Optimizing water quality with data analytics and machine learning
- 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 |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
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: