|Koger Iii, Clifford|
Submitted to: Weed Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/29/2003
Publication Date: 3/1/2004
Citation: Koger III, C.H., Shaw, D.R., Reddy, K.N., Bruce, L.M. 2003. Detection of pitted morningglory with hyperspectral remote sensing. I. effects of tillage and cover crop residue. Weed Science. 52:222-229.
Interpretive Summary: Current remote sensing technologies have been used with limited success for weed detection in row-crop production systems. However, newer technologies such as hyperspectral sensors, which collect more bands of data than current multispectral sensors, may provide for better weed detection capabilities. Field studies were conducted at the Southern Weed Science Research Unit, Stoneville, MS and Plant Science Research Center, Starkville, MS to study the potential of hyperspectral remote sensing data for detecting pitted morningglory in till and no-till plots of soybean containing rye, hairy vetch, or no cover crop residue. Pitted morningglory plant size had more influence on detection capabilities than tillage or cover crop residue system. Across all tillage and residue systems, detection accuracy was 71 to 95%, depending on size of pitted morningglory plants at time of data acquisition. Results indicate that hyperspectral remote sensing may have potential for detecting weeds in row-crop systems across a variety of tillage and cover crop residue settings.
Technical Abstract: Field experiments were conducted to evaluate the potential for hyperspectral reflectance data collected with a hand-held spectroradiometer to discriminate soybean intermixed with pitted morningglory and weed-free soybean in conventional till and no-till plots containing rye, hairy vetch, or no cover crop residue. Pitted morningglory was in the cotyledon to 6-leaf growth stage. Eight 50-nm spectral bands (1 ultraviolet, 2 visible, 4 near-infrared, 1 mid-infrared) derived from each hyperspectral reflectance measurement were used as discrimination variables. Pitted morningglory plant size had more influence on discriminant capabilities than tillage or cover crop residue systems. Across all tillage and residue systems, discrimination accuracy was 71 to 95%, depending on size of pitted morningglory plants at time of data acquisition. The versatility of the eight 50-nm bands was tested by using a discriminant model developed for one experiment location to test discriminant capabilities for the other experiment, with discrimination accuracy across all tillage and residue systems of 48 to 72%, depending on pitted morningglory plant size.