Remote sensing rainfall error correction method and system based on nonlinear classification regression analysis

Abstract

The present invention provides a remote sensing rainfall error correction method and system based on nonlinear classification and regression analysis, including: establishing a geographic spatio-temporal information database of rainfall in the target watershed; dividing the rainfall station in the target watershed, determining a training set and a test set, and calculating the rainfall in the target watershed The initial error correction field at the station; the correction field is determined based on the geographic information of the observation field corresponding to the training set, and a nonlinear classification regression model set is constructed based on the support vector machine classification and regression theory in the correction field step by step; according to the geographic information of the test set, it is automatically Screen the correction domain and nonlinear classification regression model parameters, estimate the rainfall error field, and perform error correction and accuracy evaluation on the background field of the test set; use the nonlinear classification regression model to construct rainfall error fields with different spatial resolutions to achieve downscaling Processing, and error correction for remote sensing rainfall products grid by grid and time period. The embodiment of the present invention can generate higher precision and higher resolution remote sensing rainfall data sets on demand.

Description

technical field [0001] The present invention relates to the fields of hydrological and meteorological data analysis and rainfall forecast research, and more specifically, to a remote sensing rainfall error correction method and system based on nonlinear classification regression analysis. Background technique [0002] Among the elements of weather change, precipitation is one of the important physical processes driving the hydrological cycle of a watershed. Its spatial distribution profoundly affects the spatial pattern of related variables such as surface runoff, flood, and soil moisture content, and drives the temporal and spatial changes of water resources in a watershed. Therefore, timely and accurate estimation of precipitation is of great significance to the national economy, social life, and the safety of people's lives and property. [0003] Today's precipitation estimation methods mainly include surface rainfall station observation, weather radar and meteorological ...

AI Technical Summary

Problems solved by technology

However, due to the extremely complex spatiotemporal variability of rainfall in the basin and the many influencing factors, although the existing remote sensing rainfall correction methods can improve the accuracy gain to a certain extent, it is still difficult to match the runoff and flood in the changing environment due to the differences in explanatory variables and the performance of the method. Analytical accuracy requirements for simulation, water resource evolution prediction, etc.

Images