Assessment for surface water quality in Lake Taihu Tiaoxi River Basin China based on support vector machine

Support vector machine (SVM) classification models were constructed using a radial basis functions (RBF). These models were used for classification according to dissolved oxygen, permanganate index, ammoniac nitrogen, total nitrogen, or total phosphorus. Cross-validation and grid-search were applied to find satisfactory parameters for RBF for the improved models. Then the improved models were used to assess water quality utilizing a real-world data set (surface water quality monitoring data). The data set was comprised of more than 2,000 water samples representing 172 different sites monitored for one hydrological year. The results showed that the method presented in this paper had excellent performance, and the SVM classification models performed relatively better than the Linear Discriminant Analysis and Quadratic Discriminant Analysis models for classification.