The streamflow prediction of Kurkursar river using hybrid artificial intelligence models

Document Type : Research/Original/Regular Article

Authors

1 Ph.D. Student/ Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 Associate Professor/ Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

3 Associate Professor/ Department of Range and Watershed Management, Faculty of Natural Resources, Urmia University, Urmia, Iran

4 Professor/ Department of Water Engineering, Center of Excellence in Hydroinformatics, Faculty of Civil Engineering, University of Tabriz, Tabriz, Iran

Abstract

Introduction
Streamflow prediction is a challenging and critical task for water resource management. Streamflow prediction is one of the essential steps for reliable and robust water resources planning and management. On the other hand, streamflow prediction plays a crucial role in water resources systems planning and mitigating hydrological extremes such as floods and droughts. Since a variety of uncertainties exist in streamflow prediction, it is necessary to enhance our efforts to robustly address uncertainties and their interactions for improving the reliability of streamflow prediction. It is highly vital for hydropower operation, agricultural planning, and flood control. Physical process-based models are developed based on the understanding of the runoff generation processes, transport in channels, and mathematical formulations or parameterization of these physical processes. Data-driven models have the advantages of low demand for model input and ease of use. Due to the influence of various factors, including climate change, human activities, and socio-economic development, the hydrological time series leads to its complicated stochastic characteristics. Statistical models are the typical examples of this category and have been widely used in streamflow predictions over different regions. Different statistical models, machine learning methods are effective in describing the nonlinear characteristics of the observations and offer an alternative approach for streamflow prediction. Over the last two decades, a variety of machine learning techniques, including the artificial neural network (ANN) and the support vector machine (SVM), have been extensively applied in water resource management and hydrological prediction.
 
Materials and Methods
In this research, from the data of precipitation (Pt), precipitation with a delay of one day (Pt-1) until precipitation with a delay of three days (Pt-3) and discharge with a delay of one day (Qt-1) until discharge with a delay of 3 days (Qt- 3) are used as input variables and discharge (Qt) is used as output variable to predict the flow of Kurkursar river in Nowshahr. The Kurkursar river basin in the north of Iran is considered a sub-basin of the North Sea, its area is 75.495 km2, the average height of the basin is about 860 m, and the overall average slope is about 80.21%. This basin has an oblique shape and is limited to the Caspian Sea from the north, the Meshlak river and part of the Chalus watershed from the south, and the Chalus watershed from the west. Various geomorphological forms such as floodplains, alluvial cones, and sediment dams have been identified in the river basin area. The time series is daily and 70% and 30% of the data are respectively used for the training and test processes. The models used in this research include three individual models (random forest model - artificial neural network and regression support vector machine) and three hybrid models including bagging tree model - random forest (BA-RF), neural network - creative rifleman (ANN-AIG) and Support Vector Machine Regression-Crow Search (SVR-CSA) was used. In order to evaluate the model, the Mean square error (MAE), root mean squared error (RMSE), Nash–Sutcliffe model efficiency coefficient (NSE), and the PSR were used. Pearson's correlation coefficient (PCC) is used for the relationship between input and output variables. Therefore, we calculate the correlation coefficients between input and output variables, then we evaluate the composition of the input model based on different scenarios. The model combination that has the highest correlation is selected as the selected model. Then, the internal coefficients of each model are optimized with the help of meta-heuristic optimization algorithms. Therefore, the prediction results and observational data of the model are compared with each other. Finally, time series graphs, data dispersion, and box plots will be drawn and we will compare different evaluation indicators quantitatively and qualitatively. Finally, we compare the results of all models with each other and choose the model that has the best result as the best model. In the final step, we will compare the accuracy increase of the hybrid model (error reduction) with the standalone model to determine the error reduction percentage.
 
Results and Discussion
The Koukursar Nowshahr river flow was predicted using seven model with combinations of predictive variables such as R (t), Q (t-1), Q (t-2), R (t-1), Q (t -3), R (t-2) and R (t-3) as input variables and flow rate (Qt) as output variable. The results show that the precipitation variable (Rt) with a value of 0.563 has the highest correlation with the output variable, followed by Q (t-1) with 0.463, Q (t-2) with 0.297, R (t-1) with 0.281, Q (t-3) with 0.251, R (t-2) with 0.124, and R (t-3) with 0.072. Variable R(t) with 0.563 has the highest correlation, and variable R(t-3) with 0.072 has the lowest correlation with the output variable. Based on this, the relationship between the input and output variables was shown based on the correlation coefficient using the radar chart. In this regard, in this research, three individual models and three hybrid models were used to predict the river flow. Among the different scenarios and combinations of the input model, model 7 was used as the final model for forecasting. The evaluation results show that the RF model in the training phase has R2= 0. 957 and in the test, a phase has R2=0.717. The RF model has the highest correlation coefficient among all research models in the training phase. Also, in the test phase, it has the third rank among all models. ANN-AIG model improved the error of the single model by 32.94 %, the single SVR-CSA model by 23.17%, and the BA-RF model by 17.74%.
 
Conclusion
The qualitative results of the models show that all the models performed very well in predicting the model. Among the research models, the ANN-AIG model has performed best in forecasting.

Keywords

Main Subjects

References

Adamowski, J. (2013). Using support vector regression to predict direct runoff, base flow and total flow in a mountainous watershed with limited data in Uttaranchal, India. Annals of Warsaw University of Life Sciences-SGGW. Land Reclamation, 45(1).
Afan, H.A., El-Shafie, A., Yaseen, Z.M., Hameed, M.M., Wan Mohtar, W.H.M., & Hussain, A. (2015). ANN based sediment prediction model utilizing different input scenarios. Water Resources Management, 29(4), 1231-1245.
Ahmed, J.A., & Sarma, A.K. (2007). Artificial neural network model for synthetic streamflow generation. Water Resources Management, 21(6), 1015-1029.
Al-Abadi, A.M., & Shahid, S. (2016). Spatial mapping of artesian zone at Iraqi southern desert using a GIS-based random forest machine learning model. Modeling Earth Systems and Environment, 2(2), 1-17.
Askarzadeh, A. (2016). A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm. Computers & Structures, 169, 1-12.
Aytek, A., Asce, M., & Alp, M. (2008). An application of artificial intelligence for rainfall-runoff modeling. Journal of Earth System Science, 117(2), 145-155.
Barzegari Banadkooki, F., Ehteram, M., Panahi, F., Sammen, S.Sh., Binti Othman, F., & El Shafie, A. (2020). Estimation of total dissolved solids (TDS) using new hybrid machine learning models. Journal of Hydrology, 587, 124989.
Behzad, M., Asghari, K., Eazi, M., & Palhang, M. (2009). Generalization performance of support vector machines and neural networks in runoff modeling. Expert Systems With Applications, 36(4), 7624-7629.
Beven, K. (1989). Changing ideas in hydrology- The case of physically-based models. Journal of Hydrology, 105(1-2), 157-172.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Choy, K.Y., & Chan, C.W. (2003). Modelling of river discharges and rainfall using radial basis function networks based on support vector regression. International Journal of Systems Science, 34(14-15), 763-773.
Cutler, A., Cutler, D.R., & Stevens, J.R. (2012). Random forests. Pp. 157-175, In: Ensemble machine learning. Springer, Boston, MA.
Danandeh Mehr, A., Kahya, E., Şahin, A., & Nazemosadat, M.J. (2015). Successive-station monthly streamflow prediction using different artificial neural network algorithms. International Journal of Environmental Science and Technology, 12(7), 2191-2200.
Dawson, C.W., & Wilby, R.L. (2001). Hydrological modelling using artificial neural networks. Progress in Physical Geography: Earth and Environment, 25(1), 80-108.
Dehghani, R., & Poudeh, H.T. (2021). Applying hybrid artificial algorithms to the estimation of river flow: a case study of Karkheh catchment area. Arabian Journal of Geosciences, 14(9), 1-19.
Dehghani, R., & Torabi Poudeh, H. (2022). Application of novel hybrid artificial intelligence algorithms to groundwater simulation. International Journal of Environmental Science and Technology, 19(5), 4351-4368.
Dehghani, R., Poudeh, H.T., Younesi, H., & Shahinejad, B. (2020). Daily streamflow prediction using support vector machine-artificial flora (SVM-AF) hybrid model. Acta Geophysica, 68(6), 1763-1778.
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.
Deo, R.C., & Şahin, M. (2016). An extreme learning machine model for the simulation of monthly mean streamflow water level in eastern Queensland. Environmental Monitoring and Assessment, 188(2), 1-24.
Flint, A.L., Flint, L.E., Bodvarsson, G.S., Kwicklis, E.M., & Fabryka-Martin, J. (2001). Evolution of the conceptual model of unsaturated zone hydrology at Yucca Mountain, Nevada. Journal of Hydrology, 247(1-2), 1-30.
Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., Meena, S.R., Tiede, D., & Aryal, J. (2019). Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sensing, 11(2), 196.
Ghafari, G.A., & Vafakhah, M. (2014). Simulation of rainfall-runoff process using artificial neural network and adaptive neuro-fuzzy interface system (case study: Hajighoshan Watershed). Journal of Watershed Management Research, 4(8), 120-136 (in Persian).
Ghorbani, M.A., Azani, A., & Naghipour, L. (2016). Comparison of the performance of support vector machine with other intelligent techniques to simulate rainfall-runoff process. Journal of Watershed Management Research, 7(13), 92-103 (in Persian). 
Guven, A., & Kişi, Ö. (2011). Daily pan evaporation modeling using linear genetic programming technique. Irrigation Science, 29(2), 135-145.
Hadi, S.J., & Tombul, M. (2018). Streamflow forecasting using four wavelet transformation combinations approaches with data-driven models: A comparative study. An International Journal Water Resources Management, 32(14), 4661-4679.
Hajian, R., Jalali, M.R., & Mastouri, R. (2022). Multi-step Lake Urmia water level forecasting using ensemble of bagging based tree models. Earth Science Informatics, 15, 2515–2543.
Hassanien, A.E., Rizk-Allah, R.M., & Elhoseny, M. (2018). A hybrid crow search algorithm based on rough searching scheme for solving engineering optimization problems. Journal of Ambient Intelligence and Humanized Computing, 1-25.
Hussien, A.G., Amin, M., Wang, M., Liang, G., Alsanad, A., Gumaei, A., & Chen, H. (2020). Crow search algorithm: theory, recent advances, and applications. IEEE Access, 8, 173548-173565.
Kambalimath, S.S., & Deka, P.C. (2021). Performance enhancement of SVM model using discrete wavelet transform for daily streamflow forecasting. Environmental Earth Sciences, 80(3), 1-16.
Khosravi, K., Cooper, J.R., Daggupati, P., Pham, B.T., & Bui, D.T. (2020). Bedload transport rate prediction: Application of novel hybrid data mining techniques. Journal of Hydrology, 585, 124774.
Khosravi, K., Mao, L., Kisi, O., Yaseen, Z.M., & Shahid, S. (2018). Quantifying hourly suspended sediment load using data mining models: case study of a glacierized Andean catchment in Chile. Journal of Hydrology, 567, 165-179.
Khosravi, K., Miraki, S., Saco, P.M., & Farmani, R. (2021). Short-term river streamflow modeling using ensemble-based additive learner approach. Journal of Hydro-environment Research, 39, 81-91.
Liaw, A., & Wiener, M. (2002). Classification and regression by random forest. R News, 2(3), 18-22.
Malik, A., Tikhamarine, Y., Souag-Gamane, D., Kisi, O., & Pham, Q.B. (2020). Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction. Stochastic Environmental Research and Risk Assessment, 34(11), 1755-1773.
Mamun, A.A., Islam, A.R.M.T., Khosravi, K., & Singh, S.K. (2022). Suspended sediment load prediction using hybrid bagging-based Heuristic Search Algorithm. Geocarto International, 37(27), 1-32.
Meraihi, Y., Gabis, A.B., Ramdane-Cherif, A., & Acheli, D. (2021). A comprehensive survey of crow search algorithm and its applications. Artificial Intelligence Review, 54(4), 2669-2716.
Mirzania, E., Malek Ahmadi, H., Shahmohammadi, Y., & Ebrahim Zadeh, A. (2021). Impact of wavelet on accuracy of estimated models in rainfall-runoff modeling (Case study: Sufi Chay). Water and Soil Management and Modeling (WSMM), 1(3), 67-79 (in Persian). 
Misra, D., Oommen, T., Agarwal, A., Mishra, S.K., & Thompson, A.M. (2009). Application and analysis of support vector machine based simulation for runoff and sediment yield. Biosystems Engineering, 103(4), 527-535.
Moldovan, D., Chifu, V., Pop, C., Cioara, T., Anghel, I., & Salomie, I. (2018). Chicken swarm optimization and deep learning for manufacturing processes. 17th RoEduNet conference: networking in education and research (RoEduNet), Cluj-Napoca, Romania, Pp. 1-6.
Momeneh, S. (2022). Performance comparison of artificial intelligence models with IHACRES model in streamflow modeling of the Gamasiab River catchment. Water and Soil Management and Modeling, 2(3), 1-16 (in Persian). 
Najibzade, N., Qaderi, K., Ahmadi, M.M., (2020). Rainfall-runoff modelling using support vector regression and artificial neural network models (case study: SafaRoud Dam Watershed). Iranian Journal of Irrigation & Drainage, 13(6), 1709-1720 (in Persian). 
Naghibi, S.A., Ahmadi, K., & Daneshi, A. (2017). Application of support vector machine, random forest, and genetic algorithm optimized random forest models in groundwater potential mapping. Water Resources Management, 31(9), 2761-2775.
Oliveira, S., Oehler, F., San-Miguel-Ayanz, J., Camia, A., & Pereira, J.M. (2012). Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest. Forest Ecology and Management, 275, 117-129.
Panah, P.G., Bornapour, M., Hemmati, R., & Guerrero, J. M. (2021). Charging station stochastic programming for hydrogen/battery electric buses using multi-criteria crow search algorithm. Renewable and Sustainable Energy Reviews, 144, 111046.
Pandhiani, S.M., Sihag, P., Shabri, A.B., Singh, B., & Pham, Q.B. (2020). Time-series prediction of streamflows of Malaysian rivers using data-driven techniques. Journal of Irrigation and Drainage Engineering, 146(7), 04020013.
Pijarski, P., & Kacejko, P. (2019). A new metaheuristic optimization method: the algorithm of the innovative gunner (AIG). Engineering Optimization, 51(12), 2049-2068.
Rashidi, S., Vafakhah, M., Lafdani, E.K., & Javadi, M.R. (2016). Evaluating the support vector machine for suspended sediment load forecasting based on gamma test. Arabian Journal of Geosciences, 9(11), 1-15.
Remesan, R., Shamim, M.A., Han, D., & Mathew, J. (2009). Runoff prediction using an integrated hybrid modelling scheme. Journal of Hydrology, 372(1-4), 48-60.
Roshni, T., Mirzania, E., Hasanpour Kashani, M., Bui, Q. A.T., & Shamshirband, S. (2022). Hybrid support vector regression models with algorithm of innovative gunner for the simulation of groundwater level. Acta Geophysica, 70(4), 1885-1898.
Roustami, S., Shahinejad, B., Younesi, H., Torabi poudeh, H., & Dehghani, R. (2022). Analysis of new hybrid artificial intelligence models in estimating flood flow. Hydrogeomorphology, 8(29), 187-201 (in Persian). 
Samantaray, S., Tripathy, O., Sahoo, A., & Ghose, D.K. (2020). Rainfall forecasting through ANN and SVM in Bolangir Watershed, India. Smart Intelligent Computing and Applications, 159, 767-774.
Samsudin, R., Saad, P., & Shabri, A. (2011). River flow time series using least squares support vector machines. Hydrology and Earth System Sciences, 15(6), 1835-1852.
Sarma, S.K. (2021). Optimally configured deep convolutional neural network for attack detection in internet of things: Impact of algorithm of the innovative gunner. An International Journal Wireless Personal Communications, 118(1), 239-260.
Shahdad, M., & Saber, B. (2022). Drought forecasting using new advanced ensemble-based models of reduced error pruning tree. Acta Geophysica, 70(2), 697-712.
Sharafati, A., Khosravi, K., Khosravinia, P., Ahmed, K., Salman, S.A., Yaseen, Z.M., & Shahid, S. (2019). The potential of novel data mining models for global solar radiation prediction. International Journal of Environmental Science and Technology, 16(11), 7147-7164.
Sudheer, C., Maheswaran, R., Panigrahi, B.K., & Mathur, S. (2014). A hybrid SVM-PSO model for forecasting monthly streamflow. Neural Computing and Applications, 24(6), 1381-1389.
Vapnik, V., Golowich, S., & Smola, A. (1996). Support vector method for function approximation, regression estimation and signal processing. Advances in neural information processing systems, 9.
Were, K., Bui, D.T., Dick, B., & Singh, B.R. (2015). A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. Ecological Indicators, 52, 394-403.
Yousefi, V., Kheiri, S., & Rajebi, S. (2020). Evaluation of K-nearest neighbor, bayesian, perceptron, RBF and SVM neural networks in diagnosis of dermatology disease. International Journal on Technical and Physical Problems of Engineering, 129(1), 114-120.
Yu, P.S., Chen, S.T., & Chang, I.F. (2006). Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328(3-4), 704-716.
Zhu, M., Sun, W., Hahn, A., Wen, Y., Xiao, C., & Tao, W. (2020). Adaptive modeling of maritime autonomous surface ships with uncertainty using a weighted LS-SVR robuts to outliers. Ocean Engineering, 200(2), 107053.
Zeinali, M.J., & Khashei Siuki, A. (2018). Assessing the Accuracy of Contemporaneous time series and neural network models in modeling rainfall-runoff (case study: Nazloochaei Catchment). Journal of Water and Soil Conservation, 25(2), 315-321 (in Persian). 
Water and Soil Management and Modelling
Volume 3, Issue 1
2023
Pages 181-199

Files

History

  • Receive Date: 11 October 2022
  • Revise Date: 30 October 2022
  • Accept Date: 01 November 2022

Share

How to cite

Statistics