Wastewater inflow time series forecasting at low temporal resolution using SARIMA model: a case study in South Australia

Forecasts of wastewater inflow are considered as a significant component to support the development of a real-time control (RTC) system for a wastewater pumping network and to achieve optimal operations. This paper aims to investigate patterns of the wastewater inflow behaviour and develop a seasonal autoregressive integrated moving average (SARIMA) forecasting model at low temporal resolution (hourly) for a short-term period of 7 days for a real network in South Australia, the Murray Bridge wastewater network/wastewater treatment plant (WWTP). Historical wastewater inflow data collected for a 32-month period (May 2016 to December 2018) was pre-processed (transformed into an hourly dataset) and then separated into two parts for training (80%) and testing (20%). Results reveal that there is seasonality presence in the wastewater inflow time series data, as it is heavily dependent on time of the day and day of the week. Besides, the SARIMA (1,0,3)(2,1,2)(24) was found as the best model to predict wastewater inflow and its forecasting accuracy was determined based on the evaluation criteria including the root mean square error (RMSE = 5.508), the mean absolute value percent error (MAPE = 20.78%) and the coefficient of determination (R(2) = 0.773). From the results, this model can provide wastewater operators curial information that supports decision making more effectively for their daily tasks on operating their systems in real-time.