رویکردهای نوین در مهندسی آب و محیط‌زیست
نشریه علمی

Machine Learning models for High-Accuracy Prediction of Energy Dissipation Through Gabion Sills Downstream of Spillways

نوع مقاله : مقاله پژوهشی

نویسندگان

Shahram Shakeri yousefi 1
Mohsen Najarchi 1
Mehdi Fuladipanah 2
Mahmood Rabani Bidgoli 3

1 Department of Civil Engineering, Ar. C., Islamic Azad University, Arak, Iran.

2 Department of Civil Engineering Ramh. C., Islamic AzadUniversity,Ramhormoz, Iran.

3 Department of Civil Engineering, Jasb. C., Islamic Azad University, Jasb, Iran.

https://doi.org/10.22034/nawee.2025.507107.1140
چکیده
Objective: the objective of this paper is to develop and compare three MLMs, SVR, GEP and ANN- for the high-accuracy prediction of energy dissipation downstream of gabion sills in spillways. Through dimensional analysis and sensitivity evaluation using the Γ-test, the most influential hydraulic and geometric parameters are identified. The performance of each model is rigorously assessed using statistical metrics to determine their predictive reliability and accuracy, with the aim of identifying the most effective computational approach for optimizing energy dissipation in gabion-structured spillway systems.
Material and Methods:  experimental data from a lab flume was used. Dimensional analysis identified key parameters affecting energy dissipation. Sensitivity analysis via the Gamma Test selected the most influential inputs. These were used to train and compare three machine learning models: SVR, GEP, and ANN.
Results and Discussion: the GEP model demonstrated superior performance, achieving the highest R² (0.936) and lowest errors (RMSE=0.003) in predicting energy dissipation. It outperformed both ANN and SVR. Sensitivity analysis identified four key hydraulic parameters as the most influential inputs.
Conclusions: the study conclusively found the Gene Expression Programming (GEP) model to be the most accurate and reliable for predicting energy dissipation over gabion sills, significantly outperforming ANN and SVR. The four key hydraulic parameters identified were crucial for model success, demonstrating the effectiveness of this machine learning approach.

کلیدواژه‌ها

Artificial Intelligence
Energy Loss
Sensitivity Analysis
Performance Assessment

عنوان مقاله English

Machine Learning models for High-Accuracy Prediction of Energy Dissipation Through Gabion Sills Downstream of Spillways

نویسندگان English

Shahram Shakeri yousefi 1
Mohsen Najarchi 1
Mehdi Fuladipanah 2
Mahmood Rabani Bidgoli 3
1 Department of Civil Engineering, Ar. C., Islamic Azad University, Arak, Iran.
2 Department of Civil Engineering Ramh. C., Islamic AzadUniversity,Ramhormoz, Iran.
3 Department of Civil Engineering, Jasb. C., Islamic Azad University, Jasb, Iran.
چکیده English

This study evaluates the energy dissipation efficiency of gabion structures positioned downstream of spillways by employing three machine learning models (MLMs): Support Vector Regression (SVR), Gene Expression Programming (GEP), and Artificial Neural Network (ANN). Utilizing 155 laboratory-derived datasets, the models were trained (70%) and tested (30%) to predict energy dissipation performance under varying hydraulic conditions. GEP emerged as the most accurate model, achieving exceptional training-phase metrics (RMSE=0.00308, MAE=0.00250, R²=0.93648), closely followed by ANN, while SVR lagged in predictive capability. During testing, GEP maintained its superiority, reinforcing its robustness, with ANN remaining competitive and SVR continuing to underperform. Sensitivity analysis via the Γ-test identified dimensionless parameters- relative tailwater depth ("y" _"2" /"y" _"1" ), gabion height-to-upstream flow depth ratio ("h" /"y" _"1" ), aggregate size-to-upstream flow depth ratio ("d" /"y" _"1" ), inflow Froude number (Fr₁)- as critical drivers of energy dissipation. These findings underscore the efficacy of evolutionary algorithms like GEP in capturing complex hydraulic interactions, attributed to their ability to evolve interpretable mathematical expressions. ANN, though less interpretable, proved a reliable alternative, while SVR’s limitations in handling nonlinear relationships were evident. The study highlights the potential of MLMs, particularly GEP, to enhance spillway design by optimizing energy dissipation, reducing erosion risks, and improving infrastructure resilience. Future work could explore hybrid models, larger datasets, and field validations to refine and broaden applicability in hydraulic engineering practice.

کلیدواژه‌ها English

Artificial Intelligence
Energy Loss
Sensitivity Analysis
Performance Assessment
Ahmadzadeh-Kaleybar, F., Shahmohammadi Kalalagh, S., Fard Moradinia, S. 2024. Simulating of Changes in Water Distribution Uniformity Coefficient in Classic Stationary Sprinkler Irrigation Using Data-Mining Models. Journal of New Approaches in Water Engineering and Environment, 3(2), 118-135. Doi: 10.22034/nawee.2024.471274.1100.
Alsubih, M., Ahmed, M., Alqadhi, S., Mallick, J. 2023. Gabion water barrier structures as a sustainable approach to water and land conservation. Environmental Science and Pollution Research, 30(60):126057-126071. DOI: 10.1007/s11356-023-31040-3.
Azamathulla, H.M., Cuan, Y.C., Ghani, A.A., Chang, C.K., 2013. Suspended sediment load prediction of river systems: GEP approach. Arabian Journal of Geosciences, 6, 3469-3480.DOI: 10.1007/s12517-012-0608-4.
Azmathullah, H.M., Deo, M.C. and Deolalikar, P.B. 2005. Neural networks for estimation of scour downstream of a ski-jump bucket. Journal of Hydraulic Engineering, 131(10): 898-908. https://doi.org/10.1061/(ASCE)0733-9429(2005)131:10(898).
Bagheri Khaneghahi,M. , Hezarjaribi,A. , Kamali,M. I. and Zamani,F. 2025. Evaluating the accuracy of AquaCrop 7.1 crop model and investigating the effect of changing the planting date on the performance of rainfed wheat in different climates of Iran. Journal of New Approaches in Water Engineering and Environment, 4(1), 129-144. Doi: 10.22034/nawee.2025.493925.1122.
Daneshfaraz, R., Majedi Asl, M., Bagherzadeh, M. 2021. Experimental Investigation of the Energy Dissipation and the Downstream Relative Depth of Pool in the Sloped Gabion Drop and the Sloped Simple Drop. Amirkabir Journal of Civil Engineering, 53(9):3665-36778. DOI: 10.22060/ceej.2020.18059.6751. 
Daneshfaraz, R., Majedi-Asl, M., Mortazavi, S., Bagherzadeh, M. 2022. Laboratory evaluation of energy dissipation in the combined structure of the vertical drop with gabion. Civil Infrastructure Researches, 8(1):145-157. DOI:10.22091/cer.2022.7720.1344 . 
Ferreira, C. 2001. Algorithm for solving gene expression programming: a new adaptive problem. Complex Systems, 13(2), pp. 87-129. https://doi.org/10.48550/arXiv.cs/0102027.
Fuladipanah, M., Jafarinia, R. 2011. The Derivation of Energy Dissipation Equation for Adverse-Slopped Stepped Spillway. World Applied Science Journal, 15(5): 637-642.
Fuladipanah, M., Hazi, M. A., Kisi, O. 2023. An in-depth comparative analysis of data-driven and classic regression models for scour depth prediction around cylindrical bridge piers. Applied Water Science, 13(12), p. 231. https://doi.org/10.1007/s13201-023-02022-0.
Fuladipanah, M., Shahhosseini, A., Rathnayake, N., Azamathulla, H.M., Rathnayake, U., Meddage, D.P.P., Tota-Maharaj, K. 2024. In-depth simulation of rainfall–runoff relationships using machine learning methods. Water Practice & Technology, 19(6), pp. 2442-2459. https://doi.org/10.2166/wpt.2024.147.
Hussain, A., Ansari, M.A., Ahmed, M.N., Ahmad, F., Jahangeer, J. 2022. Model development for energy dissipation over gabion stepped weirs using GEP and GMDH techniques. Canadian Journal of Civil Engineering, 49(6): 969-979. DOI: 10.1139/cjce-2021-0197.
Iranpour,A. , Egdernezhad,A., Heidarnejad,M. 2024. Numerical Investigation of Energy Dissipation in Baffled Piano Key Weirs. Journal of New Approaches in Water Engineering and Environment, 3(1): 55-70. Doi: 10.22034/nawee.2024.451817.1069.
Kheyraei, M., Fathi Moghaddam, M. 2016. Hydraulic Characteristics of the Crump Gabion Weirs for Free Flow Conditions. Water Engineering, 9(29):75-86. DOI: 20.1001.1.20086377.1395.9.29.6.9
Mahjoubi, A., Kashefipour, S.M., 2023. Investigation the Energy Dissipation on Gabion Stepped Weirs and Downstream Hydraulic Jump Characteristics. Irrigation Sciences and Engineering, 46(1): 65-76. DOI: 10.22055/jise.2019.14393.
Mobayen, R., Najafzadeh, M., Farrahi-Moghaddam, K. 2023. Evaluation of Regression-Based Soft Computing Techniques for Estimating Energy Loss in Gabion Spillways. Journal of Environment and Water Engineering, 9(2):241-255. DOI: 10.22034/ewe.2022.329153.1724.
Naseri, R., KashefiPour, S.M. 2022. The Effect of Gabion Stepped Spillway Porosity on Energy Dissipation and Characteristics of Downstream Hydraulic Jump of Weir. Irrigation Sciences and Engineering, 45(1): 1-17. DOI: 10.22055/jise.2019.18454.1337.
Pourhosein Ghadi, M., Dehghani, A.A., Meftah Halghi, M. 2022. Effect of different hydraulic conditions on the hyporheic flow characteristics around gabion weir structures. Iranian Journal of Eco Hydrology, 9(1): 15-33. DOI: 10.22059/ije.2022.329091.1539. 
Razi, S., Salmasi, F., Hoseinzade Dalir, A. 2019. Laboratory Study of the Effects of Step Number, Slope and Particle Size on Energy Dissipation in Gabion Stepped Spillways. Amirkabir Journal of Civil Engineering, 51(4): 749-756. DOI: 10.22060/ceej.2018.13984.5527.
Salehi, S., Esmaili, S.A., Sadeghi-Namaghi, N., Esmaili, K. 2022. Overflow and underflow within the broad-crested gabion weir in free flow with sand bed conditions. Sharif Journal Civil Engineering, 37(4): 3-13. DOI: 10.24200/j30.2021.57425.2907.
Srinivas, R., Tiwari, N.K. 2022. Oxygen aeration efficiency of gabion spillway by soft computing models. Water Quality Research Journal, 57(3):215-232. https://doi.org/10.2166/wqrj.2022.009.
Vapnik, V. 1995. The Nature of Statistical Learning Theory. Springer-Verlag. New York.
Zuhaira, A.A., Al-Hamd, R.K.S., Alzabeebee, S., Cunningham, L.S. 2021. Numerical investigation of skimming flow characteristics over non-uniform gabion-stepped spillways. Innovative Infrastructure Solutions, 6,1-19. DOI: 10.1007/s41062-021-00579-w.
رویکردهای نوین در مهندسی آب و محیط‌زیست
دوره 4، شماره 2
مهر 1404
صفحه 91-106

صفحه اصلی

راهنمای نویسندگان

ارسال مقاله

داوران

تماس با ما