, Volume 36, Issue 2, pp 201–213

A Framework to Combine Three Remotely Sensed Data Sources for Vegetation Mapping in the Central Florida Everglades

Original Research

DOI: 10.1007/s13157-015-0730-7

Cite this article as:
Zhang, C., Selch, D. & Cooper, H. Wetlands (2016) 36: 201. doi:10.1007/s13157-015-0730-7


A framework was designed to integrate three complimentary remotely sensed data sources (aerial photography, hyperspectral imagery, and LiDAR) for mapping vegetation in the Florida Everglades. An object-based pixel/feature-level fusion scheme was developed to combine the three data sources, and a decision-level fusion strategy was applied to produce the final vegetation map by ensemble analysis of three classifiers k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest (RF). The framework was tested to map 11 land-use/land-cover level vegetation types in a portion of the central Florida Everglades. An informative and accurate vegetation map was produced with an overall accuracy of 91.1 % and Kappa value of 0.89. A combination of the three data sources achieved the best result compared with applying aerial photography alone, or a synergy of two data sources. Ensemble analysis of three classifiers not only increased the classification accuracy, but also generated a complementary uncertainty map for the final classified vegetation map. This uncertainty map was able to identify regions with a high robust classification, as well as areas where classification errors were most likely to occur.


Data fusion Ensemble analysis Uncertainty analysis Wetland land-use/land-cover level vegetation mapping 

Copyright information

© Society of Wetland Scientists 2015

Authors and Affiliations

  1. 1.Department of GeosciencesFlorida Atlantic UniversityBoca RatonUSA

Personalised recommendations