Identifying the acute toxicity of contaminated sediments using machine learning models.

Ecological risk assessment of contaminated sediment has become a fundamental component of water quality management programs, supporting decision-making for management actions or prompting additional investigations. In this study, we proposed a machine learning (ML)-based approach to assess the ecological risk of contaminated sediment as an alternative to existing index-based methods and costly toxicity testing. The performance of three widely used index-based methods (the pollution load index, potential ecological risk index, and mean probable effect concentration) and three ML algorithms (random forest, support vector machine, and extreme gradient boosting [XGB]) were compared in their prediction of sediment toxicity using 327 nationwide data sets from Korea consisting of 14 sediment quality parameters and sediment toxicity testing data. We also compared the performances of classifiers and regressors in predicting the toxicity for each of RF, SVM, and XGB algorithms. For all algorithms, the classifiers poorly classified toxic and non-toxic samples due to limited information on the sediment composition and the small training dataset. The regressors with a given classification threshold provided better classification, with the XGB regressor outperforming the other models in the classification. A permutation feature importance analysis revealed that Cr, Cu, Pb, and Zn were major contributors to toxicity prediction. The ML-based approach has the potential to be even more useful in the future with the expected increase in available sediment data.

Optimal allocation and operation of sewer monitoring sites for wastewater-based disease surveillance: A methodological proposal.

Wastewater-based epidemiology (WBE) is drawing increasing attention as a promising tool for an early warning of emerging infectious diseases such as COVID-19. This study demonstrated the utility of a spatial bisection method (SBM) and a global optimization algorithm (i.e., genetic algorithm, GA), to support better designing and operating a WBE program for disease surveillance and source identification. The performances of SBM and GA were compared in determining the optimal locations of sewer monitoring manholes to minimize the difference among the effective spatial monitoring scales of the selected manholes. While GA was more flexible in determining the spatial resolution of the monitoring areas, SBM allows stepwise selection of optimal sampling manholes with equiareal subcatchments and lowers computational cost. Upon detecting disease outbreaks at a regular sewer monitoring site, additional manholes within the catchment can be selected and monitored to identify source areas with a required spatial resolution. SBM offered an efficient method for rapidly searching for the optimal locations of additional sampling manholes to identify the source areas. This study provides strategic and technical elements of WBE including sampling site selection with required spatial resolution and a source identification method.