Applying Kohonen self-organizing map as a software sensor to predict biochemical oxygen demand.

Area of Science:

• Environmental Science
• Water Quality Monitoring
• Wastewater Treatment

Background:

• Biochemical oxygen demand (BOD5) is crucial for assessing water pollution and wastewater treatability.
• Traditional BOD5 bioassays require 5 days, hindering real-time process control and decision-making.
• Previous rapid biosensor development for BOD5 estimation has faced limitations.

Purpose of the Study:

• To develop a rapid prediction method for BOD5 using Kohonen self-organizing map (KSOM)-based software sensors.
• To overcome the time constraints associated with conventional BOD5 bioassays.
• To enable real-time decision-making in water and wastewater management.

Main Methods:

• Development of a Kohonen self-organizing map (KSOM) algorithm.
• Implementation of KSOM as a software sensor for BOD5 prediction.
• Validation of KSOM-based BOD5 estimates against conventional bioassay results.

Main Results:

• KSOM-based software sensors demonstrated rapid prediction of BOD5.
• The developed method achieved good agreement with traditional BOD5 bioassay measurements.
• The software sensor provides a viable alternative for timely water quality assessment.

Conclusions:

• Kohonen self-organizing map-based software sensors offer a promising solution for rapid BOD5 prediction.
• This approach facilitates timely intervention and cost savings in water and wastewater treatment.
• The study highlights the potential for AI-driven tools in environmental monitoring and process control.