Corn yield remote sensing prediction method and system

Abstract

The invention discloses a corn yield remote sensing prediction method and a system. The method comprises the following steps: acquiring a remote sensing image of corn in a to-be-detected area in a setgrowth period, wherein the set growth period comprises a milk ripening period and a ripening period; determining attribute parameters of each remote sensing image, wherein the attribute parameters comprise a difference vegetation index, a ratio vegetation index, an enhanced vegetation index and a greenness vegetation index; and inputting the attribute parameters into a GA-BP neural network modelto predict the yield of the corn in the to-be-detected area, wherein the GA-BP neural network model is a model obtained by training according to historical remote sensing images of the corn in the to-be-detected area in a set growth period and corresponding historical yield data. The corn yield remote sensing prediction method and the system provided by the invention have the characteristic of high prediction precision.

Description

technical field [0001] The invention relates to the technical field of crop yield prediction, in particular to a method and system for remote sensing prediction of corn yield. Background technique [0002] At present, the estimation of corn yield using remote sensing data is generally based on the regression model, which establishes a linear relationship between yield and a variable. However, the regression model needs to be supported by a large amount of local measured production data, and the calculation process is relatively time-consuming. Moreover, the structure is too simple to simply describe the linear relationship, and the prediction accuracy is not high. Contents of the invention [0003] The purpose of the present invention is to provide a corn yield remote sensing prediction method and system, which are characterized by simplicity and high prediction accuracy. [0004] To achieve the above object, the present invention provides the following scheme: [0005] ...

AI Technical Summary

Problems solved by technology

However, the regression model needs to be supported by a large amount of local measured production data, and the calculation process is relatively time-consuming. Moreover, the structure is too simple to describe the linear relationship, and the prediction accuracy is not high.

Images