Fluorescence-informed water quality prediction in water distribution systems

Abstract Conventional drinking water monitoring relies on laboratory-based chemical and microbiological analyses that are often time intensive. This study evaluates a rapid optical alternative by integrating excitation–emission matrix (EEM) fluorescence spectroscopy, parallel factor analysis (PARAFAC), and machine learning to predict intact cell count (ICC) within a chlorinated drinking water distribution system. A full scale network in the Okanagan Valley, Canada was monitored, and fluorescence-derived dissolved organic matter (DOM) components were used as predictors in tree-based classification models. Fluorescence alone showed moderate skill in predicting ICC, but incorporating contextual factors (chlorine residual and turbidity) markedly improved performance. The ICC models could categorically distinguish microbial levels within the distribution system, though absolute accuracy declined at sites not seen during training, indicating a need for site-specific calibration. Notably, this work is the first to assess fluorescence-based metrics for determining ICC in drinking water distribution systems. The findings demonstrate that a unified fluorescence-PARAFAC approach can provide timely alternative measures for water quality, as it shows promise for microbial risk indication when augmented with operational data. Overall, the work highlights the potential of fluorescence-informed machine learning to bridge conventional chemical and microbiological monitoring, offering a pathway toward more responsive water quality management.