Explainable Machine Learning for Methylene Blue Removal Under Irradiation: Assessing Nominal Cu-Loading in AC@NiO

The time-dependent removal performance under irradiation of activated-carbon-supported nickel oxide (AC@NiO) samples containing nominal Cu-loadings of 0%, 3%, 5%, 7.5%, and 10% was examined using experimental concentration data and an explainable machine-learning (ML) framework. Reaction time and nominal Cu-loading were used as predictors. Preliminary screening with $C_t/C_0$ as the common target showed that Random Forest (RF) outperformed K-Nearest Neighbors, Multi-Layer Perceptron, and Support Vector Regression. The target-specific regularized RF models were fitted for $C_t/C_0$ and $\ln (C_0/C_t)$; normalized apparent removal efficiency was derived deterministically as $\eta /100=1-C_t/C_0$. Across 10 controlled random seeds, the mean leave-one-out cross-validation $R^2$ values were $0.9691\pm 0.0013$ for $C_t/C_0$ and the derived $\eta /100$, and $0.9152\pm 0.0090$ for $\ln (C_0/C_t)$. A fixed chronological evaluation, trained at $t\le 100$ min and evaluated at $100<t\le 120$ min, yielded mean $R^2$ values of $0.9668\pm 0.0073$ and $0.8890\pm 0.0163$, respectively. Because the composition-specific RF predictions were constant across this boundary interval, these scores are interpreted as later-time boundary diagnostics rather than evidence of temporal extrapolation. Point-estimate SHAP, impurity-based, and permutation-based analyses assigned greater predictive importance to reaction time, whereas moving-block bootstrap results showed that this ranking was sensitive to temporal resampling. Among the five tested compositions, the nominal 5% Cu-containing sample exhibited the most favorable apparent removal profile. This finding is specific to the investigated conditions and does not establish a universal optimum or a causal physicochemical mechanism.