Urban water demand forecasting and uncertainty assessment using ensemble wavelet-bootstrap-neural network models

Abstract

[1] A new hybrid wavelet-bootstrap-neural network (WBNN) model is proposed in this study for short term (1, 3, and 5 day; 1 and 2 week; and 1 and 2 month) urban water demand forecasting. The new method was tested using data from the city of Montreal in Canada. The performance of the WBNN method was compared with the autoregressive integrated moving average (ARIMA) and autoregressive integrated moving average model with exogenous input variables (ARIMAX), traditional NNs, wavelet analysis-based NNs (WNN), bootstrap-based NNs (BNN), and a simple na€ ıve persistence index model. The WBNN model was developed as an ensemble of several NNs built using bootstrap resamples of wavelet subtime series instead of raw data sets. The results demonstrated that the hybrid WBNN and WNN models produced significantly more accurate forecasting results than the traditional NN, BNN, ARIMA, and ARIMAX models. It was also found that the WBNN model reduces the uncertainty associated with the forecasts, and the performance of WBNN forecasted confidence bands was found to be more accurate and reliable than BNN forecasted confidence bands. It was found in this study that maximum temperature and total precipitation improved the accuracy of water demand forecasts using wavelet analysis. The performance of WBNN models was also compared for different numbers of bootstrap resamples (i.e., 25, 50, 100, 200, and 500) and it was found that WBNN models produced optimum results with different numbers of bootstrap resamples for different lead time forecasts with considerable variability.Citation: Tiwari, M. K., and J. Adamowski (2013), Urban water demand forecasting and uncertainty assessment using ensemble wavelet-bootstrap-neural network models, Water Resour. Res., 49,

Wavelet-Based Hydrological Time Series Forecasting

“…Various studies have demonstrated the effectiveness of this practice due to the ability of wavelet analysis (Wang and Ding 2003;Sang 2013;Nourani et al 2014;Tiwari and Adamowski 2013;Rathinasamy et al 2013). However, forecasting results of hydrological extremes (including both maximum and minimum) have not been obviously improved in many case studies.…”

Gene Expression Programming Coupled with Unsupervised Learning: A Two-Stage Learning Process in Multi-Scale, Short-Term Water Demand Forecasts

“…The majority of recent research uses data-driven techniques with learning algorithms for predictive analysis. Artificial neural networks (ANN) are probably the most popular ones [17][18][19], also most studies are done with slight changes in such models when pre-processing the data or changes in the structures of the defined ANN models. One study combined ANN with the wavelet bootstrapping machine learning approach as a hybrid model to improve performance of the models by pre-processing the data [20].…”

Evaluating the Impact of Meteorological Factors on Water Demand in the Las Vegas Valley Using Time-Series Analysis: 1990–2014

“…Maidment et al [4] and Tiwari et al [20] use a time-series model to describe monthly water use. Maidment et al [4] described that water consumption is mainly composed of four components: (1) a long-term trend due to policies and socio-economic variables, (2) seasonal variation from the annual cycle of weather, (3) autocorrelation due to perpetuation of past water use variation, and (4) climatic correlation due to rainfall, evaporation, and air temperature.…”