Vinyl Chloride Degradation Using Ozone-Based Advanced Oxidation Processes: Bridging Groundwater Treatment and Machine...

Water scarcity is fostering an urgent need to drive research into novel and synergistic water treatment approaches, with advanced oxidation processes (AOPs) emerging as a superior option for treating various contaminants. The spread of vinyl chloride (VC) through groundwater sources raises concerns for potable water production due to its toxic and carcinogenic properties. This study integrates ozone-based degradation experiments with data-driven modelling approaches to statistically characterize and predict VC removal under different water-matrix conditions. Ozonation alone enables partial removal of VC from two contaminated groundwater samples, while integration of O₃/H₂O₂ treatment further enhances the degradation efficacy (70-97%). Decreasing VC concentration below the parametric value of 0.5 µg/L requires application of the peroxone process or photodegradation by O₃/H₂O₂/UV for groundwater with higher levels of interfering compounds. Advanced machine learning models and ensemble methods were also tested to enhance predictive accuracy for target molecule degradation, considering water characteristics and treatment parameters as input features. An ensemble of Random Forest and Neural Network predictions yielded the best performance (R² = 0.99; Mean Squared Error = 10.8), demonstrating the effectiveness of ensemble approaches for complex chemical prediction tasks and highlighting areas for further refinement to improve interpretability and predictive consistency of AOP treatment outcomes. This study not only aligns with the current momentum in AI-assisted AOP research but also advances it by delivering a generalizable, reproducible, and interpretable ensemble model trained on experimentally diverse datasets.