Machine Learning-Based Computation of Transient Bed Profiles for cohesive channel bed
Keywords:
Machine Learning Models, Transient Bed Profiles, Cohesive Sediments, Gamma-test Sensitivity Analysis, Hydraulic Erosion ModelingAbstract
This study utilizes machine learning models, including Support Vector Machine (SVM), Gene Expression Programming (GEP), and Artificial Neural Network (ANN), to predict transient bed profiles in cohesive channel beds composed of clay-silt-sand-gravel mixtures with clay content ranging from 10% to 50%. By leveraging 4,200 experimental data points (70% for training and 30% for testing), dimensional analysis and Γ-test for sensitivity analysis were employed to identify key dimensionless parameters: clay percentage (Pc), normalized time ( ), relative density ( ), void ratio (e), moisture content (w), and normalized distance ( ). GEP demonstrated superior performance, achieving the highest testing accuracy (R2=0.9955, RMSE=1.8456), followed by SVM (R2 = 0.9870, RMSE = 3.2480) and ANN (R2 = 0.9838, RMSE = 3.9143). Taylor diagrams and DDR analysis validated the robustness of Gene Expression Programming (GEP), demonstrating optimal correlation and minimal variance compared to observed data. GEP’s symbolic regression yielded interpretable equations using operators (+, -, *, /, x2, ), while SVM and ANN exhibited higher deviations for extreme values. This study emphasizes GEP's effectiveness in capturing nonlinear erosion dynamics, making it a reliable tool for predicting bed degradation in hydraulic engineering applications. The results highlight the significance of model interpretability and parameter selection, offering valuable insights for soil erosion management and sediment transport modeling.
References
1. Achite, M., Yaseen, Z. M., Heddam, S., Malik, A., & Kisi, O. (2022). Advanced machine learning models development for suspended sediment prediction: comparative analysis study. Geocarto International, 37(21), 6116-6140.
2. Ahmad, Z., Singh, U. K., & Kumar, A. (2018). Incipient motion for gravel particles in clay-silt-gravel cohesive mixtures. J Soils Sediments, 18, 3082–3093. doi: 10.1007/s11368-017-1869-z.
3. Amistapuram, K., Pandiri, L., Raju, V. R., Paleti, S., Singireddy, S., & Sheelam, G. K. (2025). AI-Based Cloud Infrastructure and MLOps Frameworks for Scalable Data Engineering Across Banking and Insurance. In 2025 IEEE International Conference on Communication Networks and Computing (CNC) (pp. 186–192). IEEE. 2025 IEEE International Conference on Communication Networks and Computing (CNC). https://doi.org/10.1109/cnc68716.2025.11484532
4. Azmathullah, HM, Deo, MC and Deolalikar, PB (2005). Neural Networks for Estimation of Scour Downstream of a Ski-Jump Bucket. Journal of Hydraulic Engineering 131 (10), 898-908
5. Baranwal, A., & Das, B. S. (2024). Live-bed scour depth modelling around the bridge pier using ANN-PSO, ANFIS, MARS, and M5Tree. Water Resources Management, 38(12), 4555-4587.
6. Baranwal, A., Kumar, S., Saurabh, S., & Das, B. S. (2025). Estimation of Bridge Pier Scour Depth Under Clear Water and Live Bed Scouring Conditions Using MARS and ETR Machine Learning Technique. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 1-27.
7. Mattaparthi, R. (2025). GenAI-Augmented Diagnostic Reasoning for Diesel Engine Fault Triage: A Large Language Model Framework for Technician Decision Support at Scale. Journal of Material Sciences & Manufacturing Research, 6(12), 1. https://doi.org/10.47363/jmsmr/2025(6)226
8. Bezak, N., Borrelli, P., Mikoš, M., Auflič, M. J., & Panagos, P. (2024). Towards multi-model soil erosion modelling: An evaluation of the erosion potential method (EPM) for global soil erosion assessments. CATENA, 234, 107596, doi: 10.1016/j.catena.2023.107596.
9. Cortes C., Vapnik V. (1995) Support-vector networks. Machine learning, 20, 273-297.
10. Fardoost, E., Dastgahi, M., Nourali, R., & Ayati, E. (2024). Assessment of GEP and ANN for Predicting Suspended Sediment Load: A Case Study of Ghatoor and Aland Rivers, West Azerbaijan, Iran. Journal of Hydraulic and Water Engineering, 1(2), 11-26.
11. Fatahi, M. and Lashkar-Ara, B. (2017). Estimating scour below inverted siphon structures using stochastic and soft computing approaches. Journal of AI and Data Mining, 5(1), 55-66.
12. Ferreira, C. (2001) Gene Expression Programming: A New Adaptive Algorithm for Solving Problems. Complex System, 13(2), 87–129.
13. Fuladipanah, M., Azamathulla, H. M., Kisi, O., Kouhdaragh, M., & Mandala, V. (2024). Quantitative forecasting of bed sediment load in river engineering: an investigation into machine learning methodologies for complex phenomena. Water Supply, 24(2), 585-600. https://doi.org/10.2166/ws.2024.017
14. Kolla, S. K. (2025). Next-Generation Precision Healthcare: AI-Driven Clinical Intelligence, Predictive Analytics, and Adaptive Decision Support Systems. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(4), 12539-12552.
15. Fuladipanah, M., Azamathulla, H. M., Tota-Maharaj, K., Mandala, V., & Chadee, A. (2023). Precise forecasting of scour depth downstream of flip bucket spillway through data-driven models. Results in Engineering, 20, 101604.
16. Gupta, D., Hazarika, B. B., Berlin, M., Sharma, U. M., & Mishra, K. (2021). Artificial intelligence for suspended sediment load prediction: a review. Environmental earth sciences, 80(9), 346.
17. Hamizak, S. N., Suifa, Z., Jelania, J., & Ahmada, N. (2024). Dynamic of Sediment Transport Capacity by Overland Flow: A Review. Jurnal Kejuruteraan, 36(5), 2019–2034. doi: 10.17576/jkukm-2024-36(5)-21.
18. Siva Hemanth Kolla, Narendra Mangala. (2025). DESIGNING AUTONOMOUS LLM AGENT FRAMEWORKS USING GEN AI PIPELINES TO ENHANCE CUSTOMER SERVICE MANAGEMENT AND KNOWLEDGE WORKFLOWS. Lex Localis - Journal of Local Self-Government, 23(S6), 9719–9733. https://doi.org/10.52152/rhxpbz87
19. Jacobs, W., Le Hir, P., Van Kesteren, W., & Cann, P. (2011). Erosion threshold of sand–mud mixtures. Cont. Shelf Res. 31(10): S14–S25. doi: 10.1016/j.csr.2010.05.012.
20. Jain, R. K., & Kothyari, U. C. (2009). Cohesion influences on erosion andbed load transport. Water Resour. Res. 45(6), W06410. doi: 10.1029/2008WR007044.
21. Kheimi, M. (2024). Data-driven approaches for estimation of sediment discharge in rivers. Earth Science Informatics, 17(1), 761-781.
22. Mattaparthi, R. (2025). GenAI-Augmented Diagnostic Reasoning for Diesel Engine Fault Triage: A Large Language Model Framework for Technician Decision Support at Scale. Journal of Material Sciences & Manufacturing Research, 6(12), 1. https://doi.org/10.47363/jmsmr/2025(6)226
23. Koncar N. 1997. Optimisation methodologies for direct inverse neurocontrol. (Publication No. SW72BZ) [Doctoral dissertation London University Englan].
24. Lashkar-Ara, B., Baharvand, S., & Najafi, L. (2020). The Study of the Performance of Data-Driven Models to Predict the Scour Depth Caused by the Aerated Vertical Jet. Irrigation Sciences and Engineering, 43(4), 79-89.
25. Lashkar-Ara, B., Kalantari, N., Sheikh Khozani, Z., & Mosavi, A. (2021). Assessing machine learning versus a mathematical model to estimate the transverse shear stress distribution in a rectangular channel. Mathematics, 9(6), 596.
26. Mangalampalli, B. M., Kolla, S. K., Bandi, V. D. V. K., Yandamuri, U. S., & Rani, P. S. (2025). Designing Intelligent Healthcare Ecosystems through Adaptive Data Integration and Autonomous Learning Systems. Vascular and Endovascular Review, 8(20s), 330-347.
27. Li, K-Q., Liu, Y., & Kang, Q. (2022). Estimating the thermal conductivity of soils using six machine learning algorithms. International Communications in Heat and Mass Transfer, 136, 106139. doi: 10.1016/j.icheatmasstransfer.2022.106139.
28. Liu, C., Han Li, H., Xu, J., Gao,, W., Shen, X., & Miao, S. (2023). Applying Convolutional Neural Network to Predict Soil Erosion: A Case Study of Coastal Areas. Int. J. Environ. Res. Public Health, 20(3), 2513. doi: 10.3390/ijerph20032513.
29. Majedi-Asl, M., Daneshfaraz, R., Fuladipanah, M., Abraham, J., & Bagherzadeh, M. (2020). Simulation of bridge pier scour depth base on geometric characteristics and field data using support vector machine algorithm. Journal of Applied Research in Water and Wastewater, 7(2), 137-143.
30. Kolla, S. H. (2025). Autonomous Agentic Frameworks for Enterprise Service Operations and Intelligent Process Automation. International Journal of Science, Research and Technology, 8(4), 14643-14655.
31. Majeed, F., Ziggah, Y. Y., Kusi-Manu, C., Ibrahim, B., & Ahenkorah, I. (2022). A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines. Geosystems and Geoenvironment, 1(2), 100038.
32. Moradinejad, A. (2024). Suspended load modeling of river using soft computing techniques. Water Resources Management, 38(6), 1965-1986.
33. Moradinejad, A., Khosrobeigi, S., Akbari, M., & Hosseini, S. A. (2024). Investigating soft calculation methods in river suspended sediment estimation (Hassan Abad station of Tirah river). Water and Soil Management and Modeling, 4(2), 241-260.
34. Murtaza, N., Khan, D., Rezzoug, A., Khan, Z. U., Benzougagh, B., & Khedher, K. M. (2025). Scour depth prediction around bridge abutments: A comprehensive review of artificial intelligence and hybrid models. Physics of Fluids, 37(2).
35. Raghunath Loganathan. (2025). AGENTIC AI FRAMEWORKS FOR AUTONOMOUS RISK DETECTION AND COMPLIANCE REMEDIATION IN ENTERPRISE DATA CENTER OPERATIONS. Lex Localis - Journal of Local Self-Government, 23(S6), 9672–9697. https://doi.org/10.52152/3f90ak91
36. Noori R., Khakpour A., Omidvar B., Farokhnia A. 2010. Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistics. Expert Systems with Applications 37: 5856-5862.
37. Sammen, S. S., Amini, A., Othman Ahmed, K., Sadeghifar, T., Pushparaj, J., & Naganna, S. R. (2025). Improving Bridge Safety: A Spider Monkey Optimization-based ANN Model for Scour Depth Prediction. Water Resources Management, 1-23.
38. Shalini, S. H. A. L. I. N. I., & Roshni, T. (2023). Application of GEP, M5-TREE, ANFIS, and MARS for predicting scour depth in live bed conditions around bridge piers. Journal of Soft Computing in Civil Engineering, 7(4), 24-49.
39. Lebcir, I., Mageswari, S. U., Bhosale, Y. H., Nagubandi, A. R., & Mahabooba, M. M. Agile Strategic Management in the Age of Disruption: Leveraging AI and Data Analytics for Competitive Advantage.
40. Singh, U. K., & Ahmad, Z. (2019). Transport rate and bed profile computations for clay–silt–gravel mixture. Environ Earth Sci., 78, 432. doi: 10.1007/s12665-019-8419-5.
41. Singh, U. K., Ahmad, Z., & Kumar, A. (2017). Formulation for critical shear stress of cohesive sediment mixture. Current Science, 113(11), 2105-2111.
42. Singh, U. K., Jamei, M., Karbasi, M., Malik, A., & Pandey, M. (2022). Application of a modern multi-level ensemble approach for the estimation of critical shear stress in cohesive sediment mixture. Journal of Hydrology, 607, 127549, doi: 10.1016/j.jhydrol.2022.127549.
43. Tao, H., Al-Khafaji, Z. S., Qi, C., Zounemat-Kermani, M., Kisi, O., Tiyasha, T., ... & Yaseen, Z. M. (2021). Artificial intelligence models for suspended river sediment prediction: state-of-the art, modeling framework appraisal, and proposed future research directions. Engineering Applications of Computational Fluid Mechanics, 15(1), 1585-1612.
44. Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res-Atmos 106:7183–7192.
45. Yang, J., Jia, D., Zhai, B., Chen, X, & Wang, J. (2024). Bank erosion under the impacts of fluvial erosion, frost heaving/freeze-thaw process of rivers in seasonal frozen regions. Heliyon, 10(17), e37448. doi: 10.1016/j.heliyon. 2024.e37448.
Additional Files
Published
Issue
Section
License
Copyright (c) 2025 European Advanced Journal for Science & Engineering (EAJSE)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Articles published in the European Advanced Journal for Science & Engineering (EAJSE) are made freely available online immediately upon publication under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium or format, provided the original work is properly cited. Authors retain copyright of their work. By submitting to EAJSE, authors grant the journal the right of first publication. For details, visit: https://creativecommons.org/licenses/by/4.0/
