Coupling process-based modeling with machine learning for long-term simulation of wastewater treatment plant operations

Abstract

Effective treatment of sewage by wastewater treatment plants (WWTPs) are essential to protecting water environment as well as people's health worldwide. However, operation of WWTPs is usually intricate due to precarious influent characteristics and nonlinear sewage treatment processes. Effective modeling of WWTPs can provide valuable decision-making support to facilitate their daily operations and management. In this study, we have built a novel hybrid model by combining a process-based WWTP model (GPS-X) with a data-driven machine learning model (Random Forest) to improve the simulation of long-term hourly effluent ammonium-nitrogen concentration of a WWTP. Our study results have shown that the hybrid GPS-X-RF model performs the best with a coefficient of determination (R2) of 0.95 and root mean squared error (RMSE) of 0.23 mg/L, followed by the GPS-X model with a R2 of 0.93 and RMSE of 0.33 mg/L and last the Random Forest model with a R2 of 0.84 and RMSE of 0.41 mg/L. Capable of incorporating wastewater treatment mechanisms and utilizing superior data mining capabilities of machine learning, the hybrid model adapts better to the large fluctuations in influent and operating conditions of the WWTP. The proposed hybrid modeling framework may be easily extended to WWTPs of various size and types to simulate their operations under increasingly variable environmental and operating conditions.