科研之友
微信
新浪微博
Facebook
分享链接
摘要
Normalized Difference Vegetation Index (NDVI) has been found to have good correlations with many physical properties of soybean surfaces. Due to the factors of air temperature, humidity, solar radiation, soil moisture, etc., NDVI of soybean varies dynamically in a day. The establishment of the soybean NDVI prediction model at different times in a day can effectively modify this variation. The soybean NDVI values are continuously monitored in hours during soybean seeding, flowering & podding and maturating stages by way of Green Seeker. Results show that the trend of NDVI change every day in the three stages is taken on as a reverse parabola. The NDVI value reaches to the maximum at 8 am or 9 am and decreases to its minimum at 2 pm before a moderate rise. A model for intraday and long-term NDVI change for soybean is built. The test of the model with independent data indicates that the precision meets the demands, with the root mean square error (RMSE) of each day being 3.95, 5.45 and 2.86 for the seeding stage, the bean podding stage and the maturation period, respectively. The prediction RMSEs of the soybean NDVI model for soybeans of the three stages for the fifth day are 5.75, 2.65 and 5.51, respectively and the prediction RMSEs for the sixth day are 9.74, 2.82 and 14.04, respectively according to the data from the first four days.
- 出版日期2014-10
- 单位西北农林科技大学
