|Lawrence, Rick - MONTANA STATE UNIVERSITY|
|Wood, Shana - MONTANA STATE UNIVERSITY|
Submitted to: American Society for Photogrammetry and Remote Sensing Proceedings
Publication Type: Abstract Only
Publication Acceptance Date: October 29, 2005
Publication Date: October 30, 2006
Citation: Lawrence, R., Wood, S., Sheley, R.L. 2006. Mapping invasive plants using hyperspectral imagery, classification trees, and classification thresholds [abstract]. American Society for Photogrammetry and Remote Sensing Proceedings. 100(2006):356-362. Technical Abstract: Invasive nonindigenous plants are threatening the biological integrity of North American rangelands, as well as the economies that are supported by those ecosystems. Spatial information is critical to fulfilling invasive plant management strategies. Traditional invasive plant mapping has utilized ground-based hand or GPS mapping. The shortfalls of ground-based methods include the limited spatial extent covered and the associated time and cost. Mapping vegetation with remote sensing covers large spatial areas and maps can be updated at an interval determined by management needs. The objective of the study was to map leafy spurge (Euphorbia esula L.) and spotted knapweed (Centaurea maculosa Lam.) using 128-band hyperspectral (5 m and 3 m resolution) imagery and assess the accuracy of the resulting maps. Classification tree analysis (CTA) was used to classify the hyperspectral imagery and classification thresholds were applied to the accuracy assessment to evaluate the e! ffects of target species being over represented in the resulting maps. Target species map accuracies were 61% for leafy spurge and 74% for spotted knapweed. When classification thresholds allowed limited amounts of target species pixels to be present at non-target species sites, an alternative measure of accuracy was provided with 82% for leafy spurge and 86% for spotted knapweed, although estimates of total area infested could not be made and infestation sites could not be precisely located with this alternative approach.