Premium
Water Demand Forecasting Accuracy and Influencing Factors at Different Spatial Scales Using a Gradient Boosting Machine
Author(s) -
Xenochristou M.,
Hutton C.,
Hofman J.,
Kapelan Z.
Publication year - 2020
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/2019wr026304
Subject(s) - gradient boosting , boosting (machine learning) , mean absolute percentage error , water consumption , scale (ratio) , econometrics , statistics , consumption (sociology) , range (aeronautics) , mean absolute error , computer science , environmental science , mean squared error , mathematics , machine learning , geography , random forest , engineering , water resource management , cartography , social science , aerospace engineering , sociology
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.