Using Data Mining to Predict Sludge and Filamentous Microorganism Sedimentation

Abstract

IntroductionConsidering the stochasticity of the volume and quality of the incoming sewage, the operating parameters of reactors need to be controlled within a certain range so that the performance of the respective units of a sewage treatment plant (STP) can be optimized and the desirable pollution reduction effect achieved [1,2]. This requires prediction of various biochemical processes taking place in the reactor, using physical or statistical method for the purpose. The former have the advantage that the qualitative variability of sewage at the discharge from the reactor and the biological reactor's operating parameters is based on differential equation systems. However, for the calibration of physical models, one needs detailed information about the reaction path in the respective units, which requires continuous high-resolution measurements of a number of qualitative parameters of the sewage at the inlet, discharge and inside the reactor, leading to considerable problems in the experimental phase. Moreover, due to the number of model parameters and strong interactions between them, their calibration may often be difficult, as confirmed in multiple Pol. AbstractThis study attempted to develop statistical regression models for predicting the settleability of activated sludge based on the quality of incoming sewage and on the identified dominant filamentous species. As part of the analyses conducted for the purpose, classification models are presented that enable identification of the respective filamentous microorganisms, based on the working parameters of the bioreactor and the quality of the influent. The study calculations demonstrated that the modeling methods based on artificial neural networks, random forests, and boost trees can be applied for the identification of filamentous microorganisms Microthrix parvicella, Nostocoida sp., and Thiotrix sp. in activated sludge chambers in the STP located in Sitkówka-Nowiny. The best predictive capacity, covering identification of the above-mentioned filamentous bacterial species in activated sludge chambers, was observed for statistical models obtained by the random forest method.

The Impact of Different Powdered Mineral Materials on Selected Properties of Aerobic Granular Sludge

“…In recent years, actions have been taken to improve and intensify the technology of activated sludge [1][2][3]. The previous actions in this area led to the development of a method using such sludge in the form of granules.…”