Modeling of bunus regional sewage treatment plant using machine learning approaches

Certain aspects of the dynamics of wastewater treatment plants appear to be chaotic, which makes modeling of the process of wastewater treatment plants extremely difficult. An appropriate model is key for the optimal operation of the plant. Conventional prediction techniques are not good enough to produce the desired results and determination of the suitable structure of using either fuzzy, artificial neural network or adaptive neuro-fuzzy interface system becomes cum-bersome. This article proposed the application of advanced machine learning methodologies, for example, extreme learning machine (ELM), support vector machine (SVM) for modeling the Bunus regional sewage treatment plant. These advanced machine learning methods were also compared with conventional autoregressive integrated moving average (ARIMA). Observed data from the Bunus regional wastewater treatment plant was used for the modeling. The simulation results indicated that the ELM model performed better than the SVM and ARIMA models with a decrease in mean absolute percentage error by 19% and 29% than SVM and ARIMA models respectively. As the choice of input parameters often affects the modeling performance different combinations of input variables were selected. It was observed that influent biological oxygen demand, chemical oxygen demand, suspended solids, ammonium iron (NH₄ ) were able to model the process better than other input parameter combinations.