METHOD AND APPARATUS FOR DETECTING SPATIAL DOWNSCALED PRECIPITATION DATA, AND ELECTRONIC DEVICE

摘要

A method for detecting spatial downscaled precipitation data. The method for detecting spatial downscaled precipitation data comprises the following steps: establishing and training an optimal random forest algorithm model according to daytime surface temperature, nighttime surface temperature, a surface temperature difference between day and night, a digital elevation model, and the vegetation index with a second resolution of a sample region, as well as satellite remote sensing precipitation data of the sample region (S40); inputting daytime surface temperature, nighttime surface temperature, a surface temperature difference between day and night, a digital elevation model, and the vegetation index with a first resolution of a region to be detected to the optimal random forest algorithm model to obtain precipitation data with the first resolution of said region (S70); and performing residual correction on the precipitation data with the first resolution to obtain spatial downscaled precipitation data of the region to be detected (S80). The method for detecting spatial downscaled precipitation data can obtain precipitation data with relatively high resolution.