Abstract:Using grided data from 2419 stations of National Meteorological Information Centre during 2012-2013 and the TRMM (3B40RT, 3B41RT, 3B42RT), CMORPH, GSMaP, HYDRO satellite derived rainfall data, this paper evaluated and discussed the validation of rainfall estimates from the six data with 0.25°×0.25° spatial resolution and the accuracy of the retrieved daily rainfall products over the whole China, Eastern China and Western China. Results show that the accuracy of satellite derived data is higher in spring, summer and autumn than in winter. The linear correlation coefficient, mean absolute error (MAE), root mean square error (RMSE), probability of detection (POD), and the false alarm ratio (FAR) change with seasons. Meanwhile, the index of each data is better in summer than in winter. The quantitative statistical metrics are obviously different, changing in monthly scale. The estimate ability of satellite derived rainfall is poor when estimating solid and small amount precipitation. For the large range of precipitation events over China, all the 6 rainfall products have better result. The better quality is realized by merging multi sources, and the worse quality results from single source microwave, infrared or visible light. The 3B42RT retrieves better falling area of rainfall, but extreme value is larger. The comprehensive evaluation of the CMORPH is better than others. The spatial distribution of accuracy of satellite derived rainfall is related to terrains of China.