Prediction of multi-sectoral longitudinal water withdrawals using hierarchical machine learning models
Open Access
- 31 August 2023
- journal article
- research article
- Published by IWA Publishing in Journal of Hydroinformatics
- Vol. 25 (6) , 2389-2405
Abstract
Accurate models of water withdrawal are crucial in anticipating the potential water use impacts of drought and climate change. Machine learning methods can simulate the complex, nonlinear relationship between water use and potential explanatory factors, but rarely incorporate the hierarchical nature of water use data. This work presents a novel approach for the prediction of water withdrawals across multiple usage sectors using an ensemble of models fit at different hierarchical levels. Models were fit at the facility and sectoral grouping levels, as well as across facility clusters defined by temporal water use characteristics. Using repeated holdout cross-validation and a dataset of over 300,000 observations of monthly water withdrawal across 1,509 facilities, it demonstrates that ensemble predictions led to statistically significant improvements in predictive performance in five of the eight sectors analyzed. The use of ensemble modeling resulted in lower predictive errors compared to facility models in 65% of facilities analyzed. The relative improvement gained by ensemble modeling was greatest for facilities with fewer observations and higher variance, indicating its potential value in predicting withdrawal for facilities with relatively short data records or data quality issues.Keywords
All Related Versions
Funding Information
- Virginia Polytechnic Institute and State University (NA)
This publication has 58 references indexed in Scilit:
- Insights into declining single‐family residential water demandsJournal AWWA, 2012
- Estimating and Verifying United States Households’ Potential to Conserve WaterJournal of Water Resources Planning and Management, 2012
- Urban water demand modeling: Review of concepts, methods, and organizing principlesWater Resources Research, 2011
- Fast Stable Restricted Maximum Likelihood and Marginal Likelihood Estimation of Semiparametric Generalized Linear ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Effects of Urban Spatial Structure, Sociodemographics, and Climate on Residential Water Consumption in Hillsboro, Oregon1Jawra Journal of the American Water Resources Association, 2010
- Seasonal Residential Water Demand Forecasting for Census TractsJournal of Water Resources Planning and Management, 2010
- Sensitivity of residential water consumption to variations in climate: An intraurban analysis of Phoenix, ArizonaWater Resources Research, 2008
- Estimating the Number of Clusters in a Data Set Via the Gap StatisticJournal of the Royal Statistical Society Series B: Statistical Methodology, 2001
- Global Water Resources: Vulnerability from Climate Change and Population GrowthScience, 2000
- A numerically stable dual method for solving strictly convex quadratic programsMathematical Programming, 1983