Prediction of Water Demand Using Artificial Neural Networks Models and Statistical Model

Full Text (PDF, 1068KB), PP.40-55

Views: 0 Downloads: 0


Mohammed Awad 1,* Mohammed Zaid-Alkelani 2

1. Department of Computer Systems Engineering, Arab American University, Palestine

2. Department of Computer Science, Arab American University, Palestine

* Corresponding author.


Received: 19 Mar. 2019 / Revised: 22 Apr. 2019 / Accepted: 9 May 2019 / Published: 8 Sep. 2019

Index Terms

Prediction, Future Water Demand, Multilayer Perceptron NNs, Levenberg Marquardt Algorithm, Radial Basis Function NNs, Genetic Algorithms, ARIMA


The prediction of future water demand will help water distribution companies and government to plan the distribution process of water, which impacts on sustainable development planning. In this paper, we use a linear and nonlinear models to predict water demand, for this purpose, we will use different types of Artificial Neural Networks (ANNs) with different learning approaches to predict the water demand, compared with a known type of statistical methods. The dataset depends on sets of collected data (extracted from municipalities databases) during a specific period of time and hence we proposing a nonlinear model for predicting the monthly water demand and finally provide the more accurate prediction model compared with other linear and nonlinear methods. The applied models capable of making an accurate prediction for water demand in the future for the Jenin city at the north of Palestine. This prediction is made with a time horizon month, depending on the extracted data, this data will be used to feed the neural network model to implement mechanisms and system that can be employed to predicts a short-term for water demands. Two applied models of artificial neural networks are used; Multilayer Perceptron NNs (MLPNNs) and Radial Basis Function NNs (RBFNNs) with different learning and optimization algorithms Levenberg Marquardt (LM) and Genetic Algorithms (GAs), and one type of linear statistical method called Autoregressive integrated moving average ARIMA are applied to the water demand data collected from Jenin city to predict the water demand in the future. The execution results appear that the MLPNNs-LM type is outperformed the RBFNN-GAs and ARIMA models in the prediction the water demand values.

Cite This Paper

Mohammed Awad, Mohammed Zaid-Alkelani, "Prediction of Water Demand Using Artificial Neural Networks Models and Statistical Model", International Journal of Intelligent Systems and Applications(IJISA), Vol.11, No.9, pp.40-55, 2019. DOI:10.5815/ijisa.2019.09.05


[1]MEKONNEN, Mesfin M.; HOEKSTRA, Arjen Y. Four billion people facing severe water scarcity. Science advances, 2016, 2.2: e1500323.‏
[2]HASSAN, F. A. Water history for our times, IHP Essays on Water History No. 2. International Hydrological Programme, UNESCO, Paris, 2010.‏
[3]GHIASSI, Manoochehr; ZIMBRA, David K.; SAIDANE, Hassine. Urban water demand forecasting with a dynamic artificial neural network model. Journal of Water Resources Planning and Management, 2008, 134.2: 138-146.‏
[4]WAGNER, Neal, et al. Intelligent techniques for forecasting multiple time series in real-world systems. International Journal of Intelligent Computing and Cybernetics, 2011, 4.3: 284-310.
[5]AWAD, Mohammed. Forecasting of chaotic time series using RBF neural networks optimized by genetic algorithms. Int. Arab J. Inf. Technol., 2017, 14.6: 826-834.‏
[6]AWAD, Mohammed, et al. Prediction of Time Series Using RBF Neural Networks: A New Approach of Clustering. Int. Arab J. Inf. Technol., 2009, 6.2: 138-143.‏
[7]KHANDELWAL, Ina; ADHIKARI, Ratnadip; VERMA, Ghanshyam. Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Computer Science, 2015, 48: 173-179.‏
[8]KIHORO, J.; OTIENO, R. O.; WAFULA, C. Seasonal time series forecasting: A comparative study of ARIMA and ANN models. 2004.‏
[9]KOFINAS, D., et al. Urban water demand forecasting for the island of Skiathos. Procedia Engineering, 2014, 89: 1023-1030.‏
[10]SAMPATHIRAO, Ajay Kumar, et al. Water demand forecasting for the optimal operation of large-scale drinking water networks: The Barcelona Case Study. IFAC Proceedings Volumes, 2014, 47.3: 10457-10462.‏
[11]HERRERA, Manuel, et al. Predictive models for forecasting hourly urban water demand. Journal of Hydrology, 2010, 387.1-2: 141-150.‏
[12]ADHIKARI, Ratnadip; AGRAWAL, Ramesh K. An introductory study on time series modeling and forecasting. arXiv preprint. 2013.‏ arXiv:1302.6613.
[13]ZHANG, Guoqiang; PATUWO, B. Eddy; HU, Michael Y. Forecasting with artificial neural networks: The state of the art. International journal of forecasting, 1998, 14.1: 35-62.‏
[14]LIU, Junguo; SAVENIJE, Hubert HG; XU, Jianxin. Forecast of water demand in Weinan City in China using WDF-ANN model. Physics and Chemistry of the Earth, Parts A/B/C, 2003, 28.4-5: 219-224.‏
[15]HAWLEY, Delvin D.; JOHNSON, John D.; RAINA, Dijjotam. Artificial neural systems: A new tool for financial decision-making. Financial Analysts Journal, 1990, 46.6: 63-72.‏
[16]DREISEITL, Stephan; OHNO-MACHADO, Lucila. Logistic regression and artificial neural network classification models: a methodology review. Journal of biomedical informatics, 2002, 35.5-6: 352-359.‏
[17]WAN, Eric A. Neural network classification: A Bayesian interpretation. IEEE Transactions on Neural Networks, 1990, 1.4: 303-305.‏
[19]JAYALAKSHMI, T.; SANTHAKUMARAN, A. Statistical normalization and backpropagation for classification. International Journal of Computer Theory and Engineering, 2011, 3.1: 1793-8201.‏
[20]GOYAL, P.; CHAN, Andy T.; JAISWAL, Neeru. Statistical models for the prediction of respirable suspended particulate matter in urban cities. Atmospheric Environment, 2006, 40.11: 2068-2077.‏
[21]IHM, Sun Hoo; SEO, Seung Beom; KIM, Young-Oh. Valuation of Water Resources Infrastructure Planning from Climate Change Adaptation Perspective using Real Option Analysis. KSCE Journal of Civil Engineering, 2019, 1-9.‏
[22]ALSHARIF, Mohammed H.; YOUNES, Mohammad K.; KIM, Jeong. Time Series ARIMA Model for Prediction of Daily and Monthly Average Global Solar Radiation: The Case Study of Seoul, South Korea. Symmetry, 2019, 11.2: 240.‏
[23]AWAD, Mohammed, et al. Prediction of Time Series Using RBF Neural Networks: A New Approach of Clustering. Int. Arab J. Inf. Technol., 2009, 6.2: 138-143.‏
[24]CHEN, Ching-Fu; CHANG, Yu-Hern; CHANG, Yu-Wei. Seasonal ARIMA forecasting of inbound air travel arrivals to Taiwan. Transportmetrica, 2009, 5.2: 125-140.‏
[25]JIANG, Heng; LIVINGSTON, Michael; ROOM, Robin. Alcohol consumption and fatal injuries in Australia before and after major traffic safety initiatives: a time series analysis. Alcoholism: clinical and experimental research, 2015, 39.1: 175-183.‏
[26]TOPUZ, B. Kilic, et al. Forecasting of Apricot Production of Turkey by Using Box-Jenkins Method. Turkish Journal of Forecasting vol, 2018, 2.2: 20-26.‏
[27]ZHANG, Lina; XIN, Fengjun. Prediction Model of River Water Quality Time Series Based on ARIMA Model. In: International Conference on Geo-informatics in Sustainable Ecosystem and Society. Springer, Singapore, 2018. p. 127-133.
[28]FARAWAY, Julian; CHATFIELD, Chris. Time series forecasting with neural networks: a comparative study using the airline data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 1998, 47.2: 231-250.‏
[29]NURY, Ahmad Hasan; HASAN, Khairul; ALAM, Md Jahir Bin. Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh. Journal of King Saud University-Science, 2017, 29.1: 47-61.‏
[30]Gardner, Matt W., and S. R. Dorling. "Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences." Atmospheric Environment 32.14-15 (1998): 2627-2636.
[31]Ki┼či, Özgür, and ErdalUncuo─člu. "Comparison of three back-propagation training algorithms for two case studies." (2005).
[32]BURGES, Christopher, et al. Learning to rank using gradient descent. In: Proceedings of the 22nd International Conference on Machine learning (ICML-05). 2005. p. 89-96.‏
[33]BATTITI, Roberto. First-and second-order methods for learning: between steepest descent and Newton's method. Neural Computation, 1992, 4.2: 141-166.‏
[34]CUI, Miao, et al. A new approach for determining damping factors in the Levenberg-Marquardt algorithm for solving an inverse heat conduction problem. International Journal of Heat and Mass Transfer, 2017, 107: 747-754.
[35]CHEN, Zhen-Yao; KUO, R. J. Combining SOM and evolutionary computation algorithms for RBF neural network training. Journal of Intelligent Manufacturing, 2019, 30.3: 1137-1154.‏
[36]POMARES, Héctor, et al. An enhanced clustering function approximation technique for a radial basis function neural network. Mathematical and Computer Modelling, 2012, 55.3-4: 286-302.‏
[37]AWAD, Mohammed. Optimization RBFNNs parameters using genetic algorithms: applied on function approximation. International Journal of Computer Science and Security (IJCSS), 2010, 4.3: 295-307.‏
[38] Accessed [14 09 2018].
[39]AWAD, Mohammed. Input Variable Selection Using Parallel Processing of RBF Neural Networks. Int. Arab J. Inf. Technol., 2010, 7.1: 6-13.‏
[40]AWAD, Mohammed. Chaotic Time series Prediction using Wavelet Neural Network. Journal of Artificial Intelligence: Theory & Application, 2010, 1.3.‏
[41]MEMARIAN, Hadi; BALASUNDRAM, Siva Kumar. Comparison between multi-layer perceptron and radial basis function networks for sediment load estimation in a tropical watershed. Journal of Water Resource and Protection, 2012, 4.10: 870.‏
[42]JAIN, Ashu; VARSHNEY, Ashish Kumar; JOSHI, Umesh Chandra. Short-term water demand forecast modelling at IIT Kanpur using artificial neural networks. Water resources management, 2001, 15.5: 299-321.
[43]MSIZA, Ishmael S.; NELWAMONDO, Fulufhelo Vincent; MARWALA, Tshilidzi. Water demand prediction using artificial neural networks and support vector regression. 2008.‏
[44]ZOU, Guang-yu, et al. Urban water consumption forecast based on neural network model. INFORMATION AND CONTROL-SHENYANG-, 2004, 33: 364-368.‏
[45]DENG, Xiao, et al. Hourly Campus Water Demand Forecasting Using a Hybrid EEMD-Elman Neural Network Model. In: Sustainable Development of Water Resources and Hydraulic Engineering in China. Springer, Cham, 2019. p. 71-80.