Prediction of Escherichia coli concentration from wetting properties of beach sand using machine learning models

Abstract

The presence of Escherichia coli (E. coli) in beach sand is directly related to public health outcomes. Physicochemical and wetting properties of sand influence the survival and proliferation of these indicator bacteria. In this study, we aim to predict E. coli concentration using some of these properties including zeta potential, moisture content, BET surface area, BET pore radius, state of sand, processing temperature, and water contact angle of the beach sand. We have developed five Machine Learning regression models including the Artificial Neural Network (ANN), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Random Forest (RF), and k-Nearest Neighbors (KNN) for this. ANN outperformed other models in predicting E. coli concentration. In the data-driven analysis, the state of sand, processing temperature, and the contact angle presenting the wettability of the sand are identified as the most crucial parameters in predicting E. coli concentration.