Extended linear and non-linear auto-regressive models for forecasting the urban water consumption of a fast-growing city in an arid region

Abstract

Accurate water consumption forecasting models are required for fast-growing cities in arid regions. In the present study, two forecasting models are proposed for urban-water consumption using extended Auto-Regressive Integrated Moving Average (ARIMA) and Nonlinear Auto-Regressive Exogenous (NARX) methods. Various extension of these models by adding new forecaster factors were tested to find superior linear and nonlinear models. The ARIMA and NARX model accuracy with and without additional forecaster factors (minimum, maximum and mean temperature, precipitation, mean relative humidity, sunshine hours, mean dew point temperature, mean wind speed, and population) were compared using accuracy indices. The ARIMA model which includes sunny hour in addition to the base model predictors was selected as the superior linear model and also the model NARX which includes sunny hours and population in addition to the base model’s predictors was selected as the superior nonlinear model. This infers that sunny hour has linear performance and population predictor has non-linear performance in forecasting water consumption. This shows adding sunny hours and population as forecaster factors can robust forecasting performance considerably. By extending the models with these additional forecasting factors, the precision of daily water consumption forecasts can be improved for providing a better urban water supply.