Construction of a tree-species classification map using multispectral images of UAVs: A case study of the Dong Rui Commune wetlands, Vietnam

Abstract

Abstract Wetlands provide resources, regulate the environment, and stabilize shorelines; however, they are among the most vulnerable ecosystems in the world. Managing and monitoring wetland ecosystems are important for the development and maintenance of ecosystem services and their sustainable use in the context of climate change. We used Phantom 4 multispectral unmanned aerial vehicles (UAVs) to collect data from wetland areas in the Dong Rui Commune, which is one of the most diverse and valuable wetland ecosystems in northern Vietnam. A tree-species classification map was constructed through a combination of the visual classification method and spectral reflectance values of each plant species, and the characteristic distributions of mangrove plants, including Bruguiera gymnorrhiza, Rhizophora stylosa, and Kandelia obovata, were determined with an overall accuracy of 91.11% and a kappa coefficient (K) of 0.87. Universal reflectance graphs of each mangrove plant species were constructed for five wave channels, including blue, green, red, red edges, and near-infrared and the normalized difference vegetation index (NDVI). An experiment was conducted to map plant taxonomy in the same area based only on a graph of spectral reflectance values at five single-spectral bands and constructed NDVI values, resulting in an overall accuracy of 78.22% and a K of 0.67. The constructed map is useful for classifying, monitoring, and evaluating the structure of each group of mangroves, thereby enabling the efficient management and conservation of the Dong Rui Commune wetlands.