Enhanced iodinated disinfection byproducts formation in iodide/iodate-containing water undergoing UV-chloramine sequential disinfection: Machine learning-aided identification of reaction mechanisms

Restricted to the complex nature of dissolved organic matter (DOM) in various aquatic environments, the mechanisms of enhanced iodinated disinfection byproducts (I-DBPs) formation in water containing both I^- and IO₃^- (designated as I^-/IO₃^- in this study) during the ultraviolet (UV)-chloramine sequential disinfection process remains unclear. In this study, four machine learning (ML) models were established to predict I-DBP formation by using DOM and disinfection features as input variables. Extreme gradient boosting (XGB) algorithm outperformed the others in model development using synthetic waters and in cross-dataset generalization of surface waters. Shapley additive explanation (SHAP) analysis, partial dependence plots (PDPs), and individual conditional expectation (ICE) analysis were then employed to explain the models' workings and feature interactions, aiding in identification and quantification of underlying mechanisms. A type of DOM component (namely DC_b) was found as the greatest contributor and identified as reduced quinones associated with broken-down lignin within higher plant-derived fulvic substance, serving as precursors and electron shuttles for I-DBP formation. Based on the interactional effects acquired from explanation results, the ejection of e^-_aq from excited DOM and pre-existing I^- in the I^-/IO₃^- system were identified responsible for the enhanced generation of I-DBPs compared to that in the I^- or IO₃^- alone systems; extra DOM scavenged reactive iodine species (RIS), contributing to a limited enhancement. These findings and the methodology developed here together enhance our understanding of the mechanisms how DOM limitedly promotes I-DBP formation during UV-chloramine sequential disinfection of I^-/IO₃^--containing water and facilitate effective online monitoring in the future.