Prediction of water quality index in constructed wetlands using support vector machine

• Published in: Environmental science and pollution research international Vol. 22; no. 8; pp. 6208 - 6219
• Main Authors: Mohammadpour, Reza, Shaharuddin, Syafiq, Chang, Chun Kiat, Zakaria, Nor Azazi, Ghani, Aminuddin Ab, Chan, Ngai Weng
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer-Verlag 01.04.2015; Springer Berlin Heidelberg; Springer Nature B.V
• Subjects: Animals; Aquatic plants; Aquatic Pollution; Artificial wetlands; Atmospheric Protection/Air Quality Control/Air Pollution; Back propagation; Catalysis; Chemical oxygen demand; constructed wetlands; Construction equipment; Correlation; data collection; Datasets; Earth and Environmental Science; ecosystems; Ecotoxicology; Environment; Environmental Chemistry; Environmental Health; Flowers & plants; Free surfaces; human health; Mathematical models; Models, Theoretical; Neural networks; Neural Networks (Computer); prediction; Predictions; Propagation; Research Article; Stormwater management; Support Vector Machine; Support vector machines; Surface water; Variables; Waste Water Technology; Water Management; Water Pollutants - chemistry; Water pollution; Water Pollution Control; Water quality; Water Quality - standards; Water resources; Wetlands; Malaysia; Support vector machine; Water quality index; Neural networks; Constructed wetland; Surface water
• ISSN: 0944-1344; 1614-7499
• DOI: 10.1007/s11356-014-3806-7

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 (R²) = 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.