SPATIAL AUTOCORRELATED MACHINE LEARNING SATELLITE PRECIPITATION DATA DOWNSCALING METHOD AND SYSTEM

摘要

A spatial autocorrelated machine learning satellite precipitation data downscaling method, comprising: acquiring TRMM precipitation data and earth surface parameter data; pre-processing the earth surface parameter data to obtain DEM data with spatial resolutions of 1 km and 25 km, a daytime earth surface temperature, a nighttime earth surface temperature, a daytime and nighttime earth surface temperature difference, and NDVI data; performing spatial autocorrelation analysis on the TRMM precipitation data to obtain an estimated spatial autocorrelation value of precipitation data with a spatial resolution of 25 km; downscaling the spatial autocorrelation value of the precipitation data with the spatial resolution of 25 km until the spatial resolution is 1 km; establishing a non-linear regression model; and obtaining precipitation downscaling data with a spatial resolution of 1 km on the basis of the non-linear regression model. Also provided are a system and a terminal. A downscaling result of the method is superior to a downscaling result based on a conventional regression model, and the method has important theoretical and practical significance and value in terms of popularization and application.