Predicting E. coli concentrations using limited qPCR deployments at Chicago beaches

Culture-based methods to measure Escherichia coli (E. coli) are used by beach administrators to inform whether bacteria levels represent an elevated risk to swimmers. Since results take up to 12 h, statistical models are used to forecast bacteria levels in lieu of test results; however they underestimate days with elevated fecal indicator bacteria levels. Quantitative polymerase chain reaction (qPCR) tests return results within 3 h but are 2–5 times more expensive than culture-based methods. This paper presents a prediction model which uses limited deployments of qPCR tested sites with inter-beach correlation to predict when bacteria will exceed acceptable thresholds. The model can be used to inform management decisions on when to warn residents or close beaches due to exposure to the bacteria. Using data from Chicago collected between 2006 and 2016, the model proposed in this paper increased sensitivity from 3.4 percent to 11.2 percent–a 230 percent increase. We find that the correlation between beaches are substantial enough to provide higher levels of precision and sensitivity to predictive models. Thus, limited deployments of qPCR testing can be used to deliver better predictions for beach administrators at lower cost and less complexity. Keywords: Random forest, Escherichia coli, Recreational water quality, Fecal indicator bacteria, Chicag