Evaluation of airborne lidar data to predict vegetation Presence/Absence

Journal of Coastal Research
By: , and 

Links

Abstract

This study evaluates the capabilities of the Experimental Advanced Airborne Research Lidar (EAARL) in delineating vegetation assemblages in Jean Lafitte National Park, Louisiana. Five-meter-resolution grids of bare earth, canopy height, canopy-reflection ratio, and height of median energy were derived from EAARL data acquired in September 2006. Ground-truth data were collected along transects to assess species composition, canopy cover, and ground cover. To decide which model is more accurate, comparisons of general linear models and generalized additive models were conducted using conventional evaluation methods (i.e., sensitivity, specificity, Kappa statistics, and area under the curve) and two new indexes, net reclassification improvement and integrated discrimination improvement. Generalized additive models were superior to general linear models in modeling presence/absence in training vegetation categories, but no statistically significant differences between the two models were achieved in determining the classification accuracy at validation locations using conventional evaluation methods, although statistically significant improvements in net reclassifications were observed. ?? 2009 Coastal Education and Research Foundation.
Publication type Article
Publication Subtype Journal Article
Title Evaluation of airborne lidar data to predict vegetation Presence/Absence
Series title Journal of Coastal Research
DOI 10.2112/SI53-010.1
Issue SPECIAL ISSUE 53
Year Published 2009
Language English
Larger Work Type Article
Larger Work Subtype Journal Article
Larger Work Title Journal of Coastal Research
First page 83
Last page 97
Google Analytic Metrics Metrics page
Additional publication details