Monitoring and Forecasting Winter Wheat Freeze Injury and Yield from Multi-Temporal Remotely Sensed Data. Issue 2 (2nd April 2016)

• Record Type: Journal Article
• Authors: Wang, Huifang; Huo, Zhiguo; Zhou, Guangsheng; Wu, Li; Feng, Haikuan
• Is Part Of: Intelligent automation & soft computing. Volume 22:Issue 2(2016)
• Page Start: 255
• Page End: 260
• Publication Date: 2016-04-02
• Subjects: Winter wheat -- freeze injury levels -- change detection -- yield assessment; Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 003.5
• DOI: 10.1080/10798587.2015.1095475
• Languages: English
• ISSNs: 1079-8587

Abstract

Abstract: Remote-sensing techniques provide crop growth information economically, rapidly, and objectively on a large scale. Remote sensing has been widely used to monitor crop growth and forecast yield. In this study, three Huanjing satellite (HJ) charge-coupled device (CCD) images of winter wheat at growth-wintering (December 2, 2009; pre-freeze injury), regreening (April 2, 2010; post-freeze injury), and jointing stages (April 23, 2010) were acquired for the Gaocheng area in Hebei Province. According to the change characteristics of the normalized difference vegetation index (NDVI) of field samplings of post-freeze injury, we built a multi-line-progress model between the NDVI difference (ΔNDVI) and field samplings, which correspond with field investigation data. The damage levels (uninjured, mild, moderate, and serious) and the growth levels (better, good, bad, and worse) were also specified in the model. As a result, the coefficient of determination (R 2 ) of this model reached 0.6001; 20 sampling points were used to validate the model and R 2 reached 0.5255. This study demonstrates the feasibility of using early growth stage model to predict yield and provides a tentative prediction of the yield in the Hebei area using HJ-CCD images of China.