Water Demand Forecasting Accuracy and Influencing Factors at Different Spatial Scales Using a Gradient Boosting Machine. Issue 8 (20th August 2020)

• Record Type: Journal Article
• Authors: Xenochristou, M.; Hutton, C.; Hofman, J.; Kapelan, Z.
• Is Part Of: Water resources research. Volume 56:Issue 8(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-08-20
• Subjects: water demand forecasting -- Gradient Boosting Machines -- spatial scales -- smart demand data -- weather influence; Hydrology -- Periodicals; 333.91
• DOI: 10.1029/2019WR026304
• Languages: English
• ISSNs: 0043-1397

Abstract

Abstract: Understanding, comparing, and accurately predicting water demand at different spatial scales is an important goal that will allow effective targeting of the appropriate operational and conservation efforts under an uncertain future. This study uses data relating to water consumption available at the household level, as well as postcode locations, household characteristics, and weather data in order to identify the relationships between spatial scale, influencing factors, and forecasting accuracy. For this purpose, a Gradient Boosting Machine (GBM) is used to predict water demand 1–7 days into the future. Results show an exponential decay in prediction accuracy from a Mean Absolute Percentage Error (MAPE) of 3.2% to 17%, for a reduction in group size from 600 to 5 households. Adding explanatory variables to the forecasting model reduces the MAPE up to 20% for the peak days and smaller household groups (20–56 households), whereas for larger aggregations of properties (100–804 households), the range of improvement is much smaller (up to 1.2%). Results also show that certain types of input variables (past consumption and household characteristics) become more important for smaller aggregations of properties, whereas others (weather data) become less important. Key Points: The Mean Absolute Percentage Error increases exponentially from 3.2% to 17% for a reduction in group size from 600 to 5 households Past consumption data and household characteristics are important predictors of consumption for smaller aggregations of properties The weather influence on consumption only becomes visible for larger aggregations of properties