Skip to main content
ARS Home » Research » Publications at this Location » Publication #279727

Title: Remote distinction of a noxious weed (musk thistle: Carduus nutans) using airborne hyperspectral imagery and the support vector machine classifier

Author
item MIRIK, MUSTAFA - Texas Agrilife Research
item ANSLEY, R. JAMES - Texas Agrilife Research
item STEDDOM, KARL - Texas Agrilife Research
item JONES, DAVID - Texas Agrilife Research
item RUSH, CHARLES - Texas Agrilife Research
item MICHELS, JR., GERALD - Texas Agrilife Research
item Elliott, Norman - Norm

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/18/2013
Publication Date: 2/1/2013
Citation: Mirik, M., Ansley, R.J., Steddom, K., Jones, D.C., Rush, C.M., Michels Jr., G.J., Elliott, N.C. 2013. Remote distinction of a noxious weed (musk thistle: Carduus nutans) using airborne hyperspectral imagery and the support vector machine classifier. Remote Sensing. 5(2):612-630.

Interpretive Summary: Remote detection of invasive plant species using geospatial imagery may significantly improve monitoring, planning, and management practices by eliminating shortfalls such as observer bias and accessibility involved in ground-based surveys. The use of remote sensing for accurate mapping invasion extent and pattern offers a set of advantages including repeatability, large area coverage, and cost-effectiveness over ground-based methods. It is particularly and practically critical for locating, early mapping, and controlling small infestations before they reach economically and ecologically significant levels over larger land areas. This study was designed to explore the ability of remote sensing for mapping musk thistle infestation in mid-April and at peak flowering stage in mid-June. These results indicate that repeated detection of the infestation extent, as well as infestation severity or intensity of this noxious weed is possible using remote sensing imagery.

Technical Abstract: Remote detection of invasive plant species using geospatial imagery may significantly improve monitoring, planning, and management practices by eliminating shortfalls such as observer bias and accessibility involved in ground-based surveys. The use of remote sensing for accurate mapping invasion extent and pattern offers a set of advantages including repeatability, large area coverage, and cost-effectiveness over ground-based methods. It is particularly and practically critical for locating, early mapping, and controlling small infestations before they reach economically and ecologically significant levels over larger land areas. This study was designed to explore the ability of hyperspectral imagery for mapping preflowering-stage Carduus nutans infestation in mid-April and at peak flowering stage in mid-June using the support vector machine classifier and; to assess and compare the resulting mapping accuracy for these two distinctive phenological stages. Accuracy assessment revealed that the overall accuracies were 79 and 91% with kappa coefficients 0.57 and 0.81 for the classified images at pre-flowering and peak flowering stages, respectively. These results indicate that repeated detection of the infestation extent, as well as infestation severity or intensity of this noxious weed in a spatial and temporal context is possible using hyperspectral remote sensing imagery.