It is commonly assumed that the persistence model, using day-old monitoring results, will provide accurate estimates of real-time bacteriological concentrations in beach water. However, the persistence model frequently provides incorrect results.
This study: 1. develops a site-specific predictive model, based on factors significantly influencing water quality at Beachway Park; 2. determines the feasibility of the site-specific predictive model for use in accurately predicting
near real-time E. coli levels.
A site-specific predictive model, developed for Beachway Park, was evaluated and the results were compared to the persistence model. This critical performance evaluation helped to identify the inherent inaccuracy of the persistence model for Beachway Park, which renders it an unacceptable approach for safeguarding public health from recreational water-borne illnesses. The persistence model, supplemented with a site-specific predictive model, is recommended as a feasible method to accurately predict bacterial levels in water on a near real-time basis.
Development of Predictive Models for “Very Poor” Beach Water Quality Gradings Using Class-Imbalance Learning