Short-Term Urban Water Demand Prediction Considering Weather Factors

Abstract

Accurate and reliable forecasting plays a key role in the planning and designing of municipal water supply infrastructures. Recent studies related to water demand prediction have shown that water demand is driven by weather variables, but the results do not clearly show to what extent. The principal aim of this research was to better understand the effects of weather variables on water demand. Additionally, it aimed to offer an appropriate and reliable technique to predict municipal water demand by using the Gravitational Search Algorithm (GSA) and Backtracking Search Algorithm (BSA) with Artificial Neural Network (ANN). Moreover, eight weather factors were adopted to evaluate their impact on the water demand. The principal findings of this research are that the hybrid GSA-ANN (Agent=40) model is superior in terms of fitness function (based on RMSE) for yearly and seasonal phases. In addition, it is evidently clear from the findings that the GSA-ANN model has the ability to simulate both seasonal and yearly patterns for daily data water consumption.

A Method for Predicting Long-Term Municipal Water Demands Under Climate Change

“…Previous studies have demonstrated the power of ANN to produce good non-linear models for urban water demand (Toth et al, 2018). However, unlike other applications of hydrology, ANN has not been extensively used in municipal water demand modelling (Zubaidi et al, 2018b), even when it has proven to be able to deal with a large number of input and output patterns, and is capable of handling different complex nonlinear environmental problems, making it appropriate for long-term prediction modelling (Mutlu et al, 2008).…”

Short-Term Forecasting of Household Water Demand in the UK Using an Interpretable Machine Learning Approach

“…Machine learning models are able to provide accurate water demand forecasts (Herrera et al, 2010;Anele et al, 2017;Chen et al, 2017;Zubaidi et al, 2018) but they have been 76…”

Urban Water Demand Prediction for a City That Suffers from Climate Change and Population Growth: Gauteng Province Case Study

“…The training process of the ANN model is repeated a large number of times over an epoch (i.e., 1000 iterations) until the error between the observed and simulated urban water reaches its minimum. The data were split randomly into three sets 70% for training, 15% for testing and 15% for validation, as previously conducted by Zubaidi et al [21] and Zubaidi et al [35]. As in Gharghan et al [36], cross-validation was used to ensure the generalization capabilities of the model and avoid overfitting, and the stopping criterion for training was done using the root mean square error (RMSE) as an objective function (i.e., error not more than the value of RMSE in the testing stage).…”

“…However, there are cases where conventional methods performed as well as or even better than ANN in terms of accuracy, such as Li et al [27]. The latter can be due to a number of reasons, for example that the models falling into a local instead of the global minimum, leading to a sub-optimal solution [34], or not using the right network design or hyperparameters for training the neural network [35]. Hence, in order to avoid these drawbacks, different approaches have been combined with the ANN model, such as heuristic algorithms [36], and different hybrid models have been proposed.…”

“…From the application area viewpoint, another significant consideration is the selection of the best model input that drives the dependent variable [50,51]. Several techniques were applied in different studies, such as principal component analysis (PCA) [52,53], variance inflation factor (VIF) [21,35] and mutual information (MI) [54,55]. In this study, the mutual information technique was used to select the best scenario of model input based on several historical observed water consumption data.…”