Use of PCA-RBF model for prediction of chlorophyll-a in Yuqiao Reservoir in the Haihe River Basin, China

Abstract

Chlorophyll-a is a well-accepted index for phytoplankton abundance and population of primary producers in an aquatic environment. The relationships between chlorophyll-a and 18 chemical, physical and biological water quality variables in YuQiao Reservoir (YQR) in the Haihe River Basin in P.R. China were studied by using principal component analysis (PCA) coupled with a radial basis function network (RBF) model to predict chlorophyll-a levels. Principal component analysis was used to simplify the complexity of relations between water quality variables. Score values obtained by PC scores were used as independent variables in the RBF models. In the forecast, only five selected score values obtained by PC analysis were used for the prediction of chlorophyll-a levels. Correlative analysis between the modeled results and observed data indicates that the correlative coefficient is 0.61, and analysis of the forecast error rate shows that the average forecast error is 32.9%, proving the viability of the forecast model.