3,918
Views
35
CrossRef citations to date
0
Altmetric
Research Articles

Applying human mobility and water consumption data for short-term water demand forecasting using classical and machine learning models

ORCID Icon, ORCID Icon, ORCID Icon, ORCID Icon, ORCID Icon & ORCID Icon
Pages 32-42 | Received 22 May 2019, Accepted 20 Feb 2020, Published online: 10 Mar 2020
 

ABSTRACT

Water demand forecasting is a crucial task in the efficient management of the water supply system. This paper compares classical and adapted machine learning algorithms used for water usage predictions including ARIMA, support vector regression, random forests and extremely randomized trees. These models were enriched with human mobility data to improve the predictive power of water demand forecasting. Furthermore, a framework for processing mobility data into time-series correlated with water usage data is proposed. This study uses 51 days of water consumption readings and over 7 million geolocated mobility records from urban areas. Results show that using human mobility data improves water demand prediction. The best forecasting algorithm employing a random forest method achieved 90.4% accuracy (measured by the mean absolute percentage error) and is better by 1% than the same algorithm using only water data, while classic ARIMA approach achieved 90.0%. The Blind (copying) prediction achieved 85.1% of accuracy.

Acknowledgements

This work was carried out within the Climate-KIC’s Pathfinder Programme under Grant [number TC2018A_2.1.3-CHASE_P127-1A] supported by the EIT, a body of the European Union. The paper presents part of the results of the project CHASE: Citizens’ behaviour patterns for smart utilities and service management. The authors wish to thank the Selectivv Mobile House company and Municipal Water and Sewerage Company (MPWiK) for sharing the data for this study.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Supplementary material

Supplemetary data for this article can be accessed here.

Additional information

Funding

This work was supported by the Climate-KIC [Citizens’ behaviour patterns for smart utilities] under Grant [number TC2018A_2.1.3-CHASE_P127-1A].