Crop growth prediction method and system

Abstract

The invention provides a crop growth prediction method and system. The crop growth prediction method comprises the steps of obtaining a normalized vegetation index corresponding to a current year anda normalized vegetation index corresponding to each historical year; carrying out fitting reconstruction on the normalized vegetation indexes corresponding to the current year and each historical yearto obtain a current NDVI fitting curve and each historical NDVI fitting curve; normalizing the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI growth curve and each historical NDVI growth curve; calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year, and predicting the growth of the target crops in the current year; and predicting the later growth vigor of the target crop according to the obtained optimal matching year, and guiding the crop management.

Description

technical field [0001] The invention relates to the field of agricultural technology, in particular to a method and system for predicting crop growth. Background technique [0002] The dynamic change of crop growth in field crop production is closely related to the final yield and quality, so it is of great value and significance to monitor crop growth dynamically. Remote sensing observation has the advantages of wide coverage and high efficiency, and overcomes many problems such as time-consuming, high cost, and destructiveness caused by ground sampling observation. However, at present, the monitoring of crop growth using remote sensing mainly uses discrete periodic observations. For example, the remote sensing vegetation index (such as NDVI and EVI) is estimated at nodes such as the jointing stage and the filling stage of winter wheat, and compared with the historical remote sensing vegetation index in the same period. Determine how good or bad the growth is. The advanta...

AI Technical Summary

Problems solved by technology

This difference in growth and phenology due to the sowing date will also cause large errors in the later remote sensing monitoring and evaluation.

[0005] (3) Remote sensing is an instantaneous observation, which only represents the growth status of crops at the time of satellite transit. Although multiple growth periods can be monitored, it lacks correlation analysis of different growth periods due to independent comparative analysis of multiple growth periods. It often results in conflicting judgments of growth in different growth periods, making it difficult to comprehensively evaluate the dynamic trend of crop growth

Images