Submitted to: Geocarto International
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/1/2011
Publication Date: 5/31/2012
Citation: Yang, C., Goolsby, J., Everitt, J.H., Du, Q. 2012. Applying six classifiers to airborne hyperspectral imagery for detecting giant reed. Geocarto International. 27(5):413-424. Interpretive Summary: Accurate information on the spatial distribution and infested areas of giant reed is essential for effective management of this invasive weed. This study evaluated six different image classification techniques to identify giant reed from airborne hyperspectral imagery taken from a site along the US-Mexican portion of the Rio Grande in 2009 and 2010. Accuracy assessment showed that two classification techniques (support vector machine and maximum likelihood) can be used to more effectively distinguish giant reed from associated plant species.
Technical Abstract: This study evaluated and compared six different image classifiers, including minimum distance (MD), Mahalanobis distance (MAHD), maximum likelihood (ML), spectral angle mapper (SAM), mixture tuned matched filtering (MTMF) and support vector machine (SVM), for detecting and mapping giant reed (Arundo donax L.), an invasive weed that presents a severe threat to agroecosystems and riparian areas throughout the southern United States and northern Mexico. Airborne hyperspectral imagery with 102 usable bands covering a spectral range of 475-845 nm was collected from a giant reed-infested site along the US-Mexican portion of the Rio Grande in 2009 and 2010. The imagery was transformed with minimum noise fraction (MFN) to reduce the spectral dimensionality and noise. The six classifiers were applied to the 30-band transformed MNF imagery for each of the two years. Accuracy assessment and kappa analysis showed that SVM and ML generally performed better than the other four classifiers for overall classification and for distinguishing giant reed in both years. These results indicate that airborne hyperspectral imagery in conjunction with SVM and ML classification techniques is effective for detecting giant reed.