Method and system for determining optimal trend yield-per-unit model

Abstract

The invention discloses a method and a system for determining an optimal trend yield-per-unit model. The determining method includes the following steps: acquiring historical yield-per-unit data of a crop; building a plurality of different trend yield-per-unit models according to the historical yield-per-unit data of the crop; and selecting an optimal trend yield-per-unit model by judging a plurality of indicators. Thus, the accuracy of prediction of crop yield is improved.

Description

technical field [0001] The invention relates to the field of agricultural production, in particular to a method and system for determining an optimal trend yield model. Background technique [0002] In the prior art, there are many methods for predicting crop yield, which can be roughly divided into statistical prediction methods, remote sensing prediction methods and dynamic growth model methods. The most widely used method is the statistical forecasting method. Based on the statistical forecasting method, many forecasting models have been derived. One of them is a meteorological model, which focuses on the short-term impact of meteorological fluctuations on crop yields, so that crop yields can be predicted. In order to improve the accuracy of forecasting crop yield, it is also necessary to consider the crop trend yield model. The conventional method only needs to judge the indicator once and relies too much on a certain indicator. For example, use the root mean square erro...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method and system for determining the optimal trend yield model, which can select the optimal trend yield model, thereby solving the problem of low crop yield prediction accuracy

Images