A water use study was conducted to understand the drivers of historical water use in the Providence Water Supply Board network (the service area of Providence Water Supply Board and its wholesale customers) and to forecast future water use in the same network. A cubist regression model was developed to model daily per capita water use rates for three water use categories in each of the 10 public water suppliers within this network using data from 2005-2021. The three water use categories are domestic water use, commercial water use, and industrial water use. This cubist regression model was then used to forecast water use in 2030 and 2040 based on simulated future scenarios of low and high climate warming; low and high economic growth; and low, medium, and high population growth. This data release contains the input data used to develop the cubist regression model, the simulated future scenarios, the model estimates generated by the model, and an R script that creates the cubist regression model.