In order to determine the most suitable retrieval model for estimating chlorophyll concentration in Lake Taihu and provide a reference for the application of the satellite data, the difference model, the ratio model, the three-band model and APPEL model were built to estimate chlorophyll concentration based on the data of MODIS, MERIS, GOCI and HJ-1 CCD sensor. The dataset included the measured water quality parameters and the synchronous spectra data in November 2007, April 2009 and August 2011. The results of the analysis showed that the decision coefficient of the APPEL model was between 0.7308 and 0.8107 for the different satellite data, the relative error was between 15% and 24%, and the root mean square error was between 21% and 32%; The decision coefficient of the three-band model was between 0.6014 and 0.7610, the relative error was between 28% and 36%, and the root mean square error was between 39% and 46%; The decision coefficient of different models was between 0.4954 and 0.7244, the relative error was between 39% and 53%, and the root mean square error was between 51% and 72%; The decision coefficient of the ratio model was between 0.4918 and 0.7098, the relative error was between 41% and 55%, and the root mean square error was between 56% and 75%.To sum up, the APPEL model showed a strong stability and was suitable for the chlorophyll concentration retrieval of Lake Taihu for different sensor data. In addition, different band widths and band positions had different influences on the retrieval model for estimating chlorophyll concentration.When the band position was close to the characteristic wavelength of chlorophyll, narrow band width was beneficial for the accuracy of the model; while when the band position was far away from the position of the characteristic wavelength, the band width should be increased reasonably.