machine - Artificial Neural Networks | Not provided | Pier dimensions Sediment mean diameter | Scour depth around piers |

[112] | 321 experimental datasets of flumes, scour depths measured with a point gauge | 75% Training 25% Testing | Extreme Learning Machines | Different sets of input combinations were used to find the most effective variables. | - Support Vector Machine - Artificial Neural Networks | Critical and avarage flow velocity Flow depth Median diameter of particles Pile diameter Number of piles normal to the flow Distance between adjacent piles in line with the flow | Scour depth around piers |

[113] | 476 field pier scour depth measurements | 80% Training 20% Testing | Extreme Learning Machines | Dimensional analysis to detect effective dimensionless parameters | Existing regression based models Richardson & Davis [114] Johnson [115] Shen [116] Laursen and Toch [13] | Ratio of pier width to flow depth Ratio of pier length to flow depth | |

[117] | 104 sets of experiments to measure scour depths with an electronic total station device | Not provided | - Gradient Tree Boosting - Group Method of Data Handling technique. | Coefficient of Determination as to the performance index | Support Vector Machine ANFIS Particle Swarm Optimization-Based Support Vector Machine. | For clear water scour: Sediment size and quantity Velocity Flow time | The scour depth of circular, rectangular round-nosed, and sharp-nosed piers |

[118] | 237 pier scour depth measurement datasets taken with echo sounder | Not provided | Evolutionary Radial Basis Function Neural Network model = Radial Basis Function Neural Network and Artificial Bee Colony | Not provided | Genetic Programming Back-propagation neural network Regression Tree Support Vector Machine - HEC18 -Mississippi’s method Van Wilson [119] Laursen and Toch [13] Froehlich [120] | Pier shape factor Pier width Skew of the pier to approach the flow Velocity of the flow Depth of flow Grain Size of The Bed Material (d _{50})Gradation of bed material | Scour depth |

[121] | 170 data samples of clear-water scour depths | Not provided | Support Vector Regression-based model | Filter and wrapper feature selection strategies (for performance improvement) | HEC18 Richardson & Davis [114] Melville & Coleman [122] Ataie-Ashtiani [123] | Under three groups: Pier geometry Flow property Material characteristic of the riverbed | Local scour around complex piers |

[124] | 403 sets of upstream and 61 sets of field downstream scour depth measurements | 80% Training 20% Validation | Nondominated Sorting Genetic Algorithm | Support Vector Machine for increasing the pool of field data | HEC18 Froehlich [120] Gene expression programming model | Pier width Approaching flow depth Median grain size, Sediment gradation coefficient Gradation of bed material | Critical scour depth |

[85] | 232 field data | 66% Training 34% Testing | Deep Neural Network | Back-Propagation Neural Network | Froehlich Equation [120] Froehlich Design HEC-18 HEC-18/Mueller Equation (1996) Back-Propagation Neural Network | - Not provided | Local scour around bridge piers |

[125] | 175 experimental datasets for scour depth | Not provided | Sequential quadratic programming optimization Least Square Support Vector Machine | Sequential quadratic programming to seek the optimal coefficients | - HEC18 - Melville and Coleman [122] - Ataie-Ashtiani [123] | Flow direction Pile-cap width Covering soil height Pier length Critical velocity of sediment movement Flow velocity Median grain size Flow depth River bed material Standard deviation | Scour depth of a Bridge with a complex pier |

_{50}/l, where “d

_{50}” is the sediment size and “l” is the dimension of the abutment which is perpendicular to the flow), and relative flow depth (h/l). Finally, for semicircular and 45° wing shape abutments, the combination of Excess Abutment Froude number and relative sediment size was the most effective parameter combination in scour prediction. The weighted instance handler wrapper-Kstar for vertical-wall abutments, random committee-Kstar for semicircular walls, and 45° wing wall were the best algorithms among five novel hybrid algorithms studied. Their algorithms outperformed the empirical formulas of Dey and Barbhuiya [6] and Muzzammil [7]. The hybrid approach of [107], based on a random subspace meta classifier, resulted in the pile cap level being the most sensitive factor in the prediction of complex piers’ local scour depths. The reduced error pruning tree base classifier resulted in similar root mean square errors to artificial neural networks, support vector machines, and M5P. The predictions obtained through reduced error pruning tree and other machine learning algorithms were significantly better than the scour depths computed with the empirical models of FDOT and HEC-18. Both [109] and [110] were able to increase the prediction power of standalone algorithms with the hybrid algorithms they proposed. [111] proposed a self-adaptive evolutionary extreme learning machine to predict scour around bridge piers. They indicated that the ratio of the median diameter of particle size to flow depth, the ratio of pier length to flow depth, and the ratio of pier width to flow depth were the most effective parameters. Self-adaptive evolutionary extreme learning machines outperformed artificial neural networks and support vector machines. In 2018, [112] proposed 25 models to predict scour around coastal and hydraulic pile groups. The extreme learning machine model generated had the most optimal input parameter combination and provided better results than the artificial neural networks and support vector machines considered. They also identified that pier diameter affected the predictions the most. Later in 2019, it was shown that extreme learning machines were one of the most effective heuristic optimization algorithms for non-linear systems [113]. The sensitivity analysis included 31 models with different input combinations [113]. Their approach outperformed the empirical equations of Richardson and Davis [114], Johnson [115], Shen [116], and Laursen and Toch [13]. They recommended that the proposed methodology be improved by utilizing other artificial intelligence methods such as gene expression programming, and the group method of data handling.

#### 2.2. Synthesis of the Results

#### 2.2.1. Cluster 1—Synthesis of Conventional Monitoring-Based Studies to Detect Scour

#### 2.2.2. Cluster 2—Synthesis of Machine Learning-Based Studies

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Zhao, M. A Review on Recent Development of Numerical Modelling of Local Scour around Hydraulic and Marine Structures. J. Mar. Sci. Eng.
**2022**, 10, 1139. [Google Scholar] [CrossRef] - Bihs, H.; Olsen, N.R.B. Numerical modeling of abutment scour with the focus on the incipient motion on sloping beds. J. Hydraul. Eng.
**2011**, 137, 1287–1292. [Google Scholar] [CrossRef] - Nordila, A.; Ali, T.; Faisal, A.; Badrunnisa, Y. Local scour at wide bridge Piers. Int. J. Eng. Res. Technol. (IJERT)
**2014**, 3, 742–754. [Google Scholar] - Guan, D.; Chiew, Y.M.; Wei, M.; Hsieh, S.C. Characterization of horseshoe vortex in a developing scour hole at a cylindrical bridge pier. Int. J. Sediment Res.
**2019**, 34, 118–124. [Google Scholar] [CrossRef] - Oliveto, G.; Hager, W.H. Temporal evolution of clear-water pier and abutment scour. J. Hydraul. Eng.
**2002**, 128, 811–820. [Google Scholar] [CrossRef] - Dey, S.; Barbhuiya, A.K. Time variation of scour at abutments. J. Hydraul. Eng.
**2005**, 131, 11–23. [Google Scholar] [CrossRef] - Muzzammil, M. ANFIS approach to the scour depth prediction at a bridge abutment. J. Hydroinform.
**2010**, 12, 474–485. [Google Scholar] [CrossRef] [Green Version] - Campbell, K.E.; Ruffell, A.; Pringle, J.; Hughes, D.; Taylor, S.; Devlin, B. Bridge Foundation River Scour and Infill Characterisation Using Water-Penetrating Radar. Remote Sens.
**2021**, 13, 2542. [Google Scholar] [CrossRef] - Huber, E.; Anders, B.; Huggenberger, P. Quantifying scour depth in a straightened gravel-bed river with ground-penetrating radar. In Proceedings of the 17th International Conference on Ground Penetrating Radar (GPR) IEEE, Rapperswil, Switzerland, 18–21 June 2018; pp. 1–4. [Google Scholar]
- Hou, S.; Jiao, D.; Dong, B.; Wang, H.; Wu, G. Underwater inspection of bridge substructures using sonar and deep convolutional network. Adv. Eng. Inform.
**2022**, 52, 101545. [Google Scholar] [CrossRef] - Raju, R.D.; Nagarajan, S.; Arockiasamy, M.; Castillo, S. Feasibility of Using Green Laser in Monitoring Local Scour around Bridge Pier. Geomatics
**2022**, 2, 355–369. [Google Scholar] [CrossRef] - Mutlu Sumer, B. Mathematical modeling of scour: A review. J. Hydraul. Res.
**2007**, 45, 723–735. [Google Scholar] [CrossRef] - Laursen, E.M.; Toch, A. Scour around Bridge Piers and Abutments; Ames, I.A., Ed.; Iowa Highway Research Board: Iowa City, IA, USA, 1956; Volume 4.
- Kirkil, G.; Constantinescu, G.; Ettema, R. Detached eddy simulation investigation of turbulence at a circular pier with scour hole. J. Hydraul. Eng.
**2009**, 135, 888–901. [Google Scholar] [CrossRef] - Yagci, O.; Yildirim, I.; Celik, M.F.; Kitsikoudis, V.; Duran, Z.; Kirca, V.O. Clearwater scour around a finite array of cylinders. Appl. Ocean Res.
**2017**, 68, 114–129. [Google Scholar] [CrossRef] - Oben-Nyarko, K.; Ettema, R. Pier and abutment scour interaction. J. Hydraul. Eng.
**2011**, 137, 1598–1605. [Google Scholar] [CrossRef] - Malekjafarian, A.; Prendergast, L.J.; OBrien, E.J. Detecting bridge scour using mode shapes derived from time-domain data. In Proceedings of the Civil Engineering Research in Ireland 2018 (CERI2018) Conference, Dublin, Ireland, 29–30 August 2018. [Google Scholar]
- Prendergast, L.J.; Hester, D.; Gavin, K. Determining the presence of scour around bridge foundations using vehicle-induced vibrations. J. Bridge Eng.
**2016**, 21, 04016065. [Google Scholar] [CrossRef] [Green Version] - Tan, C.; Zhao, H.; OBrien, E.J.; Uddin, N.; Fitzgerald, P.C.; McGetrick, P.J.; Kim, C.W. Extracting mode shapes from drive-by measurements to detect global and local damage in bridges. Struct. Infrastruct. Eng.
**2020**, 17, 1–8,11,13. [Google Scholar] [CrossRef] - Klinga, J.V.; Alipour, A. Assessment of structural integrity of bridges under extreme scour conditions. Eng. Structures
**2015**, 82, 55–71. [Google Scholar] [CrossRef] - Prendergast, L.J.; Gavin, K.; O’Sullivan, J.J. Non-intrusive bridge scour analysis technique using laboratory test apparatus. In Proceedings of the Bridge and Concrete Research in Ireland, Dublin, Ireland, 6–7 September 2012. [Google Scholar]
- Ahmad, N.; Bihs, H.; Kamath, A.; Arntsen, Ø.A. Three-dimensional CFD modeling of wave scour around a side-by-side and triangular arrangement of piles with REEF3D. Procedia Eng.
**2015**, 116, 683–690. [Google Scholar] [CrossRef] [Green Version] - Khan, M.A.; McCrum, D.P.; Prendergast, L.J.; OBrien, E.J.; Fitzgerald, P.C.; Kim, C.W. Laboratory investigation of a bridge scour monitoring method using decentralized modal analysis. Struct. Health Monit.
**2021**, 20, 3327–3341. [Google Scholar] [CrossRef] - Kallias, A.N.; Imam, B. Probabilistic assessment of local scour in bridge piers under changing environmental conditions. Struct. Infrastruct. Eng.
**2016**, 12, 1228–1241. [Google Scholar] [CrossRef] - Muzzammil, M.; Alam, J.; Kumar, K.; Khalid, M. Reliability Analysis of a Complex Pier Against Local Scour. J. Inst. Eng. Ser. A
**2022**, 103, 1237–1245. [Google Scholar] [CrossRef] - Tubaldi, E.; Macorini, L.; Izzuddin, B.A.; Manes, C.; Laio, F. A framework for probabilistic assessment of clear-water scour around bridge piers. Struct. Saf.
**2017**, 69, 11–22. [Google Scholar] [CrossRef] [Green Version] - Jafari-Asl, J.; Ben Seghier, M.; Ohadi, S.; Dong, Y.; Plevris, V. A comparative study on the efficiency of reliability methods for the probabilistic analysis of local scour at a bridge pier in clay-sand-mixed sediments. Modelling
**2021**, 2, 63–77. [Google Scholar] [CrossRef] - Jonkman, S.N.; Steenbergen, R.D.J.M.; Morales-Napoles, O.; Vrouwenvelder, A.C.W.M.; Vrijling, J.K. Probabilistic Design: Risk and Reliability Analysis in Civil Engineering; Collegedictaat CIE4130; TU Delft, Department Hydraulic Engineering: Delft, The Netherlands, 2015; p. 103. Available online: http://resolver.tudelft.nl/uuid:e53b8dca-a0db-4433-b9f9-e190a507f99f (accessed on 22 January 2023).
- Ley, C.; Martin, R.K.; Pareek, A.; Groll, A.; Seil, R.; Tischer, T. Machine learning and conventional statistics: Making sense of the differences. Knee Surgery, Sports Traumatology. Arthroscopy
**2022**, 30, 1–5. [Google Scholar] - Gattulli, V.; Lepidi, M.; Potenza, F. Dynamic testing and health monitoring of historic and modern civil structures in Italy. Struct. Monit. Maint.
**2016**, 3, 71–90. [Google Scholar] [CrossRef] - Prendergast, L.J.; Gavin, K. A review of bridge scour monitoring techniques. J. Rock Mech. Geotech. Eng.
**2014**, 6, 138–149. [Google Scholar] [CrossRef] - Maroni, A.; Tubaldi, E.; Ferguson, N.; Tarantino, A.; McDonald, H.; Zonta, D. Electromagnetic sensors for underwater scour monitoring. Sensors
**2020**, 20, 4096. [Google Scholar] [CrossRef] [PubMed] - Marr, J. Bridge Scour Monitoring Technologies: Development of Evaluation and Selection Protocols for Application on River Bridges in Minnesota; (No. MN/RC 2010-14); Minnesota. Dept. of Transportation, Research Services Section: Saint Paul, MN, USA, 2010. [Google Scholar]
- Boujia, N.; Schmidt, F.; Chevalier, C.; Siegert, D.; Pham Van Bang, D. Using rocking frequencies of bridge piers for scour monitoring. Struct. Eng. Int.
**2021**, 31, 286–294. [Google Scholar] [CrossRef] - Purnomo, D.A.; Aspar, W.A.N.; Barasa, W.; Harjono, S.M.; Sukamdo, P.; Fiantika, T. Initial Implementation of Structural Health Monitoring System of a Railway Bridge. In IOP Conference Series: Materials Science and Engineering; IOP Publishing: Bristol, UK, 2021; Volume 1200, No. 1; p. 012019. [Google Scholar]
- Van der Auweraer, H.; Peeters, B. Sensors and systems for structural health monitoring. J. Struct. Control
**2003**, 10, 117–125. [Google Scholar] [CrossRef] - Lynch, J.P. An overview of wireless structural health monitoring for civil structures. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci.
**2007**, 365, 345–372. [Google Scholar] [CrossRef] - Fitzgerald, P.C.; Malekjafarian, A.; Cantero, D.; OBrien, E.J.; Prendergast, L.J. Drive-by scour monitoring of railway bridges using a wavelet-based approach. Eng. Struct.
**2019**, 191, 1–11. [Google Scholar] [CrossRef] - Chandrasekaran, S. Structural Health Monitoring. In Structural Health Monitoring with Application to Offshore Structures; Indian Institute of Technology Madras: Toh Tuck Link, Singapore, 2019; pp. 24–26. [Google Scholar] [CrossRef]
- Martinez, D.; Malekjafarian, A.; OBrien, E. Bridge flexural rigidity calculation using measured drive-by deflections. J. Civ. Struct. Health Monit.
**2020**, 10, 833–844. [Google Scholar] [CrossRef] - Bernardini, L.; Carnevale, M.; Somaschini, C.; Matsuoka, K.; Collina, A. A Numerical Investigation of New Algorithms for The Drive-by Method in Railway Bridge Monitoring. In Proceedings of the EURODYN 2020, XI. International Conference on Structural Dynamics, Athens, Greece, 23–26 November 2020; pp. 1033–1043. [Google Scholar]
- Malekjafarian, A.; Prendergast, L.J.; OBrien, E. Use of mode shape ratios for pier scour monitoring in two-span integral bridges under changing environmental conditions. Can. J. Civ. Eng.
**2020**, 47, 962–973. [Google Scholar] [CrossRef] - Fitzgerald, P.C.; Malekjafarian, A.; Bhowmik, B.; Prendergast, L.J.; Cahill, P.; Kim, C.W.; OBrien, E.J. Scour damage detection and structural health monitoring of a laboratory-scaled bridge using a vibration energy harvesting device. Sensors
**2019**, 19, 2572. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Lin, T.K.; Chang, Y.S. Development of a real-time scour monitoring system for bridge safety evaluation. Mech. Syst. Signal Process.
**2017**, 82, 503–518. [Google Scholar] [CrossRef] - Liu, W.; Zhou, W.; Li, H. Bridge scour estimation using unconstrained distributed fiber optic sensors. J. Civ. Struct. Health Monit.
**2022**, 12, 775–784. [Google Scholar] [CrossRef] - Prendergast, L.J.; Gavin, K.; Hester, D. Isolating the location of scour-induced stiffness loss in bridges using local modal behavior. J. Civ. Struct. Health Monit.
**2017**, 7, 483–503. [Google Scholar] [CrossRef] [Green Version] - Malekjafarian, A.; Kim, C.W.; OBrien, E.J.; Prendergast, L.J.; Fitzgerald, P.C.; Nakajima, S. Experimental Demonstration of a Mode Shape-Based Scour-Monitoring Method for Multispan Bridges with Shallow Foundations. J. Bridge Eng.
**2020**, 25, 04020050. [Google Scholar] [CrossRef] - Funderburk, M.L.; Huang, S.K.; Loh, C.H.; Loh, K.J. Densely distributed and real-time scour hole monitoring using piezoelectric rod sensors. Adv. Struct. Eng.
**2019**, 22, 3395–3411. [Google Scholar] [CrossRef] - Azhari, F.; Tom, C.; Benassini, J.; Loh, K.J.; Bombardelli, F.A. Design and characterization of a piezoelectric sensor for monitoring scour hole evolution. Sens. Smart Struct. Technol. Civ. Mech. Aerosp. Syst.
**2014**, 9061, 301–309. [Google Scholar] - Azhari, F.; Loh, K.J. Laboratory validation of buried piezoelectric scour sensing rods. Struct. Control Health Monit.
**2017**, 24, e1969. [Google Scholar] [CrossRef] - Chen, Y.; Tang, F.; Li, Z.; Chen, G.; Tang, Y. Bridge scour monitoring using smart rocks based on magnetic field interference. Smart Mater. Struct.
**2018**, 27, 085012. [Google Scholar] [CrossRef] - Michalis, P.; Tarantino, A.; Tachtatzis, C.; Judd, M.D. Wireless monitoring of scour and re-deposited sediment evolution at bridge foundations based on soil electromagnetic properties. Smart Mater. Struct.
**2015**, 24, 125029. [Google Scholar] [CrossRef] [Green Version] - Hashimoto, K.; Shiotani, T.; Mitsuya, H.; Chang, K.C. MEMS Vibrational Power Generator for Bridge Slab and Pier Health Monitoring. Appl. Sci.
**2020**, 10, 8258. [Google Scholar] [CrossRef] - Elsaid, A.; Seracino, R. Rapid assessment of foundation scour using the dynamic features of the bridge superstructure. Constr. Build. Mater.
**2014**, 50, 42–49. [Google Scholar] [CrossRef] - Zhang, H.; Li, Z.; Reven, A.; Scharfenberg, B.; Chen, G.; Ou, J. UAV-Based Smart Rock Positioning for Determination of Bridge Scour Depth. In Proceedings of the 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure (SHMII-9), St. Louis, MO, USA, 4–7 August 2019. [Google Scholar]
- OBrien, E.J.; Malekjafarian, A.; Fitzgerald, P.C. Bridge Scour Detection using Vehicle Acceleration Measurements. In Proceedings of the Civil Engineering Research in Ireland 2018 Conference (CERI 2018), Dublin, Ireland, 29–30 August 2018. [Google Scholar]
- OBrien, E.J.; McCrum, D.P.; Khan, M.A.; Prendergast, L.J. Wavelet-based operating deflection shapes for locating scour-related stiffness losses in multi-span bridges. Struct. Infrastruct. Eng.
**2021**, 19, 238–253. [Google Scholar] [CrossRef] - Chopra, A.K. Dynamics of Structures, 4th ed.; Prentice-Hall International Series; Civil Engineering and Engineering Mechanics: Delhi, India, 2007; pp. 428–441, 883–904. [Google Scholar]
- Cerna, M.; Harvey, A.F. The Fundamentals of FFT-Based Signal Analysis and Measurement. In Application Note 041; National Instruments: Austin, TX, USA, 2000. [Google Scholar]
- Feldman, M. Hilbert transform in vibration analysis. Mech. Syst. Signal Process.
**2011**, 25, 735–802. [Google Scholar] [CrossRef] - Brincker, R.; Zhang, L.; Andersen, P. Modal identification of output-only systems using frequency domain decomposition. Smart Mater. Struct.
**2001**, 10, 441. [Google Scholar] [CrossRef] [Green Version] - Le, T.P.; Paultre, P. Modal identification based on the time–frequency domain decomposition of unknown-input dynamic tests. Int. J. Mech. Sci.
**2013**, 71, 41–50. [Google Scholar] [CrossRef] - Grossmann, A.; Kronland-Martinet, R.; Morlet, J. Reading and understanding continuous wavelet transforms. In Wavelets; Springer: Berlin/Heidelberg, Germany, 1990; pp. 2–20. [Google Scholar]
- Torrence, C.; Compo, G.P. A practical guide to wavelet analysis. Bull. Am. Meteorol. Soc.
**1998**, 79, 61–78. [Google Scholar] [CrossRef] - Gao, Y. Structural Health Monitoring Strategies for Smart Sensor Networks, Microform Edition; University of Illinois at Urbana-Champaig: Champaign, IL, USA, 2005. [Google Scholar]
- Nagayama, T.; Spencer Jr, B.F.; Rice, J.A. Autonomous decentralized structural health monitoring using smart sensors. Struct. Control Health Monit Off. J. Int. Assoc. Struct. Control Monit. Eur. Assoc. Control Struct.
**2009**, 16, 842–859. [Google Scholar] [CrossRef] - Sim, S.H.; Spencer, B.F., Jr.; Zhang, M.; Xie, H. Automated decentralized modal analysis using smart sensors. Struct. Control Health Monit.
**2010**, 17, 872–894. [Google Scholar] [CrossRef] - Teolis, A.; Benedetto, J.J. Computational Signal Processing with Wavelets; Springer: Boston, MA, USA, 1998. [Google Scholar]
- Claesen, M.; De Moor, B. Hyperparameter Search in Machine Learning. arXiv
**2015**, arXiv:1502.02127. [Google Scholar] - Zanakis, S.H.; Evans, J.R. Heuristic “optimization”: Why, when, and how to use it. Interfaces
**1981**, 11, 84–91. [Google Scholar] [CrossRef] - Aldwaik, M.; Adeli, H. Advances in optimization of highrise building structures. Struct. Multidiscip. Optim.
**2014**, 50, 899–919. [Google Scholar] [CrossRef] - Topping, B.H.V. Shape optimization of skeletal structures: A review. J. Struct. Eng.
**1998**, 109, 1933–1951. [Google Scholar] [CrossRef] - Cong, S.; Jia, Y.; Deng, K. Particle Swarm and Ant Colony Algorithms and Their Applications in Chinese Traveling Salesman Problem. In New Achievements in Evolutionary Computation; Korosec, P., Ed.; IntechOpen: Rijeka, Croatia, 2010; pp. 298–302. [Google Scholar]
- Sivanandam, S.N.; Deepa, S.N. Genetic algorithm optimization problems. In An Introduction to Genetic Algorithms; Springer: Berlin/Heidelberg, Germany, 2008; pp. 165–209. [Google Scholar]
- Hare, W.; Nutini, J.; Tesfamariam, S. A survey of non-gradient optimization methods in structural engineering. Adv. Eng. Softw.
**2013**, 59, 19–28. [Google Scholar] [CrossRef] - Dorigo, M.; Birattari, M.; Stutzle, T. Ant colony optimization. IEEE Comput. Intell. Mag.
**2006**, 1, 28–39. [Google Scholar] [CrossRef] - Ng, S.T.; Zhang, Y. Optimizing construction time and cost using an ant colony optimization approach. J. Constr. Eng. Manag.
**2008**, 134, 721–728. [Google Scholar] [CrossRef] - Christodoulou, S. Ant colony optimization in construction scheduling. In Proceedings of the International Conference on Computing in Civil Engineering, Cancun, Mexico, 12–15 July 2005; pp. 1–11. [Google Scholar]
- Kaveh, A.; Talatahari, S. An improved ant colony optimization for constrained engineering design problems. Eng. Comput.
**2010**, 27, 155–182. [Google Scholar] [CrossRef] - Venter, G.; Sobieszczanski-Sobieski, J. Particle swarm optimization. AIAA J.
**2003**, 41, 1583–1589. [Google Scholar] [CrossRef] [Green Version] - Wang, S.C. Artificial neural network. In Interdisciplinary Computing in Java Programming; Springer: Boston, MA, USA, 2003; pp. 81–100. [Google Scholar]
- Uddin, S.; Khan, A.; Hossain, M.E.; Moni, M.A. Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inform. Decis. Mak.
**2019**, 19, 1–16. [Google Scholar] [CrossRef] [PubMed] - Rumelhart, D.E.; Hinton, G.E.; Williams, R.J. Learning representations by back-propagating errors. Nature
**1986**, 323, 533–536. [Google Scholar] [CrossRef] - Li, J.; Cheng, J.H.; Shi, J.Y.; Huang, F. Brief introduction of back propagation (BP) neural network algorithm and its improvement. In Advances in Computer Science and Information Engineering; Springer: Berlin/Heidelberg, Germany, 2012; pp. 553–558. [Google Scholar]
- Pal, M. Deep neural network-based pier scour modeling. ISH J. Hydraul. Eng.
**2019**, 28, 80–85. [Google Scholar] [CrossRef] - Maulud, D.; Abdulazeez, A.M. A review on linear regression comprehensive in machine learning. J. Appl. Sci. Technol. Trends
**2020**, 1, 140–147. [Google Scholar] [CrossRef] - Sun, Y.; Zhang, J.; Li, G.; Wang, Y.; Sun, J.; Jiang, C. Optimized neural network using beetle antennae search for predicting the unconfined compressive strength of jet grouting coalcretes. Int. J. Numer. Anal. Methods Géoméch.
**2019**, 43, 801–813. [Google Scholar] [CrossRef] - Sun, J.; Wang, J.; Zhu, Z.; He, R.; Peng, C.; Zhang, C.; Huang, J.; Wang, Y.; Wang, X. Mechanical Performance Prediction for Sustainable High-Strength Concrete Using Bio-Inspired Neural Network. Buildings
**2022**, 12, 65. [Google Scholar] [CrossRef] - Charfi, I.; Miteran, J.; Dubois, J.; Atri, M.; Tourki, R. Definition and performance evaluation of a robust SVM based fall detection solution. In Proceedings of the 2012 Eighth International Conference on Signal Image Technology and Internet-Based Systems IEEE, Sorrento, Italy, 25–29 November 2012; pp. 218–224. [Google Scholar]
- Ukil, A. Support vector machine. In Intelligent Systems and Signal Processing in Power Engineering; Springer: Berlin/Heidelberg, Germany, 2007; pp. 161–226. [Google Scholar]
- Duan, K.; Keerthi, S.S.; Poo, A.N. Evaluation of simple performance measures for tuning SVM hyperparameters. Neurocomputing
**2003**, 51, 41–59. [Google Scholar] [CrossRef] - Dong, S.; Yang, J. On computing the hyperparameter of extreme learning machines: Algorithm and application to computational PDEs, and comparison with classical and high-order finite elements. J. Comput. Phys.
**2021**, 463, 111290. [Google Scholar] [CrossRef] - Oneto, L.; Bisio, F.; Cambria, E.; Anguita, D. Slt-based elm for big social data analysis. Cogn. Comput.
**2017**, 9, 259–274. [Google Scholar] [CrossRef] - Bao, X.; Li, Y.; Li, J.; Shi, R.; Ding, X. Prediction of train arrival delay using hybrid ELM-PSO approach. J. Adv. Transp.
**2021**, 2021, 7763126. [Google Scholar] [CrossRef] - Truong, V.H.; Vu, Q.V.; Thai, H.T.; Ha, M.H. A robust method for safety evaluation of steel trusses using Gradient Tree Boosting algorithm. Adv. Eng. Softw.
**2020**, 147, 102825. [Google Scholar] [CrossRef] - Anghel, A.; Papandreou, N.; Parnell, T.; De Palma, A.; Pozidis, H. Benchmarking and optimization of gradient boosting decision tree algorithms. arXiv
**2018**, arXiv:1809.04559. [Google Scholar] - Ghodsi, H.; Khanjani, M.J. Application of improved GMDH models to predict local scour depth at complex bridge piers. Civil Eng. J.
**2020**, 6, 69–84. [Google Scholar] [CrossRef] - Najafzadeh, M.; Azamathulla, H.M. Neuro-fuzzy GMDH to predict the scour pile groups due to waves. J. Comput. Civ. Eng.
**2015**, 29, 04014068. [Google Scholar] [CrossRef] - Madandoust, R.; Bungey, J.H.; Ghavidel, R. Prediction of the concrete compressive strength by means of core testing using GMDH-type neural network and ANFIS models. Comput. Mater. Sci.
**2012**, 51, 261–272. [Google Scholar] [CrossRef] - Xu, L.; Wang, X.; Bai, L.; Xiao, J.; Liu, Q.; Chen, E.; Jiang, X.; Luo, B. Probabilistic SVM classifier ensemble selection based on GMDH-type neural network. Pattern Recognit.
**2020**, 106, 107373. [Google Scholar] [CrossRef] - Stefenon, S.F.; Ribeiro, M.H.D.M.; Nied, A.; Mariani, V.C.; dos Santos Coelho, L.; da Rocha, D.F.M.; Grebogi, R.B.; de Barros Ruano, A.E. Wavelet group method of data handling for fault prediction in electrical power insulators. Int. J. Electrical Power Energy Syst.
**2020**, 123, 106269. [Google Scholar] [CrossRef] - Samsudin, R.; Saad, P.; Shabri, A. River flow time series using least squares support vector machines. Hydrol. Earth Syst. Sci.
**2011**, 15, 1835–1852. [Google Scholar] [CrossRef] [Green Version] - Martinek, R.; Zidek, J. The real implementation of ANFIS channel equalizer on the system of software-defined radio. IETE J. Res.
**2014**, 60, 183–193. [Google Scholar] [CrossRef] - Vieira, J.; Dias, F.M.; Mota, A. Neuro-fuzzy systems: A survey. In Proceedings of the 5th WSEAS NNA International Conference on Neural Networks and Applications, Udine, Italia, 25–27 March 2004; pp. 1–6. [Google Scholar]
- Han, M.; Zhao, Y. Dynamic control model of BOF steelmaking process based on ANFIS and robust relevance vector machine. Expert Syst. Appl.
**2011**, 38, 14786–14798. [Google Scholar] [CrossRef] - Fattahi, H.; Hasanipanah, M. An integrated approach of ANFIS-grasshopper optimization algorithm to approximate flyrock distance in mine blasting. Eng. Comput.
**2021**, 38, 2619–2631. [Google Scholar] [CrossRef] - Zhang, J.; Zhao, H. A Prediction Model for Local Scour Depth around Piers Based on CNN. In Proceedings of the 2020 International Conference on Information Science, Parallel and Distributed Systems (ISPDS) IEEE, Xi’an, China, 14–16 August 2020; pp. 318–320. [Google Scholar]
- Dong, H.; Chen, F.; Zhou, H.; Guo, C.; Sun, Z. A Prediction Model for Local Scour Depth around Piers Based on Machine Learning. In IOP Conference Series: Earth and Environmental Science; IOP Publishing: Bristol, UK, 2020; Volume 525, No. 1; p. 012080. [Google Scholar]
- Khosravi, K.; Khozani, Z.S.; Mao, L. A comparison between advanced hybrid machine learning algorithms and empirical equations applied to abutment scour depth prediction. J. Hydrol.
**2021**, 596, 126100. [Google Scholar] [CrossRef] - Tien Bui, D.; Shirzadi, A.; Amini, A.; Shahabi, H.; Al-Ansari, N.; Hamidi, S.; Singh, S.K.; Thai Pham, B.; Ahmad, B.B.; Ghazvinei, P.T. A Hybrid Intelligence Approach to Enhance the Prediction Accuracy of Local Scour Depth at Complex Bridge Piers. Sustainability
**2020**, 12, 1063. [Google Scholar] - Ebtehaj, I.; Sattar, A.M.; Bonakdari, H.; Zaji, A.H. Prediction of scour depth around bridge piers using self-adaptive extreme learning machine. J. Hydroinform.
**2017**, 19, 207–224. [Google Scholar] [CrossRef] - Ebtehaj, I.; Bonakdari, H.; Moradi, F.; Gharabaghi, B.; Khozani, Z.S. An integrated framework of Extreme Learning Machines for predicting scour at pile groups in clearwater conditions. Coast. Eng.
**2018**, 135, 1–15. [Google Scholar] [CrossRef] - Ebtehaj, I.; Bonakdari, H.; Zaji, A.H.; Sharafi, H. Sensitivity analysis of parameters affecting scour depth around bridge piers based on the non-tuned, rapid extreme learning machine method. Neural Comput. Appl.
**2019**, 31, 9145–9156. [Google Scholar] - Richardson, E.V.; Davis, S.R. Evaluating Scour at Bridges; (No. FHWA-NHI-01-001); The United States. Federal Highway Administration, Office of Bridge Technology: Lakewood, CO, USA, 2001.
- Johnson, P.A. Reliability-based pier scour engineering. J. Hydraul. Eng.
**1992**, 118, 1344–1358. [Google Scholar] [CrossRef] - Shen, H.W.; Schneider, V.R.; Karaki, S. Local scour around bridge piers. J. Hydraul. Div.
**1969**, 95, 1919–1940. [Google Scholar] [CrossRef] - Sreedhara, B.M.; Patil, A.P.; Pushparaj, J.; Kuntoji, G.; Naganna, S.R. Application of gradient tree boosting regressor for the prediction of scour depth around bridge piers. J. Hydroinform.
**2021**, 23, 849–863. [Google Scholar] [CrossRef] - Cheng, M.Y.; Cao, M.T.; Wu, Y.W. Predicting equilibrium scour depth at bridge piers using evolutionary radial basis function neural network. J. Comput. Civ. Eng.
**2015**, 29, 04014070. [Google Scholar] - Van Wilson, K. Scour at Selected Bridge Sites in Mississippi; US Department of the Interior: Washington DC, USA; US Geological Survey: Denver, CO, USA, 1995; Volume 94, No. 4241.
- Froehlich, D.C. Analysis of onsite measurements of scour at piers. In Hydraulic Engineering: Proceedings of the 1988 National Conference on Hydraulic Engineering; American Society of Civil Engineers: New York, NY, USA, 1988; pp. 534–539. [Google Scholar]
- Hoang, N.D.; Liao, K.W.; Tran, X.L. Estimation of scour depth at bridges with complex pier foundations using support vector regression integrated with feature selection. J. Civ. Struct. Health Monit.
**2018**, 8, 431–442. [Google Scholar] - Melville, B.W.; Coleman, S.E. Bridge Scour; Water Resources Publication: Littleton, CO, USA, 2000. [Google Scholar]
- Ataie-Ashtiani, B.; Baratian-Ghorghi, Z.; Beheshti, A.A. Experimental investigation of clear-water local scour of compound piers. J. Hydraul. Eng.
**2010**, 136, 343–351. [Google Scholar] [CrossRef] - Kim, I.; Fard, M.Y.; Chattopadhyay, A. Investigation of a bridge pier scour prediction model for safe design and inspection. J. Bridge Eng.
**2015**, 20, 04014088. [Google Scholar] [CrossRef] - Liao, K.W.; Muto, Y.; Lin, J.Y. Scour depth evaluation of a bridge with a complex pier foundation. KSCE J. Civ. Eng.
**2018**, 22, 2241–2255. [Google Scholar] - Amini, A.; Mohammad, T.A. Local scour prediction around piers with complex geometry. Mar. Georesources Geotechnol.
**2017**, 35, 857–864. [Google Scholar] [CrossRef] - Mueller, D.S.; Wagner, C.R. Field Observations and Evaluations of Streambed Scour at Bridges; (No. FHWA-RD-03-052); United States, Federal Highway Administration, Office of Research, Development, and Technology: Richmond, VA, USA, 2005.

**Figure 1.**Scour monitoring devices - copied from [32].

Study Ref. | Device Type | Sensing Mechanism | Signal Processing Method | The Target Property of Signal Processing | Scour Validation Tests | Laboratory or Field Tests | Target Property |
---|---|---|---|---|---|---|---|

[45] | Unconstrained distributed fiber optic sensors | Ultra-weak fiber Bragg grating | Empirical formula | Central wavelengths | Detecting different signals of set of fibers embedded in sand and other fibers freely in water | Standard deviation value higher than zero for several minutes | Scour depth and location |

[44] | Velocity sensors, inclinometer, wireless transmitter, and camera | 2 Velocity sensors | Hilbert transform and empirical mode decomp. | Individual instant frequencies | Single-pier laboratory scour test | Caisson-type and pile-group foundation scour tests | Rigid body motion |

[48] | Rod sensor | Piezoelectric Polymer Film | Wavelet packet transform and Hilbert transform | Instant the natural frequency of the rod | Flume test | Test with different pier cross-sections | Scour depth |

[49] | Piezoelectric Polymer Film | Fast fourier transform | Instant natural frequency of the rod | Clamped to a laboratory bench | None | ||

Planted in sand | |||||||

Implemented in the sand | |||||||

[50] | Flume test | Tested on 1 pier | |||||

[51] | 1 Direction-Unknown and 1 Direction-Known smart rocks | Ambient magnetic field | Theory of magnetic field | Distribution of the magnetic field induced by smart rocks | Field validation tests | Tests on the upstream side of a pier | Localize the position or track the move of the smart rock |

[52] | E.magnetic sensors | Changes in the dielectric permittivity of the soil | The reflection feature of e.magnetic waves | The porosity of the soil | ‘Static’ scour simulations | Not provided | Scour depth variation |

Real-time open channel flume tests | |||||||

[55] | Unmanned Aerial Vehicle -based smart rock positioning system | 3-axis magnetometer and global positioning system on Unmanned Aerial Vehicle | Algorithm to locate smart rocks using measured magnetic intensities | Magnetometer measuring magnetic fields before and after the smart rock has been deployed | Not provided | I-44W Roubidoux Creek Bridge Pier | Depth of scour, i.e., vertical move of the rock |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Tola, S.; Tinoco, J.; Matos, J.C.; Obrien, E.
Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review. *Appl. Sci.* **2023**, *13*, 1661.
https://doi.org/10.3390/app13031661

**AMA Style**

Tola S, Tinoco J, Matos JC, Obrien E.
Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review. *Applied Sciences*. 2023; 13(3):1661.
https://doi.org/10.3390/app13031661

**Chicago/Turabian Style**

Tola, Sinem, Joaquim Tinoco, José C. Matos, and Eugene Obrien.
2023. "Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review" *Applied Sciences* 13, no. 3: 1661.
https://doi.org/10.3390/app13031661