Performance evaluation of hybrid constructed wetlands for nitrogen removal and statistical approaches.

Nitrogen pollution in water bodies has become a pressing environmental and public health issue worldwide, demanding the implementation of effective nitrogen removal strategies. This research paper delves into the performance evaluation of hybrid constructed wetlands (HCWs) as a sustainable and innovative approach for nitrogen removal, employing a comprehensive year-long dataset gathered from a practical setup. The study collected data under diverse operating conditions to investigate the effectiveness of HCWs in removing nitrogen. Results revealed that HCWs achieved nitrogen removal efficiencies ranging from 28% to 65%, influenced by temperature and hydraulic retention time. Optimal removal occurred at an average temperature of 28°C and a 4-day hydraulic retention time. Notably, performance declined during colder periods, with temperatures below 15°C. The study also aims to predict nitrogen removal by three modeling techniques, that is, artificial neural networks (ANNs), support vector machines Pearson VII kernel function (SVM PUK), and multiple linear regression (MLR). Prediction has been done considering temperature (TEMP), hydraulic loading rate (HLR), initial concentration of chemical oxygen demand (COD) (CODin), initial concentration of total nitrogen (TNin ), initial concentration of total phosphorous (TPin ), and initial concentration of turbidity (TBin ) as input parameters, whereas reduction of total nitrogen (RED TN) is regarded as output parameter. The performance of the soft computing techniques has been compared in terms of coefficient of determination (R2 ), root mean square error (RMSE), and mean absolute error (MAE). The analysis revealed that the performance of the SVM (PUK) model (R2 : 0.572, RMSE: 0.0359, MAE: 0.0294) for the prediction of TN reduction is superior followed by MLR (R2 : 0.562, RMSE: 0.0365, MAE: 0.0294) and ANN (R2 : 0.597, RMSE: 0.0377, MAE: 0.0301). The present study concludes that the treated effluent by the HCWs, using water hyacinth and water lettuce, is of fair quality, thus having potential application for the treatment of rice mill wastewater in warmer climates. Further, machine learning approaches employed in estimating the total nitrogen reduction by HCWs technology have shown promising applicability and utilization in such studies. PRACTITIONER POINTS: Hybrid constructed wetlands (HCWs) are effective in removing nitrogen from wastewater. The performance of HCWs in nitrogen removal can vary due to physical, chemical, and biological processes. The performance of the HCWs highly depends on temperature and hydraulic retention time. Artificial neural networks (ANNs) and support vector machines (SVMs) provided better predictions of nitrogen removal with high accuracy and low root mean square error.