Prediction of municipal wastewater biochemical oxygen demand using machine learning techniques: A sustainable approach

This paper proposes an integrated framework of remote sensing and machine-learning techniques to predict municipal wastewater influent biochemical oxygen demand (BOD5) in treatment plants (WWTPs). The study compares the performance several supervised algorithms, specifically decision tree, random forest, adaptive boosting, gradient boost, extreme boosting against received by two WWTPs South Kingdom Bahrain. boost algorithm model obtained best results, scoring 1.00 coefficient determination (R2) 0.08 mean absolute error (MAE) Askar WWTP dataset. In addition, developed showed its applicability robustness Al Dur dataset 0.95 R2 3.93 MAE. that empirically, using a manual sampling method obtain input feature readings, duration results can be accelerated 40 times compared traditional laboratory procedures. As result, was reduced from five days only three hours. On contrary, real-time sensors BOD5 predicted real-time. proposed approach mitigates environmental risks ensures effective process meets effluent quality parameters.