Abstract
In modern agriculture, remote sensing technology plays an essential role in monitoring crop growth and crop yield
prediction. To monitor crop growth and predict crop yield, accurate and timely crop growth information is significant, in
particularly for large scale farming. As the high cost and low data availability of high-resolution satellite images such as
RapidEye, we focus on the time-series low resolution satellite imagery. In this research, NDVI curve, which was
retrieved from satellite images of MODIS 8-days 250m surface reflectance, was applied to monitor soybean's yield.
Conventional model and vegetation index for yield prediction has problems on describing the growth basic processes
affecting yield component formation. In our research, a novel method is developed to well model the Crop Growth
Dynamics (CGD) and generate CGD index to describe the soybean's yield component formation. We analyze the
standard growth stage of soybean and to model the growth process, we have two key calculate process. The first is
normalization of the NDVI-curve coordinate and division of the crop growth based on the standard development stages
using EAT (Effective accumulated temperature).The second is modeling the biological growth on each development
stage through analyzing the factors of yield component formation. The evaluation was performed through the soybean
yield prediction using the CGD Index in the growth stage when the whole dataset for modeling is available and we got
precision of 88.5% which is about 10% higher than the conventional method. The validation results showed that
prediction accuracy using our CGD modeling is satisfied and can be applied in practice of large scale soybean yield
monitoring.
