Free-surface constructed wetlands are known as a low-energy green technique to highly decrease a wide range of pollutants in wastewater and stormwater before discharge into natural water. In this study, two spatial analyses, principal factor analysis and hierarchical cluster analysis (HACA), were employed to interpret the effect of wetland on the water quality variables (WQVs) and to classify the wetland into groups with similar characteristics. Eleven WQVs were collected at the 17 sampling stations twice a month for 13 months. All sampling stations were classified by HACA into three clusters, with high, moderate, and low pollution areas. To improve the water quality, the performance of Cluster-III (micropool) is more significant than Cluster-I and Cluster-II. Implications of this study include potential savings of time and cost for long-term data monitoring purposes in the free-constructed wetland.
Poor water quality is a serious problem in the world which threatens human health, ecosystems, and plant/animal life. Prediction of surface water quality is a main concern in water resource and environmental systems. In this research, the support vector machine and two methods of artificial neural networks (ANNs), namely feed forward back propagation (FFBP) and radial basis function (RBF), were used to predict the water quality index (WQI) in a free constructed wetland. Seventeen points of the wetland were monitored twice a month over a period of 14 months, and an extensive dataset was collected for 11 water quality variables. A detailed comparison of the overall performance showed that prediction of the support vector machine (SVM) model with coefficient of correlation (R(2)) = 0.9984 and mean absolute error (MAE) = 0.0052 was either better or comparable with neural networks. This research highlights that the SVM and FFBP can be successfully employed for the prediction of water quality in a free surface constructed wetland environment. These methods simplify the calculation of the WQI and reduce substantial efforts and time by optimizing the computations.