Abstract
Accurate weed maps are essential for the success of sitespecific herbicide application using mapbasedvariablerate sprayers. In this study, remotely sensed images acquired using an airborne digital color infrared (CIR) sensorwere used for mapping and modeling the spatial distribution of weed infestation density within a soybean field. The effectof spatial positioning error associated with data on resolution requirements and mapping accuracy was also studied.Vegetative indices developed from the threeband CIR image showed strong correlation with spatial weed density. The bestcorrelation was observed at the spatial resolutions of 4.5 m/pixel to 5.3 m/pixel, which was lower than the actual dataresolutions. Higher modeling accuracies observed at lower resolutions were caused by the positioning error associated withboth aerial imaging data and groundtruth data. At this resolution, the weed density models developed using an artificialneural network resulted in R 2 values of 0.87 and 0.83. This model mapped the spatial distribution of weed density with anR 2 value of 0.58 for a field not used in modeling.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
