Chlorophyll-a Concentration in Water: A Semi-analytical Retrieval Model Research with a BP Network

The chlorophyll-a concentration of water from Nansihu Lake of Shandong Province, China was analyzed using hyperspectral data with a semi-analytic model. First, three bands of the hyperspectral data centered at 660nm, 708nm and 812nm were chosen based on iterative optimization analysis. Then, the linear-TBA model, the poly-TBA model, and the BP-TBA model were used to determine chlorophyll concentration. Field data were used to validate the results and performances of three different models. The validation results indicated that the BP-TBA model achieved the highest accuracy with a mean relative error of 0.2268 in the training data set and 0.1983 in the validation data set. However, the BP-TBA model was not fit for turbid coastal water. When the chlorophyll-a concentration exceeded 0.03mg/L, the error increased, demonstrating a mean of 0.364.