Environmental, socioeconomic, and climatic factors influence the discharge of high-quality water from Waste Water Treatment Plants (WWTPs) for various purposes. A critical factor in determining treated effluent quality is the concentration of crucial parameters, such as Biochemical Oxygen Demand (BOD). The Hammerstein-Weiner Model (HW), Least Square Support Vector Machine (LSSVM), and Multiple Linear Regression (MLR) are three Machine Learning (ML) models used in this study. To enhance the performance of the single models, Feed Forward Back Propagation Neural Network Ensemble (FFBP-NN-E), Three different types of data were used to predict the BOD: first, environmental data from the recently constructed Nicosia Waste Water Treatment Plant (NWWTP) C1; second, metrological data from the National Aeronautics and Space Administration (NASA) (at 2 m above Earth's surface) C2; third, a hybrid data C3 that combined the environmental and metrological data C1 and C2. The models produced by the ensemble technique have significantly improved the models based on the performance of the best single models. The study demonstrates the impact of using an ensemble technique and hybrid data combination for estimating BOD in NWWTP.