Hydrophysics

Hydrophysics

The Potential of the Hybrid Support Vector Regression Model for Predicting River Sediment Discharge (Case Study: Keshkan-Lorestan River)

Document Type : Original Article

Authors
Hamidreza Babaali 1
Ebrahim Nohani 2
Reza Dehghani 3
1 Associate Professor , Department of Civil Engineering, Islamic Azad University, Khorramabad branch, Lorestan
2 Assistant Professor, Department of Civil Engineering, Materials and Energy Research Center, Dezful Branch, Islamic Azad University, Dezful, Iran.
3 PhD in Water Sciences and Engineering, Department of Soil Conservation and Watershed Management, Lorestan Province Agriculture and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization, Khorramab
Abstract
Providing a robust and reliable predictive model for river sediment discharge is an essential task for several environmental and geomorphological perspectives, including water quality, riverbed engineering sustainability, and aquatic habitats. In this research, a new hybrid intelligent approach based on the support vector regression model approach has been developed to predict river sediment discharge. For this purpose, in this research, two optimization algorithms including firefly and gray wolf were used to model the sediment discharge of the river. In order to model, the statistics and information of the Kashkan river hydrometric station located in Lorestan province were used as a case study in 7 combined scenarios of input parameters in 1403-1373. In order to evaluate the performance of the models, the evaluation criteria of correlation coefficient, root mean square error, average absolute value of error, and Nash Sutcliffe coefficient were used. The results showed that the combined scenarios in the studied models improved the performance of the model. Also, the results of the evaluation criteria showed that the support vector regression model-firefly has a correlation coefficient of 0.970, the root mean error rate (ton/day) is 0.145, the mean absolute error value (ton/day) is 0.080 and the coefficient Nash Sutcliffe has 0.980 in the validation stage. In total, the results showed that the use of intelligent models based on the support vector regression approach can be an effective approach in the sustainability of river engineering.
Keywords
Kashkan
support vector regression
suspended sediments
modeling

Subjects

  1. Sivakumar B, Jayawardena AW. An investigation of the presence of low-dimensional chaotic behaviour in the sediment transport phenomenon. Hydrological Sciences Journal. 2002 Jun 1;47(3):405-16. https://doi.org/10.1080/02626660209492943
  2. Chang HH. River morphology and river channel changes. Transactions of Tianjin University. 2008 Aug;14:254-62. https://doi.org/10.1007/s12209-008-0045-3
  3. Martinez JM, Guyot JL, Filizola N, Sondag F. Increase in suspended sediment discharge of the Amazon River assessed by monitoring network and satellite data. Catena.2009; 79(1): 257–64. https://doi.org/10.1016/j.catena.2009.05.011
  4. Frings RM, Kleinhans MG. Complex variations in sediment transport at three large river bifurcations during discharge waves in the river Rhine. Sedimentology.2008; 55(2): 1145–71. https://doi.org/10.1111/j.1365-3091.2007.00940.x.
  5. Yaseenm ZM, El-Shafie  A, Jaafar  O, Afan HA, Sayl KN. Artificial intelligence based models for stream-flow forecasting: 2000–2015. Journal od Hydrology.2015; 530(3): 829–44. https://doi.org/10.1016/j.jhydrol.2015.10.038
  6. Kisi O, Sanikhani H, Zounemat-Kermani M, Niazi F. Long-term monthly evapotranspiration modeling by several data-driven methods without climatic data. Computers and Electronics in Agriculture.2015; 115(1): 66–77. https://doi.org/10.1016/j.compag.2015.04. 015
  7. Yaseen ZM, Ebtehaj I, Bonakdari H, Deo RC, Mehr AD, Mohtar WHMW, Diop L, El-shafie A, Singh VP. Novel approach for streamflow forecasting using a hybrid ANFIS-FFA model. Journal of 2017a; 554(2): 263–76.
  8. ثاقبیان سید مهدی. تخمین بار معلق رسوبی با استفاده از روش‌های هوشمند تلفیقی با در نظر گرفتن عدم قطعیت مدل. نشریه آب‌وخاک. 1400؛ 35(4):488-475.
  9. مرادی‌نژاد امیر. مدل‌سازی برآورد میزان رسوب معلق رودخانه با استفاده از رگرسیون بردار پشتیبان و روش گروهی کنترل داده‌ها. نشریه دانش آب‌وخاک. 1403؛ 34(2):222-203.
  10. Asadi M, Fathzadeh A, Kerry R, Ebrahimi-Khushfi Z, Taghizadeh-Mehrjardi R. Prediction of river suspended sediment load using machine learning models and geo-morphometric parameters. Arabian Journal of Geosciences.2021;14(3):1-14
  11. Dashti Latif S, Chong KL, Najah Ahmed A, Huang YF, Sherif M, El-Shafie A.Sediment load prediction in Johor river: deep learning versus machine learning models. Applied Water Science. 2023;13(4):1-15
  12. Vapnik VN. The nature of statistical learning theory. Springer, New York.1995; 3(1):250-320.
  13. Vapnik VN. Statistical learning theory. Wiley, New York, 1998; 4(1): 250-320.
  14. Vapnik V, Chervonenkis A. The necessary and sufficient conditions for consistency in the empirical risk minimization method. Pattern Recognition and Image Analysis,1991;1(3): 283-305.
  15. Basak D, Pal S, Patranabis DC. Support vector regression. Neural Information Processing-Letters and Reviews. 2007 Oct;11(10):203-24.
  16. Ostu N. A Threshold Selection Method from Gray-Level Histograms [J]. IEEE Transactions on Systems Man and Cybernetics.1979; 9 (1): 62-6.
  17. Yang XS. Firefly algorithm, nature-inspired meta-heuristic algorithms. Wiley Online Libr.2008;20:79–90.
  18. Yan X, Zhu Y, Wu J, Chen H. An improved firefly algorithm with adaptive strategies. Advanced Science Letters. 2012 Sep 1;16(1):249-54.
  19. Nagy H, Watanabe K, Hirano M. Prediction of sediment load concentration in rivers using artificial neural network model. Journal of Hydraulics Engineering.2002; 128: 558-59.
  20. Kisi O, Karahan ME, Şen Z. River suspended sediment modelling using a fuzzy logic approach. Hydrological Processes: An International Journal. 2006 Dec 30;20(20):4351-62.
  21. Dehghani R, Torabi Poudeh H, Younesi H, Shahinejad B. Daily Streamflow Prediction Using Support Vector Machine-Artificial Flora (SVM-AF) Hybrid Model. Acta Geophysica. 2020;68(6):51-66. https://doi.org/10.1007/s11600-020-00472-7
  22. Dehghani R, Torabi H. Dissolved oxygen concentration predictions for running waters with using hybrid machine learning techniques. Modeling Earth Systems and Environment.2021;6(2):64-78. https://doi.org/10.1007/s40808-021-01253-x
  23. Zeidalinejad N, Dehghani R. Use of meta-heuristic approach in the estimation of aquifer's response to climate change under shared socioeconomic pathways. Groundwater for Sustainable Development.2023;20(4):112-132. https://doi.org/10.1016/j.gsd.2022.100882
  24. Dehghani R, Babaali H. Evaluation of Statistical Models and Modern Hybrid Artificial Intelligence in Simulation of Runoff Precipitation Process. Sustainable Water Resources Management.2002; 8: 154-72. https://doi.org/10.1007/s40899-022-00743-9.
Hydrophysics
Volume 9, Issue 2 - Serial Number 17
February 2024
Pages 15-25

  • Receive Date 11 November 2024
  • Revise Date 18 November 2024
  • Accept Date 30 November 2024