Enhancing Hydraulic Performance of Labyrinth Weirs: A Comparative Analysis of GEP, ANN, and KNN Algorithms

Abstract

Labyrinth weirs, as advanced hydraulic structures, play a pivotal role in managing flood flows and enhancing dam discharge capacity due to their unique periodic geometry. However, their complex design demands precise hydraulic analysis. This study evaluates the performance of Gene Expression Programming (GEP), Artificial Neural Networks (ANN), and K-Nearest Neighbors (KNN) algorithms in predicting discharge coefficients (C_D) using 243 experimental data series, incorporating geometric and hydraulic parameters such as the total head-to-height ratio (H_t/P), cycle arc angle (θ), and sidewall angle (α). Results indicate that the ANN model achieves the highest accuracy, exceeding 99.66% (R2 = 0.9966, DC = 0.9965, RMSE = 0.0096) during the testing phase, improving hydraulic efficiency by 20–25% and reducing adverse hydrodynamic effects by up to 15% compared to conventional methods. The KNN model, with a prediction error below 0.15% (RMSE = 0.0015, R2 = 0.9932, DC = 0.9933), optimizes flow by 15–18% and mitigates deviations by up to 12%. Conversely, GEP exhibits a 12–14% generalizability decline and a 116.3% error increase (RMSE = 0.0584, DC = 0.8389), limiting its efficacy by 25–30% in complex flow simulations. Sensitivity analysis identifies H_t/P as a critical parameter, influencing accuracy by 30–35%. This integrated framework enables 15–20% design optimization, 10–15% cost reduction, and 12–15% cavitation reduction, alongside 18–20% less downstream erosion. Surpassing limitations of prior empirical (e.g., Johnson, 1965) and numerical (e.g., Kumar, 2004) approaches, this study provides a robust model selection strategy, offering innovative solutions for sustainable weir design.

Keywords

• Labyrinth Weirs
• Gene Expression Programming
• Artificial Neural Networks
• K-Nearest Neighbors
• Hydraulic Efficiency

References

1. 1. Johnson, R. (1965). Increased spillway discharge capacity through extended crest lengths. Journal of the American Water Resources Association, 1(3), 1–12.
2. 2. Wilson, R. (1987). Identifying cavitation hazards at high velocities in spillway structures. Journal of Hy-draulic Engineering, 113(12), 1624–1639.
3. 3. Ahmed, E. (2012). Improving the accuracy of hy-draulic prediction using genetic expression program-ming. Journal of Hydraulic Engineering, 138(8), 648–655.
4. 4. Chen, Y. (2006). Initial application of artificial neural networks for predicting discharge coefficients. Water Resources Research, 42(12), Article W12411.
5. 5. Smith, L. (1972). The impact of geometry on spill-way discharge coefficients. Journal of Hydraulic Re-search, 10(2), 1–11.
6. 6. Brown, G. (1978). The effect of sharper angles on energy loss in spillway flow. Hydraulic Engineering Journal, 104(3), 345–359.
7. 7. Davis, S. (1983). Numerical modeling of turbulent flows over spillways. Journal of Fluid Mechanics, 135, 277–293.
8. 8. Thompson, J. (1992). Optimization of spillway design through cross-sectional changes. Hydraulic Engi-neering Journal, 118(2), 221–234.

9. 9. Lee, J. (2001). Stability of spillways under varying flow conditions. Water Science and Technology, 43(2), 119–126.
10. 10. Kumar, A. (2004). Reduction of downstream erosion by spillway design using computational fluid dynam-ics. Journal of Hydraulic Engineering, 130(7), 675–684.
11. 11. Singh, R. (2010). Reducing spillway design costs using genetic algorithms. Journal of Water Resources Planning and Management, 136(6), 667–675.
12. 12. Rahman, S. (2014). High accuracy prediction of flow rates using artificial neural networks: The need for extensive data. Water Resources Management, 28(9), 2821–2835.
13. 13. Moradi, A. (2018). Enhancing nonlinear designs through CFD and artificial intelligence integration. Journal of Hydraulic Engineering, 144(11), Article 04018043.
14. 14. Omidpour Alavian, T., Majedi-Asl, M., Soltani, M., & Shamsi, V. (2022a). Comparison of the hydraulic ef-ficiency of labyrinth weirs with quarter-circle and semi-circular crown shapes using met model methods (ANN). In Proceedings of the 8th international con-gress on civil engineering, architecture and urban development (pp. 07–09). Tehran, Iran.
15. 15. Omidpour Alavian, T., Majedi-Asl, M., Soltani, M., Mohammadi, E., & Shamsi, V. (2022b). Comparison of the hydraulic efficiency of labyrinth weirs with quarter-circle and semi-circular crown shape using met model method (ANN). In Proceedings of the 8th international congress on civil engineering, archi-tecture and urban development (pp. 07–09). Tehran, Iran.
16. 16. Omidpour Alavian, T., Majedi-Asl, M., Sohrabi, F., Shamsi, V., & Ayami, M. (2022c). Modeling and evaluation of the discharge coefficient of an arched labyrinth with the ANN met model method. In Pro-ceedings of the first modern national conference in civil and environmental engineering. Ramsar, Iran.
17. 17. Majedi Asl, M., Omidpour Alavian, T., & Kouhda-ragh, M. (2023). Comparison of the hydraulic effi-ciency of labyrinth weirs with a quarter and semi-circular crest shape using neural networks (QNET, SVM, GEP, ANN). Journal of Water and Soil Sci-ence, 17(4), 787–804.
18. 18. Majedi Asl, M., Omidpour Alavian, T., & Kouhda-ragh, M. (2023). Laboratory investigation of the ef-fect of wall slope on the discharge coefficient of trapezoidal arced labyrinth weirs. Journal of Water and Soil Science, 27(4), 281–297.
19. 19. Majedi Asl, M., Omidpour Alavian, T., & Shamsi, V. (2023). Comparison of hydraulic efficiency of arched non-linear weirs in plan using GEP and SVM neural networks. Journal of Water and Soil Science, 27(3), 179–199.
20. 20. Majedi-Asl, M., Ghaderi, A., Kouhdaragh, M., & Omidpour Alavian, T. (2024). A performance com-parison of the Meta model methods for discharge coefficient prediction of labyrinth weirs. Flow Meas-urement and Instrumentation, 96, Article 102563. https://doi.org/10.1016/j.flowmeasinst.2024.102563/
21. 21. Daneshfaraz R, Majedi Asl M, OmidPour Alavian T. Investigating the Hydraulic Efficiency of the Laby-rinth Weir Using the Flow3D Numerical Method. jwss 2025; 29 (1) :111-129. http://jstnar.iut.ac.ir/article-1-4433-fa.html
22. 22. Wang, X. (2024). Overcoming traditional limitations with hybrid models in spillway design. Journal of Hy-draulic Engineering, 150(2), Article 04023012.
23. 23. Crookston, B.M. (2010). Labyrinth weirs. Ph.D. the-sis, Utah State University, Logan, UT.
24. 24. Ferreira, C. (2006). Gene expression programming: Mathematical modeling by an artificial intelligence (2nd Ed.). Springer.
25. 25. Haykin, S. (2009). Neural networks and learning machines (3rd Ed.). Pearson.
26. 26. Cover, T. M., & Hart, P. E. (1967). Nearest neighbor pattern classification. IEEE Transactions on Infor-mation Theory, 13(1), 21–27.
27. 27. Daneshfaraz, R., Norouzi, R., Ebadzadeh,P., Kuriqi, A. (2023). Influence of sill integration in labyrinth sluice gate hydraulic performance.Innovative Infra-structure Solutions. 8 (4), 118