Effluent parameters prediction of a biological nutrient removal (BNR) process using different machine learning methods: A case study.

This paper proposes a novel targeted blend of machine learning (ML) based approaches for controlling wastewater treatment plant (WWTP) operation by predicting distributions of key effluent parameters of a biological nutrient removal (BNR) process. Two years of data were collected from Plajyolu wastewater treatment plant in Kocaeli, Türkiye and the effluent parameters were predicted using six machine learning algorithms to compare their performances. Based on mean absolute percentage error (MAPE) metric only, support vector regression machine (SVRM) with linear kernel method showed a good agreement for COD and BOD5, with the MAPE values of about 9% and 0.9%, respectively. Random Forest (RF) and EXtreme Gradient Boosting (XGBoost) regression were found to be the best algorithms for TN and TP effluent parameters, with the MAPE values of about 34% and 27%, respectively. Further, when the results were evaluated together according to all the performance metrics, RF, SVRM (with both linear kernel and RBF kernel), and Hybrid Regression algorithms generally made more successful predictions than Light GBM and XGBoost algorithms for all the parameters. Through this case study we demonstrated selective application of ML algorithms can be used to predict different effluent parameters more effectively. Wider implementation of this approach can potentially reduce the resource demands for active monitoring the environmental performance of WWTPs.

Borohydride method modification in synthesizing nano zero valent iron and its application in DDT removal.

Among the methods used in the literature for the synthesizing of nano zero valent iron (nZVI), borohydride is the most commonly used method; it is seen that different variables are used together. In this study, optimum nano zero valent iron (nZVI) synthesizing method using borohydride method has been modified by using multiple optimization method in terms of both particle size and zeta potential. Selected independent variables are selected as iron sulfate concentration, ethanol ratio, and flow rate of borohydride solution. With the optimum synthesis method determined, the lowest particle size was obtained as 70 nm only when the particle size was taken into consideration, whereas 88.2 nm nZVI could be produced when both the particle size and the zeta potential were taken into consideration. In addition, the removal of DDT, which is the most commonly used persistent organic pollutant pesticides in the world, was investigated by nZVI synthesized. Different initial DDT concentration was investigated by expressing oxidation reduction potential (ORP) difference, removal rates, and oxidation byproducts. When DDD and DDE concentrations are considered, it is found that DDT is more likely to oxidize in DDD in all studied initial DDT concentrations. Removal rate was higher than 80% with initial concentrations lower than 125 µg/L, which is a high concentration that could be found in surface waters.

Optimization of energy costs in the pretreatment of olive mill wastewaters by electrocoagulation.

In this study, the electrocoagulation process was evaluated as a pretreatment process for olive mill wastewaters. Aluminium (Al) and iron (Fe) electrodes, several contact times and 0.5, 1 and 2 A currents were used to compare chemical oxygen demand (COD) removal efficiencies for each case. The optimum contact time and current were 45 minutes and 1 A, respectively, which resulted in a COD removal of 58.7% with an Al electrode. Experimental data from distinct operational conditions were used to fit a model for COD removal efficiencies. Energy consumption was also predicted. Under optimum operational conditions, the treatment cost was approximately Euro 0.13 kg(-1) CODremoved and Euro 4.41 m(-3). The results showed that the electrocoagulation process was a cost-effective method for the pretreatment of olive mill wastewaters.

Sequence optimization in a sequencing batch reactor for biological nutrient removal from domestic wastewater.

The purpose of this work was to determine optimum sequence retention times for nutrient removal with low-cost using very short aeration time in an SBR treating domestic wastewater. During the study, four different CYCLEs were evaluated, with the highest removal efficiencies recorded for the CYCLE with fill, anaerobic, aerobic1, anoxic, aerobic2, settle, and decant sequences operated at retention times of 0.5, 2, 2, 1, 0.75, 1, and 0.5 h, respectively. For this CYCLE, the removal efficiencies of chemical oxygen demand (COD), total Kjeldahl nitrogen (TKN), ammonia nitrogen (NH(3)-N), total phosphorus (TP), and ortho-phosphate (PO(4)-P) were found, on average, to be 91, 78, 85, 87, and 83%, respectively. The optimum sequence retention time was determined via the analysis of variance (ANOVA) using the Matlab software (Mathworks Inc.). The data indicated that the total time of the aerobic sequences was shorter than those of previous studies for similar level of removal efficiencies in all parameters including N and P.