An efficient water quality index forecasting and categorization using optimized Deep Capsule Crystal Edge Graph...

Area of Science:

• Environmental Science
• Artificial Intelligence
• Water Resource Management

Background:

• River water quality is crucial for public health and environmental sustainability.
• Contamination from economic activities poses a significant threat to freshwater supplies.
• Accurate water quality monitoring is essential for effective pollution control.

Purpose of the Study:

• To develop a novel and accurate method for estimating the Water Quality Index (WQI).
• To enhance water quality (WQ) assessment using advanced computational techniques.
• To provide a reliable tool for environmental authorities to manage river water quality.

Main Methods:

• Integration of Deep Capsule Crystal Edge Graph neural networks with optimization algorithms.
• Utilizing Hybrid Crested Porcupine Genghis Khan Shark Optimization for feature selection.
• Employing Greylag Goose Optimization Algorithm to fine-tune neural network parameters.

Main Results:

• Achieved a highly accurate WQI prediction with 99% accuracy.
• Demonstrated a low Mean Squared Error (MSE) of 6.7.
• The dual optimization framework significantly improved predictive performance.

Conclusions:

• The proposed method offers a robust and precise approach to river water quality assessment.
• This tool empowers environmental authorities for proactive pollution management and restoration evaluation.
• The research advances the field of water quality monitoring through innovative AI integration.