Univariate Long-Term Municipal Water Demand Forecasting
This work addresses water demand forecasting for municipal management, but it is incremental as it applies existing methods to a specific dataset.
The study tackled forecasting citywide water consumption in London, Canada, by evaluating multiple models and found Facebook's Prophet achieved a mean absolute percentage error of 2.51% with advantages like interpretability and handling missing data.
This study describes an investigation into the modelling of citywide water consumption in London, Canada. Multiple modelling techniques were evaluated for the task of univariate time series forecasting with water consumption, including linear regression, Facebook's Prophet method, recurrent neural networks, and convolutional neural networks. Prophet was identified as the model of choice, having achieved a mean absolute percentage error of 2.51%, averaged across a 5-fold cross validation. Prophet was also found to have other advantages deemed valuable to water demand management stakeholders, including inherent interpretability and graceful handling of missing data. The implementation for the methods described in this paper has been open sourced, as they may be adaptable by other municipalities.