Hydroxyl radical (^•OH) generated during catalytic ozonation plays a central role in the degradation of ozone (O₃)-resistant micropollutants (MPs). Accurate quantification of ^•OH exposure (∫[^•OH]dt), which serves as a key indicator of oxidative capacity under defined conditions, is crucial for effective control of MPs in catalytic ozonation. However, direct in-field measurement of ∫[^•OH]dt with a ^•OH probe compound is not practical. This study explores the application of machine learning (ML) models to predict ∫[^•OH]dt in catalytic ozonation using readily available input variables. Using graphitic carbon nitride as a representative catalyst, catalytic ozonation experiments were conducted to quantify ∫[^•OH]dt (the output variable) under varying operational (O₃ dose, catalyst dose, contact time) and water quality (TOC, pH) parameters (input variables). Two ML models were constructed: Model-1 predicted only the final ∫[^•OH]dt after full O₃ consumption, whereas Model-2 included contact time as an added variable to estimate ∫[^•OH]dt in a time-dependent manner. Both models demonstrated strong predictive performance. More importantly, Model-2 effectively captured the temporal profile of ∫[^•OH]dt and yielded greater accuracy for final ∫[^•OH]dt estimates by more comprehensively reflecting the effects of each variable. The model-predicted ∫[^•OH]dt values were subsequently used for simulating MP degradation, which corresponded closely with experimental observations for multiple O₃-resistant MPs. These results demonstrate that ∫[^•OH]dt predicted from readily obtained parameters can provide a robust indicator for MP removal, and that ML-powered methods present a valuable framework for optimizing catalytic ozonation systems.