Water Quality Indicator Interval Prediction in Wastewater Treatment Process Based on the Improved BES-LSSVM Algorithm

Area of Science:

• Environmental Science
• Water Quality Management
• Computational Chemistry

Background:

• Effective monitoring of wastewater treatment plant performance relies on accurate prediction of key effluent indicators like biochemical oxygen demand (BOD) and ammonia nitrogen (NH3-N).
• Existing prediction models often face challenges in accuracy, computational efficiency, and handling data uncertainty.

Purpose of the Study:

• To develop a novel interval prediction method for effluent water quality indicators (BOD and NH3-N).
• To improve the accuracy and efficiency of wastewater treatment plant performance monitoring and control.

Main Methods:

• Data pre-processing and gray correlation analysis to identify key predictive variables for BOD and NH3-N.
• Development of an improved bald eagle search-least squares support vector machine (IBES-LSSVM) algorithm for prediction.
• Application of interval estimation to quantify model uncertainty.

Main Results:

• The proposed IBES-LSSVM method demonstrated high prediction accuracy for BOD and NH3-N.
• The approach significantly reduced computational time compared to existing algorithms.
• The interval estimation effectively analyzed the uncertainty of the LSSVM model.

Conclusions:

• The novel interval prediction method offers a robust and efficient solution for wastewater effluent quality monitoring.
• The IBES-LSSVM algorithm provides a reliable tool for predicting key water quality parameters with quantifiable uncertainty.
• This approach facilitates better control and management of wastewater treatment processes.