Mangrove mapping with rapideye imagery using support vector machine

Mangrove forests play an important role in stabilizing sediments and preventing soil erosion in coastal areas. It also provides a wide range of ecological and socioeconomic services for human beings and habitats for various wildlife forms. Thus, monitoring mangrove forests is essential for evaluating the current forest management policies. The main objective of this study is to investigate the spatial distributions of mangrove forests in the Gulf of Fonseca, Central America with Rapideye imagery. The data were processed for 2012 using the support vector machine (SVM). Various spatial and non-spatial data were collected for cross-checking and preparation of the ground reference data used for accuracy assessment of the classification results. The methods of data processing basically comprise four main steps: (1) geometric correction of the Rapideye data, (2) data masking of non-vegetated areas, (3) image classification with SVM, and (4) accuracy assessment of the classification results. The comparison results between the classification map and the ground reference data indicated that the overall accuracy and Kappa coefficient were 97% and 0.95, respectively. The information on mangrove forests obtained from this study might be useful for forest managers to devise better plans for sustainable management of mangrove ecosystems. Copyright