Prediction of Ferizi River-Flow Using Data-Driven Models

Document Type : Research

Authors

1 PhD Candidate, Department of Water Science and Engineering, Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

2 Ph.D. Candidate, Department of Range and Watershed management, Faculty of Natural Resource and Environment, Ferdowsi University of Mashhad, Mashhad, Iran

3 Associate Professor, Department of Water Science and Engineering, Faculty of Agriculture, Fasa University, Fasa, Iran

Abstract

Introduction and Objective
Rivers serve as crucial sources of freshwater on Earth, and precise prediction of river flows plays a vital role in effective water resource management. To address this need, researchers have proposed various models. These models can be categorized into two types: (1) hydrological/hydraulic physically based models and (2) data-driven models. The cited papers provide evidence of the significance of employing data-driven models for hydrological issues, particularly in predicting river discharge.
Materials and Methods
In this study, the researchers utilized a gene expression programming model (GEP) and support vector machine (SVM) to predict the discharge of the Ferizi River. The dataset used in the study covered a period of ten years (2011-2020) and consisted of daily Ferizi river discharge readings obtained from the Moushang hydrometry station. The study area had an average altitude of 2171 meters above sea level, with a longitude range of 58° 49' 30" to 59° 4' 30" E and a latitude range of 36° 20' 1" to 36° 32' 1". For the prediction models, daily river discharge data from 1 to 5 days ahead were utilized as input variables for both the GEP and SVM models. To ensure data homogeneity and address any deficiencies, the researchers employed the run test and calculated the correlation coefficient between neighboring stations. Subsequently, the dataset was randomly divided into two groups: 80% for model training and 20% for model testing, as well as evaluating the modeling error. The performance of the models was assessed during the training and validation stages using various evaluation metrics, including root mean square error (RMSE), coefficient of correlation (R), bias, Kling Gupta (KGE), and Nash–Sutcliffe model efficiency (NSE). Additionally, in order to estimate the inflow to the Ferizi River using the SVM model, three common types of kernel functions in hydrology were examined, namely linear kernel, polynomial, and radial basis functions.
Results and Discussion
Among the different functions considered, the radial basis function was selected due to its lower error compared to other functions when applied to the variables. The best input model, Model No. 5, incorporated previous flow variables with a delay of five time steps. In the training phase, both the GEP and SVM models exhibited the highest performance in forecasting the daily flow of Moshang station. The performance of the applied models suggests that SVM (RSME = 1.15, R = 0.985, NSE = 0.85, and KGE = 0.79) demonstrates higher precision in the validation stage for river discharge prediction compared to GEP (RSME = 1.65, R = 0.964, NSE = 0.78, and KGE = 0.69).
Conclusion and Suggestions 
This study has demonstrated that the utilization of soft computing techniques, such as SVM and GEP, is a powerful tool in predicting river flow. These techniques are capable of establishing a favorable relationship between input and output parameters, enabling accurate simulation of average and maximum daily flow.

Keywords

References

Abdollahi S, Raeisi J, Khalilianpour M, Ahmadi F, Kisi O. 2017. Daily mean stream flow prediction in perennial and non-perennial rivers using four data driven techniques. Water Resources Management. 31(15): 4855-4874. https://doi.org/10.1007/s11269-017-1782-7.
Ahmadi F, Radmanesh F, Mirabbasi R. 2016. Comparison between genetic programming and support vector machine methods for daily river flow forecasting (Case study: Barandoozchay River). Water and Soil. 28(6): 1162-1171. (In Persian). https://doi.org/10.22067/jsw.v0i0.32406.
Ahmadyousefi S, Bahremand A, Sheikh V, Komaki CB. 2019. Determining the snow coefficient in order to simulate the snow melting in the Shemshak watershed using the WetSpa model. Iranian Journal of Watershed Management Science. 13(47): 1-8. (In Persian). https://doi.org/20.1001.1.20089554.1398.13.47.3.1
Alinezhadi M, Mousavi SF, Hosseini K. 2021. Comparison of gene expression programming (GEP) and parametric and non-parametric regression methods in the prediction of the mean daily discharge of Karun river (A case study: Mollasani hydrometric station). Journal of Water and Soil Science. 25(1): 43-62. (In Persian). https://doi.org/10.47176/jwss.25.1.1012
Azinmehr M, Bahremand A, Kabir A. 2016. Parameter sensitivity and uncertainty analysis of the model WetSpa in the flow hydrograph simulation using PEST in Dinvar Basin Karkheh. Journal of Watershed Management Research. 7(1): 82-72. (In Persian). https://doi.org/10.18869/acadpub.jwmr.7.13.82.
Bahremand A, Corluy J, Liu Y, De Smedt F, Poórová J, Velcická L. 2005. Stream flow simulation by WetSpa model in Hornad river basin Slovakia. Floods from defence to management. London: Taylor-Francis Group. pp. 67-74.
Bayazidi M, Asadzadeh F, Kaki M. 2018. The application of intelligent techniques for predicting daily flow at Telvar basin river. Iranian journal of Ecohydrology. 5(1): 203-213. (In Persian). https://doi.org/10.22059/ije.2018.223015.386.
Behmanesh J, Mostafavi S, Zamanzad Ghavidel S. 2017. Use of soft calculations at estimation and prediction of environmental flow discharge (Case study: Khorkhoreh Chay river). Journal of Civil and Environmental Engineering. 47(3): 9-22. (In Persian).
Dehghani R, Yonesi H, Torabi Poudeh H. 2017. Comparing the performance of support vector machines gene expression programming and bayesian networks in predicting river flow (Case study: Kashkan River). Journal of Water and Soil Conservation. 24(4): 161-177. (In Persian). https://doi.org/10.22069/jwfst.2017.12398.2701.
Dehghani R, Torabi H, Younesi H, Shahinejad B. 2021. Application of wavelet support vector machine (WSVM) model in predicting river flow (Case study: Dez Basin). Watershed Engineering and Management. 13(1):98-110. (In Persian). .https://doi.org/10.22092/ijwmse.2020.128735.1748.
Delafrouz H, Ghaheri A, Ghorbani MA. 2018. A novel hybrid neural network based on phase space reconstruction technique for daily river flow prediction. Soft Computing. 22(7):2205-2215. https://doi.org/10.1007/s00500-016-2480-8.
Fatemi SE, Darabi Cheghabaleki S, Hafezparast M. 2022. The effect of preprocessing and reducing the input dimensions of the flow prediction model on optimized support vector regression by genetic algorithm. Advanced Technologies in Water Efficiency. 1(1): 24-47. (In Persian). https://doi.org/10.22126/atwe.2021.6660.1002.
Ghorbani MA, Khatibi R, Goel A, FazeliFard MH, Azani A. 2016. Modeling river discharge time series using support vector machine and artificial neural networks. Environmental Earth Sciences. 75(8): 1-13. https://doi.org/10.1007/s12665-016-5435-6.
Ghorbani MA, Khatibi R, Karimi V, Yaseen ZM, Zounemat-Kermani M. 2018. Learning from multiple models using artificial intelligence to improve model prediction accuracies: application to river flows. Water Resources Management. 32(13): 4201-4215. https://doi.org/10.1007/s11269-018-2038-x.
Hussain D, Khan AA. 2020. Machine learning techniques for monthly river flow forecasting of Hunza River Pakistan. Earth Science Informatics. 13(3): 939-949. https://doi.org/10.1007/s12145-020-00450-z.
Isazadeh M, Biazar S, Ashrafzadeh A, Khanjani R. 2019. Estimation of aquifer qualitative parameters in Guilans Plain using gamma test and support vector machine and artificial neural network models. Journal of Environmental Science and Technology. 21(2):1-21. (In Persian) https://doi.org/10.22034/jest.2019.13946.
Khashei-Siuki A, Sarbazi M. 2015. Evaluation of ANFIS ANN and geostatistical models to spatial distribution of groundwater quality (Case study: Mashhad Plain in Iran). Arabian Journal of Geosciences. 8:903–912. https://doi.org/10.1007/s12517-013-1179-8.
Khodakhah H, Aghelpour P, Hamedi Z. 2022. Comparing linear and non-linear data-driven approaches in monthly river flow prediction based on the models SARIMA LSSVM ANFIS and GMDH. Environmental Science and Pollution Research. 29(15): 21935-21954. https://doi.org/10.1007/s11356-021-17443-0
Nivesh S, Negi D, Kashyap PS, Aggarwal S, Singh B, Saran B, Sihag P. 2022. Prediction of river discharge of Kesinga sub-catchment of Mahanadi basin using machine learning approaches. Arabian Journal of Geosciences. 15(16): 1-19. https://doi.org/10.1007/s12517-022-10555-y.
Nozari H, Tavakoli F. 2018. Stream flow prediction using support vector machine based on discharge and precipitation time series on upstream stations (Case study: Taleh Zang hydrometric station). Modeling in Engineering. 16(54): 95-104. (In Persian) https://doi.org/10.22075/jme.2017.11363.1112.
Pandhiani SM, Sihag P, Shabri AB, Singh B, Pham QB. 2020. Time-series prediction of stream flows of Malaysian rivers using data-driven techniques. Journal of Irrigation and Drainage Engineering. 146(7): 04020013. https://doi.org/10.1061/(ASCE)IR.1943-4774.0001463.
Rahimi B, Hafezparast Mavaddat M. 2020. Comparison of SVM GEP and IHACRES models in prediction of runoff changes due to climate change (Case study: Jamishan Dam). Iranian Journal of Soil and Water Research. 51(10): 2483-2499. (In Persian).  https://doi.org/10.22059/ijswr.2020.303779.668640.
Sahoo A, Samantaray S, Ghose DK. 2021. Prediction of flood in Barak River using hybrid machine learning approaches: a case study. Journal of the Geological Society of India. 97(2):186-198. https://doi.org/10.1007/12594-021-1650-1.
Salarijazi M, Ghorbani K, Sohrabian E, Abdolhosseini M. 2016. Prediction of daily stream-flow using data driven models. Iranian Journal of Irrigation and Drainage. 10(4):479-488. (In Persian).
Samadi M, Fathabadi A. 2019. Application of time series ANN and SVM models in forecasting the Gorgan dam inflow rate. Environment and Water Engineering. 4(4): 299-309. (In Persian). https://doi.org/10.22034/jewe.2018.128256.1256.
Sattari M, Rezazadeh A, Safdari F, Ghahramanian F. 2016. Performance evaluation of M5 tree model and support vector regression methods in suspended sediment load modeling. Water and Soil Resources Conservation. 6(1): 109-124. (In Persian).
Shaofu M, Al-Juboori AM, Alwan AH, Abdel-Salam ASG. 2021. On the investigation of monthly river flow generation complexity using the applicability of machine learning models. Complexity. pp. 1-14. https://doi.org/10.1155/2021/3721661
Sharifi Garmdareh E, Vafakhah M, Eslamian S. 2019. Assessment the performance of support vector machine and artificial neural network systems for regional flood frequency analysis (a case study: Namak Lake watershed). Journal of Water and Soil Science. 23(1): 351-366. (In Persian). https://doi.org/10.29252/jstnar.23.1.26.
Solgi A, Zareie H, Golabi M. 2017. Performance assessment of gene expression programming model using data preprocessing methods to modeling river flow. Journal of Water and Soil Conservation. 24(2):185-201. (In Persian) https://doi.org/10.22069/jwfst.2017.11353.2573.
Taylor KE. 2001. Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research: Atmospheres. 106(D7): 7183-7192.‏ https://doi.org/10.1029/2000JD900719.
Zeinalie M, Golabi M, Niksokhan M, Sharifi M. 2020. Modeling daily river flow using simulator meta-models (Case study: Gamasiab River). Journal of Environmental Science and Technology. 22(4): 121-133. (In Persian). https://doi.org/ 10.22034/jest.2020.33087.4089.

Files

History

  • Receive Date: 29 November 2022
  • Revise Date: 03 January 2023
  • Accept Date: 19 March 2023

Share

How to cite

Statistics