ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING APPLICATIONS IN PREDICTION OF SCOUR - A REVIEW

P. DHIMMAR, R. POPAWALA

Abstract


Scour around bridge piers is one of the major attributes of bridge failure. Scour prediction has primarily depended on physical modelling and empirical formulas. Traditional empirical formulas are often insufficient for accounting for the intricate interactions of hydraulic, sediment, and geometric parameters. This paper presents a state-of-the-art review of artificial intelligence and machine learning approaches to local scour prediction, spanning the literature from 2004 to 2025, with a focus on ML, hybrid, and physics-informed models. The study reviewed various models, including artificial neural networks, adaptive neuro-fuzzy inference systems, support vector machines, gene expression programming, particle swarm optimization-based hybrids, and physics-informed neural networks, and compared early-warning Internet of Things systems. The paper offers a comprehensive evaluation of the strengths and limitations of existing machine learning models for scour estimation, considering factors such as data availability, interpretability, and adaptability to changing environmental conditions. The study also emphasizes recent advances such as deep learning, long short-term memory, convolutional neural network architectures, and physics-guided networks. Case studies and methodological comparisons are supplied to show predictive supremacy and limitations of varying approaches. The study evaluates performance, challenges, and future directions like physics-constrained learning, digital twins, and real-time monitoring. AI and physics-informed models outperform traditional empirical equations in bridge scour prediction and enable real-time monitoring through digital twin frameworks.


Keywords


Artificial intelligence (AI), Artificial neural networks (ANN), Machine learning (ML), Pier, Scour, Support vector machines (SVM).

Full Text:

PDF

References


ACHOUR B., AMARA L., MEHTA D. (2022). Control of the hydraulic jump by a thin crested sill in a rectangular channel: New experimental considerations, Larhyss Journal, No 50, pp. 31-48.

ANSARI M.A., DANISH M., HUSSAIN A., AZAMATHULLA H.M. (2024). ANFIS based approach to predict sediment removal efficiency of vortex settling basin, Larhyss Journal, No 59, pp. 193-209.

ARDICLIOGLU M., HADI A.M.W.M., PERIKU E., KURIQI A. (2022). Experimental and Numerical Investigation of Bridge Configuration Effect on Hydraulic Regime, International Journal of Civil Engineering, Vol. 20, pp. 981-991.

ATALLAH M., DJELLOULI F., HAZZEB A. (2024). Rainfall-runoff modeling using the HEC-HMS model for the Mekerra wadi watershed (N-W Algeria), Larhyss Journal, No 57, pp. 187-208.

BARANWAL A., DAS B.S., (2024). Scouring around bridge pier: a comprehensive review of countermeasure techniques, Engineering Research Express, Vol. 6, Issue 2, Paper ID 022103.

BARANWAL A., DAS B.S., CHOUDHARY A. (2023). Bridge pier scour depth prediction model-a review, Fluid Mechanics and Hydraulics, HYDRO 2021, Lecture Notes in Civil Engineering, Springer, Singapore, Vol. 314, pp. 75-88.

BATENI S.M., BORGHEI S.M., JENG D.S. (2007). Neural Network and Neuro-Fuzzy Assessments for Scour Depth around Bridge Piers, Engineering Applications of Artificial Intelligence, Vol. 20, Issue 3, pp. 401-414.

BAUDHANWALA D., MEHTA D., KUMAR V. (2024). Machine learning approaches for improving precipitation forecasting in the Ambica River basin of Navsari District, Gujarat, Water Practice & Technology, Vol. 19, No 4, pp. 1315-1329.

BELOUZ K., ZEREG S., MATALLAH, S. (2025). Modeling reservoir surface water temperature with neural networks and ANFIS, Larhyss Journal, No 64, pp. 57-81.

BOUGAMOUZA A., REMINI B., AMMARI A., SAKHRAOUI F. (2022). Oued El Abiod basin (Algeria): solid transport estimation by three artificial neural network methods, Larhyss Journal, No 49, pp. 165-179.

BOURICHE F., DEBABECHE M., CARVALHO RITA F., DJEDDOU M. (2023). Velocity distribution in a controlled hydraulic jump in a compound channel: an experimental and machine learning (ML) study, Larhyss Journal, No 54, pp. 217-237.

CHABOKPOUR J., AZAMATHULLA H.M.D. (2025a). Multi-scale CFD analysis of erosion dynamics in heterogeneous rockfill structures implications for sustainable hydraulic engineering design, Larhyss Journal, No 61, pp. 217-239.

CHABOKPOUR J., AZAMATHULLA H.M.D., NAMPALLI R.C.R., SYED S. (2025b). Unraveling complex discharge-water quality dynamics, Larhyss Journal, No 62, pp. 107–128.

CHAPLOT B., PETERS M., BIRBAL P., PU J.H., SHAFIE A. (2021). Use of gene-expression programming to estimate Manning’s roughness coefficient for low flow stream, Larhyss Journal, No 48, pp. 135-150.

CHEN X., YU Y., LIU L. (2025). Physics-informed neural network for prediction of scour depth using natural frequency of monopiles, Ocean Engineering, Vol. 339, Part 1, Paper ID 122054.

DALAL B., DEB S. (2024). An experimental study on the variation of scour depth for different pier shapes using a tilting flume, Larhyss Journal, No 57, pp. 209-239.

DALAL B., ACHOUR B. (2025). Local scour variation at parallel bridges: a case study on Golaghati bridge, Tripura, India. Larhyss Journal, No 64, pp. 107-133.

DANG N.M., TRAN D., DANG T.D., (2021). ANN optimized by PSO and Firefly algorithms for predicting scour depths around bridge piers, Engineering with Computers, Vol. 37, pp. 293-303.

DEY S., BARBHUIYA A.K. (2005). Time variation of scour at abutments, Journal of Hydraulic Engineering, Vol. 131, Issue 1, pp. 11-23.

EBTHEHAJ I., BONAKDARI H., MORADI F., GHARABAGHI B., KHOZANI Z.S. (2018). An integrated framework of extreme learning machines for predicting scour at pile groups in clear water condition, Coastal Engineering, Vol. 135, pp. 1-15.

FAREGH W., BENKHALED A. (2016). GIS based SCS-CN method for estimating runoff in Sigus watershed, Larhyss Journal, No 27, pp. 257-276. (In French)

FATEMI S.M., MOLAVI A. (2025). Comparative study of machine learning models in predicting water table fluctuations in Azarshahr Plain, Iran, Larhyss Journal, No 61, pp. 343-369.

FELLOUS S., BENDJAMA A., BENZAOUI Y. (2023). Use of machine learning algorithms and in situ data for estimating particulate organic carbon (POC) from the Mediterranean, Sea, Larhyss Journal, No 56, pp. 179-192.

FIRAT M., GÜNGÖR M. (2009). Generalized regression neural networks and feed-forward neural networks for prediction of scour depth around bridge piers, Advances in Engineering Software, Vol. 40, Issue 8, pp. 731-737.

FUJAIL A.K.M. (2022). Hybrid Artificial Neural Network Model for Prediction of Scour Depth Upstream of Bridge Piers, Soft Computing: Theories and Applications, Lecture Notes in Networks and Systems, Springer, Singapore, Vol. 425, pp. 741-746.

GHASEMI ASL M., HEIDARNEJAD M. (2023). A numerical study of the maximum scour depth around inclined bridge piers and comparison with an experimental model, Larhyss Journal, 56, pp. 55-75.

HAMDIA K.M., ZHUANG X., RABCZUK T. (2021). An efficient optimization approach for designing machine learning models based on genetic algorithm, Neural Computing and Applications, Vol. 33, pp. 1923-1933.

HASHEM T., YOUSEFPOUR N. (2024). Application of Long-Short Term Memory and Convolutional Neural Networks for Real-Time Bridge Scour Prediction, arXiv Preprint, pp. 1-29.

HONG J.H., GOYAL M.K., CHIEW Y.M., CHUA L.H.C. (2012). Predicting time-dependent pier scour depth with support vector regression, Journal of Hydrology, Vol. 468-469, pp. 241-248.

JATOLIYA A., BHATTACHARYA D., MANNA B., BENTO A., TIAGO FAZERES FERRADOSA T. (2024). Physics-based and machine-learning models for accurate scour depth prediction, Philosophical Transactions of the Royal Society A, Vol. 382, No 2264, Paper ID 20220403.

KHOSRAVI K., KHOZANI Z.S., MAO L. (2021). A comparison between advanced hybrid machine learning algorithms and empirical equations applied to abutment scour depth prediction, Journal of Hydrology, Vol. 596, Paper ID 126100.

KOHANSARBAZ A., YAGHOUBI B., IZADBAKHSH M.A., SHABANLOU S. (2021). An integration of adaptive neuro-fuzzy inference system and firefly algorithm for scour estimation near bridge piers, Earth Science Informatics, Vol. 14, pp. 1399-1411.

KUMAR A., BARANWAL A., DAS B.S. (2023). Modelling of clear water scour depth around bridge piers using M5 tree and ANN-PSO, Aqua Water Infrastructure, Ecosystem and Society, Vol. 72, No 8, pp. 1386-1403.

KUMAR A., KOTHYARI U.C., RAJU K.G.R. (2012). Flow structure and scour around circular compound bridge piers-a review, Journal of Hydro-Environment Research, Vol. 6, Issue 4, pp. 251-265.

KUMAR V., AZAMATHULLA H.M., SHARMA K.V., MEHTA D.J., MAHARAJ K.T. (2023). The state of the art in deep learning applications, challenges, and future prospects: A comprehensive review of flood forecasting and management, Sustainability, Vol. 15, Issue 13, pp. 1-33.

KUMAR V., KEDAM N., SHARMA K.V., MEHTA D.J., CALOIERO T. (2023). Advanced machine learning techniques to improve hydrological prediction: A comparative analysis of streamflow prediction models, Water, Vol. 15, Issue 14, pp. 1-24.

MARULASIDDAPPA S.B., PATIL A.P., KUNTOJI G. (2024). Prediction of scour depth around bridge abutments using ensemble machine learning models, Neural Computing and Applications, Vol. 36, pp. 1369-1380.

MEHTA D., YADAV S. (2020). Analysis of scour depth in the case of parallel bridges using HEC-RAS, Water Supply, Vol. 20, Issue 8, pp. 3419-3432.

MOHAMMADPOUR R., GHANI A.A., VAKILI M., SABZEVARI T. (2016). Prediction of temporal scour hazard at bridge abutment, Natural Hazards, Vol. 18, pp. 1891-1911.

MOLAVI A. (2025). Application of intelligent autocorrelated models for runoff simulation a case study of the Iranian Samiyan and Doostbighlou rivers, Larhyss Journal, No 64, pp. 7-32.

MUZZAMMIL M. (2008). Application of neural networks to scour depth prediction at the bridge abutments, Engineering Applications of Computational Fluid Mechanics, Vol. 2, No 1, pp. 30-40.

OĞUZ K., BOR A. (2022). Prediction of Local Scour around Bridge Piers Using Hierarchical Clustering and Adaptive Genetic Programming, Applied Artificial Intelligence, Vol. 36, No 1, Paper ID 2001734.

PAL M. (2019). Deep neural network-based pier scour modeling, Indian Society of Hydraulics (ISH) Journal of Hydraulic Engineering, Vol. 28, No 1, pp. 80-85.

PAL M., SINGH N.K., TIWARI N.K. (2011). Support vector regression-based modeling of pier scour using field data, Engineering Applications of Artificial Intelligence, Vol. 24, Issue 5, pp. 911-916.

PÉREZ-CRUZ F., BOUSQUET O. (2004). Kernel methods and their potential use in signal processing, IEEE Signal Processing Magazine, Vol. 21, No 3, pp. 57-65

RAHMAN F., CHAVAN R. (2025). Machine learning application in prediction of scour around bridge piers: a comprehensive review, Archives of Computational Methods in Engineering, Vol. 32, pp. 1299-1322.

SINGH N.B., DEVI T.T., KUMAR B. (2020). The local scour around bridge piers-a review of remedial techniques, Indian Society of Hydraulics (ISH) Journal of Hydraulic Engineering, Vol. 28, No 1, pp. 527-540.

SREEDHARA B.M., KUNTOJI G., MANDAL S. (2019). Application of particle swarm-based neural network to predict scour depth around bridge pier, International Journal of Intelligent Systems and Applications, No 11, pp. 38-47.

SULTANA T., NANDI B., DAS S. (2025). A Systematic Review of Collar-based Scour Countermeasures for Bridge Piers, Archives of Computational Methods in Engineering, pp. 1-24.

YOUSEFPOUR N., CORREA O. (2023). Towards an AI-based early warning system for bridge scour, Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, Vol. 17, Issue 4, pp. 713-739.

ZAID M., YAZDANFAR Z., CHOWDHURY H., ALAM F. (2019). A review on the methods used to reduce the scouring effect of bridge pier, Energy Procedia, Vol. 160, pp. 45-50.

ZAIDI K., DJEDDOU M., SEKIOU F., HAMEED I.A., SHAWAQFAH M. (2023). Predictive modelling of daily dried sludge production in full-scale wastewater treatment plant using different machine learning combined with empirical mode decomposition, Larhyss Journal, No 56, pp. 77-106.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.