Study On Winter Wheat Classification And Monitoring Based On Time Series Remote Sensing Data

As the population continues to grow,the need for food is increasing.Wheat,as one of the three largest cereals in the world,is of great importance in obtaining growth conditions in the early stages of its growing season,and is sometimes even more important than the exact yield obtained after harvest.In the past,the classification and monitoring of crops did not take into account their phenological differences,the calculation of their biomass did not take into account the effects of the cloud and lacked yield forecasts.In this paper,multi-period remote sensing image classification theory is used to classify and extract winter wheat growing area,the theory of crop growth model is used to monitor the growth of winter wheat,and yield calculation method is used to calculate winter wheat yield.This paper proposes a method of regionalizing the study area by using temperature difference,and improves the Light Use Efficiency(LUE)model.The statistical data and Huanjing satellite's data is used to verify that similarity classification method of time series remote sensing data can relatively accurately extract the growing area of winter wheat,and the statistical data verifies that biomass calculated by the improved LUE model and yield calculated by yield calculation method are more accurate.Regionalization of the study area and the improved LUE model can be applied in crop monitoring of the world's large-scale cultivation.