Optimizing photocatalytic dye degradation: A machine learning and metaheuristic approach for predicting methylene blue in contaminated water

• Ten advanced machine-learning models were selected to predict the degradation of methylene blue dye from contaminated water. • HistGradientBoosting (HGB) model outperformed as compared to other studied models. • Bayesian optimization was used to tune hyperparameters and achieve the best results. • The final HGB model metrics included an R² score of 0.9915, MedAE of 1.171, MSE of 5.634, MAE of 1.735, and RMSE of 2.374. • The modelling projected the highest MB dye degradation (98.99%) under optimized conditions. Dye contamination in water sources has severe environmental and public health risks; therefore, it needs effective monitoring and remediation strategies. The aim of the study is to use machine learning techniques to develop predictive models that may be used to…