Prediction of Effluent Quality (Five-Day Biological Oxygen Demand) in a Wastewater Treatment Plant Using Various Empirical Models

The Sustainable Development Goals are currently the subject of global efforts to be achieved. Decision-makers need to investigate into how technology may help achieve the SDGs to avoid any possible compromise. Estimating influent parameters of wastewater treatment plants, such as 5-day biological oxygen demand (BOD5), is generally necessary to optimize power and energy consumption. Therefore, multi-layer perceptron neural network (MLPNN), radial basis function (RBF), autoregressive integrated moving average (ARIMA), and response surface methodology (RSM) -based models for predicting BOD5 were developed using data from the inflow of the wastewater treatment plant at Lefkosa, Northern Cyprus, over a period of three years. The findings demonstrated that, in comparison to other models, the RSM model performs better, with R2 = 0.9101 for the validation phase. Additionally, the RSME and MAE show that, in terms of statistical parameters, the observed values and the obtained values of the RSM model closely agree with them.