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

Abstract

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.

Data Driven Through Machine Learning on Electricity Production by Anode Respiring Bacteria Using the Microbial Fuel Cells

“…The enhanced production of biofuels will result in greater production of electricity. It will also help in treatment of wastewater which will eventually help in meeting the needs of water scarce regions [46]. In future, scientists aim to set low cost high production reactors that will yield in high output of current.…”

Water Consumption variation in Latin America due to COVID-19 Pandemic

“…As water utilities require consumption predictions for operational reasons and updating pricing policies, ANN are one of the principal approaches used to predict water demand [12]. ANN imitate the human brain by performing non-linear calculations in a certain number of neurons, which receive input values that are transformed and transferred to other neurons or the output [13]. The great advantage of ANN is learning based on initial observations and producing equivalent outputs with new input data.…”

“…Neural networks can work with a single or multiple layers. Several learning algorithms allow the communication between neurons to determine the weights, which are values assigned to every variable from the input layer to the hidden layer [13]. The weights' modification allows the network to adapt to reduce the error between the expected output and the result from the network.…”

Study on the Optimization of Wujiang’s Water Resources by Combining the Quota Method and NSGA-II Algorithm

“…The literature on water demand forecasting using the ANN model frequently evaluates the predictive performance between regression and neural network models [21][22][23][24][25][26][27][28]. Awad et al employed two practical ANN models to forecast the future water demand of Jenin City in Palestine, achieving relatively accurate predictions [29]. Adamowski et al compared multivariate linear regression, time series analysis, and ANN forecasting models to analyze Ottawa, Canada's water demand data.…”