The presence of Escherichia coli in beach sand is directly related to public health outcomes. The physicochemical and wetting properties of sand influence the survival and proliferation of these indicator bacteria. This study is aimed at predicting E. coli concentrations using some of these properties, including the zeta potential, moisture content, Brunauer–Emmett–Teller (BET) surface area, BET pore radius, state of sand, processing temperature and water contact angle of beach sand. For this, the authors developed five machine learning regression models – namely, artificial neural network, support vector machine, gradient boosting machine, random forest and k-nearest neighbors. ANN outperformed other models in predicting E. coli concentrations. In the data-driven analysis, the state of sand, processing temperature and the contact angle representing the wettability of the sand are identified as the most crucial parameters in predicting E. coli concentrations.

中文翻译：

---

使用机器学习预测海滩沙子润湿的大肠杆菌浓度

海滩沙子中大肠杆菌的存在与公共卫生结果直接相关。沙子的物理化学和润湿特性影响这些指示细菌的存活和增殖。本研究旨在使用其中一些特性预测大肠杆菌浓度，包括 zeta 电位、水分含量、Brunauer-Emmett-Teller (BET) 表面积、BET 孔隙半径、沙子状态、加工温度和水接触角海滩沙子。为此，作者开发了五种机器学习回归模型——即人工神经网络、支持向量机、梯度提升机、随机森林和k最近邻。人工神经网络在预测大肠杆菌方面优于其他模型浓度。在数据驱动的分析中，沙子的状态、加工温度和表示沙子润湿性的接触角被确定为预测大肠杆菌浓度的最关键参数。