Iranian Journal of Irrigation & Drainage

Iranian Journal of Irrigation & Drainage

Performance Evaluation of Machine Learning Models Based on the Variable Mode Decomposition (VMD) Method in River Flow Estimation (Case Study: Dez River)

Document Type : Original Article

Authors
Nazanin Alivand 1
Ali Mohammad Akhoond-Ali 2
Farshad Ahmadi 3
1 Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz.
2 Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz.
3 Shahid Chamran university of Ahvaz
Abstract
In the present study, the monthly flow of the Dez River at the Taleh Zang station during the statistical period from 1971 to 2022 was modeled using a hybrid approach based on the Variational Mode Decomposition (VMD) signal decomposition method. The input data for the Random Forest (RF) and Support Vector Machine (SVM) models were defined based on three scenarios. In the first scenario, inputs included lagged flow data with delays of 1 to 4 months. In the second scenario, linear and nonlinear periodic terms were added to the lagged flow data as additional inputs. In the third scenario, the input data were decomposed into sub-series called Intrinsic Mode Functions (IMFs) using the VMD method before being fed into the models. The results revealed that each standalone model achieved maximum accuracy with different input patterns, but adding periodic terms moderately improved their performance. The SVM model in the second scenario showed the best performance, with a mean RMSE error of 156.83 m³/s. For the RF model, the mean error in the second scenario (162.99 m³/s) was lower than in the first scenario. In the third step, the data were decomposed using VMD, and modeling was performed with RF and SVM. Evaluation metrics indicated a significant reduction in error and improved accuracy in the hybrid models. Specifically, the VMD-SVM model reduced the RMSE by an average of 121 m³/s and outperformed the VMD-RF model in terms of precision.
Keywords
Signal Decomposition
Intrinsic Mode Functions (IMFs)
Decomposition Level
Central Frequency
احمدی، ف. 1399. ارزیابی عملکرد روش­های ماشین بردار پشتیبان و سیستم استنتاج عصبی فازی تطبیقی در پیش­بینی جریان ماهانه رودخانه­ها (مطالعه موردی: رودخانه­های نازلو و سزار). تحقیقات آب و خاک ایران. 51(3): 686-673.
احمدی، ف. 1400. بررسی کارایی روش‌های پیش­پردازش داده‌ها در بهبود عملکرد مدل برنامه ریزی بیان ژن (مطالعه موردی: رودخانه آب زال. آب و خاک. 35(2): 153-165.
باقرپور، م.، سیدیان، س.م.، فتح‌آبادی، ا.، محمدی، ا. 1397. پیش­بینی رواناب با استفاده از مدل­های جعبه سیاه و خاکستری. تحقیقات منابع آب ایران. 14(5): 219-204.
خرمی­پور، ز.، ولیخان انارکی، م.،فرزین، س. 1403. رویکردی جدید در روندیابی سیلاب بر مبنای تلفیق تئوری بیز، ماشین بردار پشتیبان و الگوریتم بهینه‌سازی فراابتکاری. نشریه آبیاری و زهکشی ایران. 18(3): 420-409. 
دهقانی، ر.، ترابی پوده، ح.، یونسی، ح.ا.، شاهی نژاد، ب. 1400. کاربرد مدل هیبریدی ماشین بردار پشتیبان - موجک در تخمین جریان رودخانه­ها (مطالعه موردی: حوضه دز). نشریه علمی - پژوهشی مهندسی و مدیریت آبخیز. 13(1): 110-98.
موسی زاده، ن.، آخوندعلی، ع.م.، احمدی، ف. 1402. توسعه مدل­های تلفیقی یادگیری ماشین مبتنی بر روش تجزیه مد تجربی گروهی کامل در برآورد جریان ورودی به سد (مطالعه موردی: سد دز). نشریه آبیاری و زهکشی ایران. 4(17): 701-685.
 
Abda, Z., Zerouali, B., Chettih, M., Guimaraes Santos, C. A., de Farias, C. A. S., & Elbleltagi, A. 2022. Assessing machine learning models for streamflow estimation: a case study in Oued Sebaou watershed (Northern Algeria). Hydrological Sciences Journal. 67(9): 1328-1341.‏
Ahmadi, F., Mehdizadeh, S., & Nourani, V. 2022. Improving the performance of random forest for estimating monthly reservoir inflow via complete ensemble empirical mode decomposition and wavelet analysis. Stochastic Environmental Research and Risk Assessment. 36(9): 2753-2768.‏
Bishop, C. M., & Nasrabadi, N. M. 2006. Pattern recognition and machine learning (Vol. 4, No. 4, p. 738). New York: springer.
Breiman, L. 2001. Random forests. Machine Learning. 45(1) : 5-32.
Chollet, F. 2021. Deep Learning with Python (2nd ed.). Manning Publications.
Choubey, V., Mishra, S., & Pandey, S. K. 2014. Time series data mining in real time surface runoff forecasting through Support Vector Machine. International Journal of Computer Applications. 98(3):274-291.‏
Cutler, A., Cutler, D.R., & Stevens, J.R. 2012. Random forests. Pp. 157-175, In: Ensemble.
Doyle, J. M., Hill, R. A., Leibowitz, S. G., & Ebersole, J. L. 2023. Random forest models to estimate bankfull and low flow channel widths and depths across the conterminous United States. JAWRA Journal of the American Water Resources Association. 59(5): 1099-1114.
Dragomiretskiy, K., & Zosso, D. 2013. Variational mode decomposition. IEEE transactions on signal processing. 62(3): 531-544.‏
Essam, Y., Huang, Y. F., Ng, J. L., Birima, A. H., Ahmed, A. N., & El-Shafie, A. 2022. Predicting streamflow in Peninsular Malaysia using support vector machine and deep learning algorithms. Scientific Reports. 12(1): 38-83.‏
Fang, W., Huang, S., Ren, K., Huang, Q., Huang, G., Cheng, G., & Li, K. 2019. Examining the applicability of different sampling techniques in the development of decomposition-based streamflow forecasting models. Journal of Hydrology. 568: 534-550.‏
Fletcher, T. 2009. Support vector machines explained. Tutorial paper. 1118: 1-19.‏
Hamel, L. 2009 Knowledge Discovery with Support Vector Machines. Hoboken, N.J. John Wiley.
He, X., Luo, J., Zuo, G., & Xie, J. 2019. Daily runoff forecasting using a hybrid model based on variational mode decomposition and deep neural networks. Water resources management. 33(4): 1571-1590.
Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., Yen, N.C., Tung, C.C., & Liu, H. H. 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences. 454(1971): 903-995.
Idemudia, O., Ehiorobo, J. O., Izinyon, C. O., & Ilaboya, I. 2024. Evaluating the performance of random forest, decision tree, support vector regression and gradient boosting for streamflow prediction. CTU Journal of Innovation and Sustainable Development. 16(2): 116-130.‏
James, G., Witten, D., Hastie, T., & Tibshirani, R. 2021. An Introduction to Statistical Learning. Springer. 610p.
Lahmiri, S. 2015. Long memory in international financial markets trends and short movements during 2008 financial crisis based on variational mode decomposition and detrended fluctuation analysis. Physica A: Statistical Mechanics and its Applications. 437: 130-138.‏
Latifoğlu, L. 2022. A novel approach for prediction of daily streamflow discharge data using correlation based feature selection and random forest method. International Advanced Researches and Engineering Journal. 6(1): 1-7.‏
Li, B. J., Sun, G. L., Liu, Y., Wang, W. C., & Huang, X. D. 2022. Monthly Runoff Forecasting Using Variational Mode Decomposition Coupled with Gray Wolf Optimizer-Based Long Short-term Memory Neural Networks. Water Resources Management. 36(6): 2095-2115.
Mahmood, O. A., Sulaiman, S. O., & Al-Jumeily, D. 2024. Forecasting for Haditha reservoir inflow in the West of Iraq using Support Vector Machine (SVM). PloS one. 19(9): e0308266.‏
Mantero, P., Moser, G., & Serpico, S. B. 2005. Partially supervised classification of remote sensing images through SVM-based probability density estimation. IEEE Transactions on Geoscience and Remote Sensing. 43(3): 559-570.
Meng, E., Huang, S., Huang, Q., Fang, W., Wang, H., Leng, G., & Liang, H. 2021. A hybrid VMD-SVM model for practical streamflow prediction using an innovative input selection framework. Water Resources Management. 35: 1321-1337.‏
Sahoo, S. K., & Satapathy, D. P. 2025. An improved support vector machine model for groundwater level prediction: a case study. Earth Science Informatics. 18(1): 1-18.
Samantaray, S., & Sahoo, A. 2024. Prediction of flow discharge in Mahanadi River Basin, India, based on novel hybrid SVM approaches. Environment, Development and Sustainability. 26(7): 18699-18723.‏
Samantaray, S., Das, S. S., Sahoo, A., & Satapathy, D. P. 2022. Monthly runoff prediction at Baitarani River basin by support vector machine based on Salp swarm algorithm. Ain Shams Engineering Journal. 13(5): 101732.‏
Sharma, B., & Goel, N. K. 2024. Streamflow prediction using support vector regression machine learning model for Tehri Dam. Applied Water Science. 14(5): 1-20.‏
Torres, M. E., Colominas, M. A., Schlotthauer, G., & Flandrin, P. 2011. A complete ensemble empirical mode decomposition with adaptive noise. In 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4144-4147). IEEE.
Vapnik, V. 1995. The nature of statistical learning theory Springer. New York. 10: 978-1.‏
Vapnik, V. 1998. The support vector method of function estimation. In Nonlinear modeling: Advanced black-box techniques. Boston, MA: Springer US.‏
Wu, Z., & Huang, N. E. 2009. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in adaptive data analysis. 1(01): 1-41.
Iranian Journal of Irrigation & Drainage
Volume 19, Issue 3 - Serial Number 112
July and August 2025
Pages 423-437