scholarly journals Weekly urban water demand forecasting using a hybrid wavelet–bootstrap–artificial neural network approach

2014 ◽  
Vol 46 (3) ◽  
pp. 197-204
Author(s):  
Kaz Adamowski ◽  
Jan F. Adamowski ◽  
Ousmane Seidou ◽  
Bogdan Ozga-Zieliński
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Demand ◽  
Demand Forecasting ◽  
Urban Water ◽  
Neural Network Approach ◽  
Water Demand Forecasting ◽  
Urban Water Demand ◽  
Artificial Neural ◽  
Artificial Neural Network Approach

Abstract Weekly urban water demand forecasting using a hybrid wavelet-bootstrap-artificial neural network approach. This study developed a hybrid wavelet-bootstrap-artificial neural network (WBANN) model for weekly (one week) urban water demand forecasting in situations with limited data availability. The proposed WBANN method is aimed at improving the accuracy and reliability of water demand forecasting. Daily maximum temperature, total precipitation and water demand data for almost three years were used in this study. It was concluded that the hybrid WBANN model was more accurate compared to the ANN, BANN and WANN methods, and can be applied successfully for operational water demand forecasting. The WBANN model simulated peak water demand very effectively. The better performance of the WBANN model indicated that wavelet analysis significantly improved the model’s performance, whereas the bootstrap technique improved the reliability of forecasts by producing ensemble forecasts. The WBANN model was also found to be effective in assessing the uncertainty associated with water demand forecasts in terms of confidence bands; this can be helpful in operational water demand forecasting.

scholarly journals Artificial Neural Networks for Urban Water Demand Forecasting: A Case Study

2019 ◽  
Vol 1284 ◽  
pp. 012004 ◽  
Author(s):  
Leandro L Lorente-Leyva ◽  
Jairo F Pavón-Valencia ◽  
Yakcleem Montero-Santos ◽  
Israel D Herrera-Granda ◽  
Erick P Herrera-Granda ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Water Demand ◽  
Demand Forecasting ◽  
Urban Water ◽  
Water Demand Forecasting ◽  
Urban Water Demand ◽  
Artificial Neural

scholarly journals Short-term water demand predictions coupling an Artificial Neural Network model and a Genetic Algorithm

2021 ◽  
Author(s):  
Majid Gholami Shirkoohi ◽  
Mouna Doghri ◽  
Sophie Duchesne
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Water Demand ◽  
Urban Water ◽  
Ann Model ◽  
Short Term ◽  
Urban Water Demand ◽  
Artificial Neural ◽  
Mean Square Errors

Abstract The application of artificial neural network (ANN) models for short-term (15 min) urban water demand predictions is evaluated. Optimization of the ANN model's hyperparameters with a Genetic Algorithm (GA) and use of a growing window approach for training the model are also evaluated. The results are compared to those of commonly used time series models, namely the Autoregressive Integrated Moving Average (ARIMA) model and a pattern-based model. The evaluations are based on data sets from two Canadian cities, providing 15 minute water consumption records over respectively 5 years and 23 months, with a respective mean water demand of 14,560 and 887 m3/d. The GA optimized ANN model performed better than the other models, with Nash-Sutcliffe Efficiencies of 0.91 and 0.83, and Relative Root Mean Square Errors of 6 and 16% for City 1 and City 2, respectively. The results of this study indicate that the optimization of the hyperparameters of an ANN model can lead to better 15 min urban water demand predictions, which are useful for many real time control applications, such as dynamic pressure control.

Sign in / Sign up

Export Citation Format

Share Document