Algorithm for monitoring water quality parameters in optical systems based on artificial intelligence data mining

Area of Science:

• Environmental Science
• Data Science
• Optical Engineering

Background:

• Increasing water pollution necessitates advanced Water Quality Monitoring (WQM) systems.
• Traditional WQM methods suffer from slow speeds, long monitoring times, operational complexity, and instability.
• Existing methods can produce secondary pollutants and delay timely detection of water contamination.

Purpose of the Study:

• To investigate artificial intelligence (AI) data mining optical systems for enhanced WQM.
• To develop and improve AI-based systems for more effective water quality detection.
• To compare the performance of AI-driven WQM against traditional approaches.

Main Methods:

• Application of an AI data mining system integrated with optical technology for water quality parameter detection.
• Experimental validation using 10 water plants to compare AI-WQM with traditional WQM.
• Evaluation metrics included WQM time, accuracy, sensitivity, and protective performance.

Main Results:

• AI-based optical systems achieved an average WQM time of 2.7 days.
• Average accuracy reached 85.95%, with an average sensitivity of 84.19%.
• The average protective score was 8.46 points, indicating superior performance.

Conclusions:

• AI data mining optical technology demonstrates vital significance and value for WQM.
• The developed AI system offers substantial improvements over traditional WQM methods.
• This technology is crucial for ensuring water quality safety in the face of environmental pollution.