An ensemble stacked model with bias correction for improved water demand forecasting

Maria Xenochristou, Zoran Kapelan

Research output: Contribution to journalArticleScientificpeer-review

6 Citations (Scopus)
1 Downloads (Pure)


Water demand forecasting is an essential task for water utilities, with increasing importance due to future societal and environmental changes. This paper suggests a new methodology for water demand forecasting, based on model stacking and bias correction that predicts daily demands for groups of ~120 properties. This methodology is compared to a number of models (Artificial Neural Networks–ANNs, Generalised Linear Models–GLMs, Random Forests–RFs, Gradient Boosting Machines–GBMs, Extreme Gradient Boosting–XGBoost, and Deep Neural Networks–DNNs), using real consumption data from the UK, collected at 15–30 minute intervals from 1,793 properties. Results show that the newly proposed stacked model that comprises of RFs, GBMs, DNNs, and GLMs consistently outperformed other water demand forecasting techniques (peak R2 = 74.1%). The stacked model’s accuracy on peak consumption days further improved by applying a bias correction method on the model’s output.

Original languageEnglish
Pages (from-to)212-223
Number of pages12
JournalUrban Water Journal
Issue number3
Publication statusPublished - 2020


  • bias correction
  • deep neural networks
  • gradient boosting machines
  • machine learning
  • model stacking
  • Water demand forecasting

Fingerprint Dive into the research topics of 'An ensemble stacked model with bias correction for improved water demand forecasting'. Together they form a unique fingerprint.

Cite this