Document Type : Short Paper

Authors

1 M.Sc. Student, Department of Water Engineering and Sciences, Faculty of Agricultural Sciences and Food Industries, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 Assist. Professor, Department of Water Engineering and Sciences, Science and Research Branch, Islamic Azad University, Tehran, Iran

3 Professor, Department of Water Engineering and Sciences, Faculty of Agricultural Sciences and Food Industries, Science and Research Branch, Islamic Azad University, Tehran, Iran

4 Assist. Professor, Research Institute of the Ministry of Energy, Tehran, Iran

Abstract

The importance of regulating the supply and demand regime shows the need for planning in the exploitation of surface water resources. The aim of this study was to compare the performance of two models of Bayesian network (BN) with a probabilistic approach and MLP neural network for flow prediction and selection of the best structural model. Monthly meteorological data including rainfall, monthly average temperature, evaporation, and the volume of water transferred from five hydrometric stations were introduced as input data to the models, and runoff to the dam was considered as predictable. Input data with different layouts were introduced to BN and MLP models. The results were obtained by comparing 17 selected models according to the index criteria: Nash-Sutcliffe coefficient (NS), mean square error (MSE), mean square error root (RMSE), and MEAN absolute prediction error (MAPE). The best model in BN model with 43.3% similarity and index criteria was estimated to be -3.98, 300, 17.3, and 0.06, respectively. The MLP model with 80% similarity and index criteria were introduced as -10.3, -8266, 23.9, and 122.3 in the best model, respectively. As a result, both models performed well in runoff estimation, but the BN model had much better accuracy in forecasting. Finally, a structural pattern with acceptable results in both MLP and BN models was identified.

Keywords

Main Subjects

Afan, H. A., Allawi, M. F., El_Shafie, A., Yaseen, Z. M., Ahmed, A. N., Malek, A. M., Koting, S. B., Salih, S. Q., Mohtar, W. H. M. W., Lai, S. H., Sefelnasr, A., Sheirf, M. and El-Safie, A. L. (2020). Input attributes optimization using the feasibility of genetic ninspired algorithm: application of river flow forecasting. Water Recour. Manag. Sci. Rep., 10(1),1_15.
Ahmadi, F. (2020). Evaluation of support vector machine and adaptive neuro-fuzzy inference system performance in prediction of monthly river flow (case study: Nazlu chai and Sezar Rivers). Iran. J. Soil Water Res., 51(3), 673-686. DIO: 10.22059/ijswr.2019.290994.668356 [In Persian].
Babaei Moghadam, A., Khaledian, M., Shahnazari, A. and Morteza Pour, M. (2016). Investigation and forecast of Ghezel Ozan and Shahroud rivers. J. Eco. Hydrol., 3(2), 195 - 204 [In Persian].
Dehghani, R., Yonesi, H. and Torabi Pode, H (2017). Comparing the performance of support vector machines, gene expression programming and bayesian networks in predicting river flow (case study: Kashkan River). J. Water Soil Conserv., 4(24), 161-177. magiran.com/p1774763 [In Persian].
Haykin, S. (1999). Neural networks: A comprehensive foundation. NJ. Prentice-Hall Inc. Englewood Cliffs.
Mohajerani, H., Mosaedi, A., Kholgh, M., Meftah Halgh, M. and Saddin, A. (2010). Introduction of Bayesian decision networks and their application in water resources management. The first national conference on coastal land water resources management [In Persian].
Nikoo, M. and Krachian, R. (2009). Evaluating the efficiency of bayesian networks in river water quality management: application of trade-ratio system. Water Wastewater, 1(20), 23-33 [In Persian].
Noorbeh, P., Roozbahani, A. and Kardan Moghaddam, H. (2018). Prediction of Zayandeh Rood Dam inflow and hydrological wet and dry periods using bayesian networks. J. Water Soil, 32(3), 633-646. DIO: 10.22067/jsw.v32i3.72084 [In Persian].
Riahi_Madvar, H., Dehghani, M. and Memarzadeh, R. and Gharabaghi, B. (2021). Short to long-teem forecasting of rivwr flows by heuristic optimization algorithms hybridized with ANFIS. Water Recour. Manage., 35(4), 1149-1166. DIO: 10.1007/s11269-020-02756-5
Speed, R., Yuanyuan, L., Quesne, T. L., Pegram, G. and Zhiwei, Z. H. (2013. (Basin water allocation planning. United Nations, Educational, Scientific and Culture Organization. PP144.