Iranian Water Research Journal

Iranian Water Research Journal

Evaluation of a hybrid model for monthly runoff estimation using support vector machine based on variational mode decomposition with whale optimization algorithm (Mashhad basin)

Document Type : Original Article

Authors
Mohammadreza Fardirad 1
Khosro Hoseini 2
1 Department of Water Engineering, Civil Engineering Faculty, Semnan University, Semnan,Iran
2 Department of Water Engineering, Civil Engineering Faculty, Semnan University, Semnan, Iran
10.22034/iwrj.2025.15105.2665
Abstract
Introduction:
The water crisis has become one of the fundamental challenges of the modern era, exacerbated by factors such as population growth, climate change, and uneven rainfall distribution. Iran, with its arid and semi-arid climate, faces significant limitations in water resource management, which impacts agriculture and the economy. Accurate runoff prediction is essential for sustainable water resource management and the design of water infrastructures. However, the complexity of nonlinear relationships and irregular flow distributions makes runoff prediction challenging. Various approaches, including physical, conceptual, and data-driven models, have been proposed. Data-driven models, leveraging machine learning, are particularly notable for their ability to analyze large datasets and uncover hidden patterns. Despite challenges (such as selecting suitable algorithms, determining effective inputs, and evaluating estimation accuracy), these models have been widely applied in hydrology. The aim of this research was to improve monthly runoff prediction in Mashhad basin by utilizing advanced machine learning approaches. In this regard, Variable Mode Decomposition (VMD) was employed as a data preprocessing method, and the Whale Optimization Algorithm (WOA) was used to enhance model accuracy. These methods were applied with the goal of achieving more accurate and efficient predictions in this field.
Methods:
The study area of Mashhad basin, located in Khorasan Razavi Province, is bordered by Hezar Masjid heights to the north and the Binalod heights to the south, with the longitudes of 59˚30' to 59˚42' East and the latitudes of 36˚12' to 36˚24' North. Meteorological and hydrometric data were provided for four stations (Ardak Band, Zoshk, Alang asadi and Kartian), from 1968 to 2022. The stationarity and stability of the time series for rainfall, evaporation, temperature, and discharge were first analyzed. Two distinct modeling approaches were employed to estimate runoff for the future month. In the first approach, three different combinations of parameters were used as model inputs. In the first scenario, all parameters with a three-month lag, determined based on the correlation coefficient of rainfall, temperature, evaporation, and discharge, were utilized. For the second scenario, after conducting sensitivity analysis on the first scenario, seven of the most influential parameters were selected. In the third scenario, the effect of using discharge with a three-month lag as the sole model input was evaluated. The Support Vector Machine (SVM) model and Long Short-Term Memory (LSTM) neural network, both in their basic and optimized forms, were applied to the data from each of the four studied stations. The accuracy of the developed models was assessed using statistical indices, including the Nash–Sutcliffe Efficiency (NSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Normalized Root Mean Square Error (NRMSE). In the second approach, the Variational Mode Decomposition (VMD) technique and the Whale Optimization Algorithm (WOA) were employed. Using this approach, the discharge time series was decomposed into several sub-series, each of which, with a three-month lag, was used as an input to both the basic and optimized SVM and LSTM models. Finally, the performance of the developed models was evaluated during the training and testing phases.
Results
This study aimed to evaluate the performance of VMD-WOA-SVM-WOA hybrid model for runoff estimation at four stations within Mashhad study basin. In this study, two different approaches for modeling runoff were investigated. In the first method, data preprocessing was performed using normalization, the optimized LSTM and SVR models performed better than the base models; however, due to the structural complexity of the hydrological data, the models' ability to identify accurate patterns and estimate runoff was limited. In the second method, data preprocessing was performed using Variable Mode Decomposition. This technique allowed for the extraction of more accurate features by separating hydrological data into components with different frequencies. The primary approach involved using the Variational Mode Decomposition (VMD) method to decompose the runoff time series into modes and optimize their frequencies with the Whale Optimization Algorithm (WOA). These modes were then used as inputs to the Support Vector Machine (SVM) model to estimate runoff for the future month. To assess the proposed model, its performance was compared with a simple SVM model using different input configurations. The results demonstrated that the VMD-WOA-SVM-WOA model achieved mean RMSE and Nash–Sutcliffe 0.185 and 0.979, respectively, with the minimum input variables. These findings align with the principles of regression modeling, emphasizing simplicity and avoiding unnecessary complexity. Furthermore, the results confirmed that increasing the number of input variables does not necessarily enhance estimation accuracy and can even introduce noise and reduce the model's generalizability. This research showed that by employing data preprocessing (VMD) and optimizing model parameters with WOA, a simple, accurate, and interpretable model can be developed. Additionally, the proposed model is not only effective for runoff estimation but also has the potential to be applied to similar studies of hydrological processes such as evapotranspiration and sediment modeling in different regions.
Conclusion:
This study investigated two approaches for runoff modeling. The first approach used data normalization and application of optimized LSTM and SVR models, which showed some improvement compared to base models. However, due to the complexity of hydrological data, the models demonstrated limited accuracy, and the overall performance based on low Nash–Sutcliffe values was not satisfactory. The second approach employed for processing, was Variational Mode Decomposition (VMD), which allowed better extraction of temporal features. With parameter optimization using the Whale Optimization Algorithm (WOA), the VMD-WOA-SVR-WOA model achieved significantly better accuracy and generalization. While VMD-WOA-LSTM also performed well, the superior results of VMD-WOA-SVR-WOA model highlighted it as an effective tool for runoff prediction and water resource management.
Keywords
Rainfall-Runoff Modeling
Support Vector Regression
Signal Processing
Optimization
1- Araghinejad, S. and Karamouz, M. 2005. Long-Lead Streamflow Forecasting using Artificial Neural Networks and Fuzzy Inference System. Iran-Water Resources Research, 1(2), pp. 29–41. (In Persian).
 
2- Bagherpour, B., Seyedian, S.M., Fatabadi, A. and Mohammadi, A. 2019. Runoff Prediction Using Black and Gray Box Models. Iran-Water Resources Research, 14(5), pp. 177–192. (In Persian).
 
3- Cortes, C. and Vapnik, V. 1995. Support-vector networks. Machine Learning, 20(3), pp. 273–297. https://doi.org/10.1007/BF00994018
 
4- Davanlou Tajbakhsh, A., Nourani, V. and Molajou, A. 2019. Hybrid Wavelet-M5 Model Application in Rainfall-Runoff Process Forecast (Case study: Aji Chay Catchment). Iran-Water Resources Research, 15(2), pp. 1–10. (In Persian).
 
5- Dragomiretskiy, K. and Zosso, D. 2014. Variational Mode Decomposition. IEEE Transactions on Signal Processing, 62(3), pp. 531–544. https://doi.org/10.1109/TSP.2013.2288675
 
6- Dunyaei, A., Saraf, A. and Ahmadi, H. 2020. Evaluation of the algorithms of the whale, magpie and cuckoo whales in optimizing the multi-objective use of the reservoir Golestan dam based on multi-criteria decision making method. Journal of Water Resources Engineering, 13(4), pp. 85–100. (In Persian).
 
7- Feng, Z., Niu, W., Tang, Z., Jiang, Z., Xu, Y., Liu, Y. and Zhang, H. 2020. Monthly runoff time series prediction by variational mode decomposition and support vector machine based on quantum-behaved particle swarm optimization. Journal of Hydrology, 583, p. 124627. https://doi.org/10.1016/j.jhydrol.2020.124627
 
8- Ghahraman, B. 2013. Performance of some Different Methods of Computing Hurst Exponent for Climatological Time Series. Journal of Water and Soil, 27(4), pp. 850–859. (In Persian).
 
9- Guo, S., Wen, Y., Zhang, X. and Chen, H. 2023. Monthly runoff prediction using the VMD-LSTM-Transformer hybrid model: a case study of the Miyun Reservoir in Beijing. Journal of Water and Climate Change, 14(9), pp. 3221–3236. https://doi.org/10.2166/wcc.2023.257
 
10-              Hochreiter, S. and Schmidhuber, J. 1997. Long Short-Term Memory. Neural Computation, 9(8), pp. 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
 
11-              Kavusi, M. and Khozeymeh Nejad, H. 2020. Review and compare performance of 4 modeling methods LS-SVM, NN, GEP and ANFIS-PSO in Simulation of Rainfall - Runoff (Study Area: Halil River - Jiroft Dam). Scientific Research Journal of Irrigation and Water Engineering of Iran, 43. (In Persian).
 
12-              Kumar, V., Kedam, N., Sharma, K.V., Mehta, D.J. and Caloiero, T. 2023. Advanced Machine Learning Techniques to Improve Hydrological Prediction: A Comparative Analysis of Streamflow Prediction Models. Water, 15(14), p. 2572. https://doi.org/10.3390/w15142572
 
13-              Merufinia, E., Sharafati, A., Abghari, H. and Hassanzadeh, Y. 2023. Performance evaluation of ANN-WOA and ANN-BWO simulation-optimization methods in predicting daily runoff (case study: Jelogir station in Karkheh watershed). Irrigation Sciences and Engineering (JISE), 47, pp. 19–36. (In Persian).
 
14- Mirjalili, S. and Lewis, A. 2016. The Whale Optimization Algorithm. Advances in Engineering Software, 95, pp. 51–67. https://doi.org/10.1016/j.advengsoft.2016.01.008
 
15- Said, S.E. and Dickey, D.A. 1984. Testing for Unit Roots in Autoregressive-Moving Average Models of Unknown Order. Biometrika, 71(3), p. 599. https://doi.org/10.2307/2336570
 
16-     Sayed, B.T., Al-Mohair, H.K., Alkhayyat, A., Ramírez-Coronel, A.A. and Elsahabi, M. 2023. Comparing machine-learning-based black box techniques and white box models to predict rainfall-runoff in a northern area of Iraq, the Little Khabur River. Water Science and Technology, 87(3), pp. 812–822. https://doi.org/10.2166/wst.2023.014
 
17-              Shafeizadeh, M., Fathian, H. and Nikbakht Shahbazi, A.R. 2019. Continuous Rainfall-Runoff Simulation by Artificial Neural Networks Based on Selection of Effective Input Variables Using Partial Mutual Information (PMI) Algorithm. Iran-Water Resources Research, 15, pp. 144–161. (In Persian).
 
18-              Tang, W., Pei, Y., Zheng, H., Zhao, Y., Shu, L. and Zhang, H. 2022. Twenty years of China’s water pollution control: Experiences and challenges. Chemosphere, 295, p. 133875. https://doi.org/10.1016/j.chemosphere.2022.133875
 
19-              Taormina, R. and Chau, K.-W. 2015. Data-driven input variable selection for rainfall–runoff modeling using binary-coded particle swarm optimization and Extreme Learning Machines. Journal of Hydrology, 529, pp. 1617–1632. https://doi.org/10.1016/j.jhydrol.2015.08.022
 
20-              Tikhamarine, Y., Souag-Gamane, D., Ahmed, A.N., Sammen, S.S., Kisi, O., Huang, Y.F. and El-Shafie, A. 2020. Rainfall-runoff modelling using improved machine learning methods: Harris hawks optimizer vs. particle swarm optimization. Journal of Hydrology, 589, p. 125133. https://doi.org/10.1016/j.jhydrol.2020.125133
 
21-              Van Houdt, G., Mosquera, C. and Nápoles, G. 2020. A review on the long short-term memory model. Artificial Intelligence Review, 53(8), pp. 5929–5955. https://doi.org/10.1007/s10462-020-09838-1
 
22-              Xu, D., Li, Z. and Wang, W. 2024. An ensemble model for monthly runoff prediction using least squares support vector machine based on variational modal decomposition with dung beetle optimization algorithm and error correction strategy. Journal of Hydrology, 629, p. 130558. https://doi.org/10.1016/j.jhydrol.2023.130558
 
23-              Yao, Z., Wang, Z., Wang, D., Wu, J. and Chen, L. 2023. An ensemble CNN-LSTM and GRU adaptive weighting model based improved sparrow search algorithm for predicting runoff using historical meteorological and runoff data as input. Journal of Hydrology, 625, p. 129977. https://doi.org/10.1016/j.jhydrol.2023.129977
 
24-              Yousefi, A., Ghafoori, M. and Lashkaripour, G. 2007. Investigation of clay minerals in the subgrade soil of Mashhad city considering their Atterberg limits. Paper presented at the Iranian Conference on Engineering Geology and the Environment, Tehran, Iran, 22 July 2007. (In Persian).
 
25- Zhang, J., Chen, X., Khan, A., Zhang, Y., Kuang, X., Liang, X., Taccari, M.L. and Nuttall, J. 2021. Daily runoff forecasting by deep recursive neural network. Journal of Hydrology, 596, p. 126067. https://doi.org/10.1016/j.jhydrol.2021.126067
 

  • Receive Date 06 February 2025
  • Accept Date 22 March 2025
  • Publish Date 22 June 2025