Developing a Model-based Drinking Water Decision Support System Featuring Remote Sensing and Fast Learning Techniques

Area of Science:

• Environmental Engineering
• Water Resource Management
• Data Science

Background:

• Drinking water treatment requires adaptive strategies to manage natural and anthropogenic water quality variations.
• Integrated sensing, monitoring, and modeling technologies are crucial for providing early warnings to plant operators.

Purpose of the Study:

• To review technical methods for water quality monitoring and develop a model-based decision support system (DSS).
• To aid water treatment operations through source water impact analysis and provide spatiotemporal water quality insights.

Main Methods:

• Literature review of technical methods for water quality management.
• Development of a model-based DSS incorporating remote sensing and fast learning techniques.
• Case study assessment at a water treatment plant in Las Vegas, USA.

Main Results:

• The DSS provides visual depictions of spatiotemporal water quality variations in source water.
• The system forecasts water quality trends one day ahead and nowcasts current intake water quality.
• The DSS assists in assessing finished water quality against treatment objectives.

Conclusions:

• The developed model-based DSS effectively supports drinking water treatment operations by analyzing source water impacts.
• Remote sensing and fast learning techniques enable user-friendly application and accurate water quality forecasting.
• The system enhances operational decision-making for maintaining drinking water quality standards.