Remote detection of invasive Melaleuca trees (Melaleuca quinquenervia) in South Florida with multispectral IKONOS imagery

Abstract

The distribution of invasive Melaleuca (Melaleuca quinquenervia (Cav.) S.T. Blake) was mapped using 4‐m spatial resolution, multispectral IKONOS imagery in an area of south Florida along the eastern edge of Everglades National Park. Detection of Melaleuca stands was achieved using a back‐propagation neural network classifier, which allowed identification of dense stands, but in some instances misclassified other woody canopies as Melaleuca. The use of IKONOS multispectral imagery to detect low‐density occurrences of Melaleuca appears limited relative to traditional methods of aerial photographic interpretation. However, analysis of landscape‐level distribution of moderate‐to‐dense Melaleuca, using Fragstats, indicated a highly aggregated Melaleuca distribution relative to other woody vegetation patches. The distribution of Melaleuca stands was associated with cultural features in the suburban environment such as canals and roads, which may act as dispersal corridors for seeds. Thus, classified IKONOS imagery may be useful for inferring landscape patterns that relate to the persistence and spread of Melaleuca and other invasive species.