Flood routing by the Muskingum Method and neural network

Öz

Floods have consistently been one of the most significant natural disasters affecting humans. In a country like Iran, their impact is particularly pronounced due to the irregular patterns of rainfall both in space and time. Flood routing is a crucial aspect of hydraulic engineering, as it enables the prediction of how floods will rise and recede at specific points along a river. Various techniques and methods are employed to address routing problems. This Manuscript explores routing using Muskingum's method, the least squares error method, and neural networks. First, three proposed neural network models with different transfer functions were evaluated to identify the best-performing model. The results were then compared using the least squares method and validated against the model proposed by Choudhury and Sankarasubramanian (2009). Ultimately, both models yielded acceptable results; however, considering the RMSE values, the least squares error method's results are closer to those proposed by Choudhury and Sankarasubramanian (2009).

Anahtar Kelimeler

• Flood routing
• Muskingum
• Least Squares Error
• Neural Network
• Transfer Function

Kaynakça

1. [1] Agami, N., Atiya, A., Saleh, M., El-Shishiny, H. (2009). A neural network based dynamic forecasting model for Trend Impact Analysis. Technological Forecasting and Social Change, 76(7), 952-962.
2. [2] Al-Humoud, J. M., Esen, I. I. (2006). Approximate Methods For The Estimation Of Muskingum Flood Routing Parameters. Water Resources Management, 20(6), 979-990.
3. [3] Choudhury, P., Sankarasubramanian, A. (2009). Ri-ver flood forecasting using complementary Muskin-gum rating equations. Journal of Hydrologic Enginee-ring, 14(7), 745-751.
4. [4] Chow, V. T., Maidment, D. R., and Mays, L. W. (1988). Applied hydrology, International Ed., McG-raw-Hill, New York.
5. [5] Chu, H.J., Chang, L.C. (2009). Applying particle swarm optimization to parameter estimation of the nonlinear Muskingum model. Journal of Hydrologic Engineering, 14(9), 1024-1027.
6. [6] Easa, S.M. (2013). Improved nonlinear Muskingum model with variable exponent parameter. Journal of Hydrologic Engineering, ASCE, 18(22), 1790-1794.
7. [7] Katipoğlu, O. M., Sarıgöl, M. (2023). Boosting flood routing prediction performance through a hybrid app-roach using empirical mode decomposition and neural networks: A case study of the Mera River in Ankara. Water Supply, 23(11), 4403-4415.
8. [8] Mirzazade, P. (2013). Investigation flood routing methods in river and reservoirs. M.Sc Thesis. Sista-nand Baluchestan University. Civil college. Sistan and Baluchestan province. Iran. 86 (in Persian).

9. [9] Moghaddam, A., Behmanesh, J., Farsijani, A. (2016). Parameters estimation for the new four-parameter nonlinear Muskingum model using the particle swarm optimization. Water resources management, 30, 2143-2160.
10. [10] Mohan, S. (1997). Parameter estimation of nonli-near Muskingum models using genetic algorithm. Journal of hydraulic engineering, 123(2), 137-142.
11. [11] Niazkar, M., Afzali, S.H. (2014). Assessment of modified honey bee mating optimization for para-meter estimation of nonlinear Muskingum models. Journal of Hydrologic Engineering, 20(4), p.04014055.
12. [12] Perumal, M. (1994). Hydrodynamic derivation of a variable parameter Muskingum method: 1. Theory and solution procedure. Hydrological sciences jour-nal, 39(5), 431-442.
13. [13] Sarıgöl, M. (2024). Evaluating the Accuracy of Machine Learning, Deep Learning and Hybrid Algo-rithms for Flood Routing Calculations. Pure and Applied Geophysics, 181(12), 3485-3506