Skip to main content
ARS Home » Research » Publications at this Location » Publication #193862
Title: MAPPING WATERHYACINTH INFESTATIONS WITH QUICKBIRD SATELLITE IMAGERY

Author
item Everitt, James
item Yang, Chenghai

Submitted to: Forest Service Remote Sensing Conference Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 3/28/2006
Publication Date: 6/15/2006
Citation: Everitt, J.H., Yang, C. 2006. Mapping waterhyacinth infestations with QuickBird satellite imaggery. Forest Service Remote Sensing Conference Proceedings. CDROM.

Interpretive Summary: Waterhyacinth is an exotic, invasive aquatic weed that often invades and clogs waterways in subtropical and tropical areas of the world. Waterhyacinth is considered the world’s worst aquatic weed and occurs in over 50 countries. QiuckBird satellite imagery was evaluated for distinguishing waterhyacinth infestations in a large reservoir in south Texas. Unsupervised and supervised image analysis techniques were used to classify false color composite images of two study sites. Accuracy assessments performed on unsupervised classification maps of the two sites had producer’s and user’s accuracies for waterhyacinth ranging from 80% to 100%, while accuracy assessments performed on supervised classification maps of the two sites had producer’s and user’s accuracies for waterhyacinth ranging from 73% to 100%. These results should be of interest to wetland resource managers.

Technical Abstract: QuickBird false color satellite imagery was evaluated for distinguishing waterhyacinth [Eichhornia crassipes (Mort.) Solms] infestations in a large reservoir in south Texas. The imagery had three bands (green, red, and near-infrared) and contained 11-bit data. Two subsets of the satellite image were extracted and used as study sites. Supervised and unsupervised classification techniques were used to classify the imagery. Accuracy assessments performed on unsupervised classification maps of the two sites had producer’s and user’s accuracies for waterhyacinth ranging from 80% to 100%, while accuracy assessments performed on supervised classification maps of the two sites had producer’s and user’s accuracies for waterhyacinth ranging from 73% to 100%. These results indicate QuickBird imagery coupled with image analysis techniques can be used successfully for detecting and mapping waterhyacinth infestations.