Optimizing water quality with data analytics and machine learning

Liang, B; Li, Z; Tian, H; Liang, S; Wang, Y; Chen, F

Optimizing water quality with data analytics and machine learning

Liang, B

Li, Z Tian, H Liang, S Wang, Y Chen, F

Permalink

Publisher:: Wiley
Publication Type:: Chapter
Citation:: Advances in Data Science and Analytics: Concepts and Paradigms, 2023, pp. 39-65
Issue Date:: 2023-10-31

Closed Access

	Filename	Description	Size
	20410086_10129832340005671.pdf	Published version	2.44 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liang, B https://orcid.org/0000-0002-6605-2167
dc.contributor.author	Li, Z
dc.contributor.author	Tian, H
dc.contributor.author	Liang, S
dc.contributor.author	Wang, Y
dc.contributor.author	Chen, F https://orcid.org/0000-0003-4971-8729
dc.date.accessioned	2023-03-11T19:06:33Z
dc.date.available	2023-03-11T19:06:33Z
dc.date.issued	2023-10-31
dc.identifier.citation	Advances in Data Science and Analytics: Concepts and Paradigms, 2023, pp. 39-65
dc.identifier.isbn	9781119791881
dc.identifier.uri	http://hdl.handle.net/10453/167051
dc.description.abstract	It is critical to continuously maintain the high quality of drinking water in water distribution network management. However, it remains challenging to predict water demand and optimize dosage to ensure safe drinking water. This paper details solutions that utilize data analytics and machine learning to provide water demand forecasting and chemical dosing optimization. Key environmental factors are used to build a Bayesian linear model to predict the water demand for each supply zone. To ensure safe drinking water, chlorine residual is one of the most important indicators. However, as the water age becomes high, the chlorine residual decays very fast. Thus, we provide a data-driven solution to determine the chlorine set points and optimize the ammonia dosage for reservoirs. The optimization results can determine the set point of the dosage devices to be installed at reservoirs. Evaluation results demonstrate that the solutions achieve reasonably consistent results.
dc.format.extent	14
dc.language	en
dc.publisher	Wiley
dc.relation.ispartof	Advances in Data Science and Analytics: Concepts and Paradigms
dc.relation.isbasedon	10.1002/9781119792826.ch3
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Optimizing water quality with data analytics and machine learning
dc.type	Chapter
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-03-11T19:06:30Z
pubs.place-of-publication	USA
pubs.publication-status	Published
dc.location	USA

Abstract:

It is critical to continuously maintain the high quality of drinking water in water distribution network management. However, it remains challenging to predict water demand and optimize dosage to ensure safe drinking water. This paper details solutions that utilize data analytics and machine learning to provide water demand forecasting and chemical dosing optimization. Key environmental factors are used to build a Bayesian linear model to predict the water demand for each supply zone. To ensure safe drinking water, chlorine residual is one of the most important indicators. However, as the water age becomes high, the chlorine residual decays very fast. Thus, we provide a data-driven solution to determine the chlorine set points and optimize the ammonia dosage for reservoirs. The optimization results can determine the set point of the dosage devices to be installed at reservoirs. Evaluation results demonstrate that the solutions achieve reasonably consistent results.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167051