Semi-supervised support vector regression model for remote sensing water quality retrieving

This paper proposed a semi-supervised regression model with co-training algorithm based on support vector machine, which was used for retrieving water quality variables from SPOT5 remote sensing data. The model consisted of two support vector regressors (SVRs). Nonlinear relationship between water quality variables and SPOT5 spectrum was described by the two SVRs, and semi-supervised co-training algorithm for the SVRs was established. The model was used for retrieving concentrations of four representative pollution indicators-permanganate index (CODmn), ammonia nitrogen (NH3-N), chemical oxygen demand (COD) and dissolved oxygen (DO) of the Weihe River in Shaanxi Province, China. The spatial distribution map for those variables over a part of the Weihe River was also produced. SVR can be used to implement any nonlinear mapping readily, and semi-supervised learning can make use of both labeled and unlabeled samples. By integrating the two SVRs and using semi-supervised learning, we provide an operational method when paired samples are limited. The results show that it is much better than the multiple statistical regression method, and can provide the whole water pollution conditions for management fast and can be extended to hyperspectral remote sensing applications.