Application of a generalized hybrid machine learning model for the prediction of H2S and VOCs removal in a compact trickle bed bioreactor (CTBB).

This study presents a generalized hybrid model for predicting H2S and VOCs removal efficiency using a machine learning model: K-NN (K - nearest neighbors) and RF (random forest). The approach adopted in this study enabled the (i) identification of odor removal efficiency (K) using a classification model, and (ii) prediction of K <100%, based on inlet concentration, time of day, pH and retention time. Global sensitivity analysis (GSA) was used to test the relationships between the inputs and outputs of the K-NN model. The results from classification model simulation showed high goodness of fit for the classification models to predict the removal of H2S and VOCs (SPEC = 0.94-0.99, SENS = 0.96-0.99). It was shown that the hybrid K-NN model applied for the "Klimzowiec" WWTP, including the pilot plant, can also be applied to the "Urbanowice" WWTP. The hybrid machine learning model enables the development of a universal system for monitoring the removal of H2S and VOCs from WWTP facilities.

Odor and volatile organic compounds biotreatment using compact trickle bed bioreactors (CTBB) in a wastewater treatment plant.

The main aim of this study was to optimize and maximize the impacts of odor and volatile organic compounds (VOCs) biodegradation in a wastewater treatment plant utilizing a pilot-scale compact trickle bed bioreactor (CTBB). A CTBB was built and tested for its long-term performance during which gases were supplied from the tank containing semi-liquid fats, oils, and fat waste. The concentrations of pollutants ranged from 0 to 140.75 mg/m3 H2S, 0 to 2500 mg/m3 VOCs, and 0 to 21.5 mg/m3 NH3. The CTBB was tested at different gas flow rates and at two pH values for the liquid phase: pH = 7.0 and 5.0. In the liquid phase, the pollutant removal efficiency was higher at pH = 7.0 than at pH = 5.0. Overall, the removal efficiency was between 81.5 % and 99.5 % for the VOCs and 87.5 % and 98.9 % for H2S, while NH3 removals were >99 %.