Identification of Mangrove Using Decision Tree Method

Abstract

The classification accuracy of mangrove is always low due to the similarity of spectra between mangrove and water-vegetation mixed pixels. Greenness and wetness were extracted by K-T transformation based on Landsat5/TM imagery. The greenness and wetness can significantly improve the separability between mangrove and water-vegetation mixed pixels by comparison with NDVI, TM3/TM5,TM5/TM4, which always were employed by other researchers. The Kappa coefficient, commission error of mangrove class were 0.90, 7.9%, respectively, by using decision tree method.