Modeling and Comparing GMDH and RBF Artificial Neural Networks in Forecasting Short-Term Demand for Drinking Water in Zahedan

Document Type : Original Article

Authors

1 Assistant Professor of Economics, Maritime and Marine Science University of Chabahar

2 Assistant Professor of Agricultural Economics, University of Sistan and Baluchestan

Abstract

The water requirement of the urban district of Zahedan City in Iran is met by the transfer of water from Sistan Chah-Nimeh reservoirs that are themselves suffering from severe water crisis. So, the prediction of the urban demand for drinking water can greatly help managers and users of urban water systems to use sound management practices. The present paper uses the artificial neural networks of GMDH and RBF, as two vigorous tools for the analysis and modeling of nonlinear relationship, to estimate monthly demand for drinking water in Zahedan in 2017. The selected parameters include mean monthly temperature, relative humidity percentage, mean precipitation, sunny hours, and previous-month consumption rate. The results of comparing MSE and MAE indicators show that after studying different structures with various number of neurons and hidden layers, the GMDH neural network with three hidden layers that has one neuron in layer 1, three neurons in hidden layer 2, and three neurons in hidden layer 3 yields the best results for the predication of short-term demand for drinking water. The comparison of linear and nonlinear activity functions reveals that in output layer of GMDH and RBF neural models, the nonlinear functions outperform linear functions. As well, among the GMDH model, the models with nonlinear output show better performance than those with linear output. Also, it is shown that the expansion of the network structure cannot improve the results considerably.

Keywords


 

Al-Zahrani, M., Abo- Monasar, A., 2015, "Urban Residential Water Demand Prediction Based on Artificial Neural Networks and Time Series Models", Water Resources Management, 29(10): 3651-3662.

Gagliardi, F., Alvisi, S., Kapelan, Z., Franchini, M., 2017, "A Probabilistic Short-Term Water Demand Forecasting Model Based on the Markov Chain", Water, 9(7): 1-15.
Khatri, K.B., Vairavamoorthy, K., 2009, "Water Demand Forecasting for the City of the Future against the Uncertainties and the Global Change Pressures: Case of Birmingham", EWRI/ASCE: 2009, Conference: Kansas, USA May.
Kostas, B., Chrysostomos, S., 2006, "Estimating urban Residential Water Demand Determinants and Forecasting Water Demand for Athens Metropolitan Area, 2000-2010", South-Eastern Europe Journal of Economics, 4(1): 47-51.
Liu, J., Mingqi, C., 2010, "Application of the Grey Theory and the Neural Network in Water Demand Forecast", Sixth International Conference on Natural Computation (ICNC).
Mousavi, S.N., Kavousi, M., 2016, "Application of neural network methods and time series models in predicting drinking water consumption, Case study of Rasht city", Journal of Water and Sewage, 27(4): 84-89. (In Persian)

Perea,R,G., ,E.M., Montesinos,P., Díaz,J,A,R.,2018,” Optimisation of water demand forecasting by artificial intelligence with short data sets”, Biosystems Engineering,April,168:141-152.

Ramezani Chermahineh, A., Zounemat Kermani, M., 2017, "Investigating the Efficiency of Support Vector Regression Methods, Multilevel Perceptron Neural Network and Multivariate Linear Regression in Determining Groundwater Levels (Case Study: Shahrekord Plain)", Watershed Management Research, 8(15): 1-12.(In Persian)
Sadeghi, H., Zolfaghri, M., Aram, R., 2012, Modeling and Urgent Forecasting Urban Water demand, Economic Policies (Neme Mofid), 7: 159-172. (In Persian)
Sardar Shahraki, A., 2017, "Optimal allocation of water sources in the Hirmand watershed using game theory and evaluation of management scenarios", Ph.D. in Agricultural Economics, Sistan and Baluchestan University, Zahedan, Iran. (In Persian)
Sharzei, G.A., Ahrari, M., Fakhrai, H., 2008, "Prediction of water demand in Tehran using structural models, time series and GMDH neural network", Economic research, 43: 151-175.
Tabesh, M., Dini, M., 2011, "Prediction of daily urban water demand using artificial neural networks, Case study: Tehran", Journal of Water and Sewage, 21(1), 84-95.
Tabesh, M., Dini, M., Khoshakhlagh, A.J., Zahraie, B., 2009, "Estimation of daily water consumption in Tehran using time series", Iranian Water Resources Researches Journal, 4: 57-65. (In Persian)
Tabesh, M., Ghosheh, S., Yazdan Panah, M.J., 2008, "The short-term demand for water in Tehran using artificial neural networks", Journal of Faculty of Engineering, 41(1): 11-24. (In Persian).