Identification for the species of aquatic higher plants in the Taihu Lake basin based on hyperspectral remote sensing

Abstract

Abstract Aquatic plants are crucial for an aquatic ecosystem, and their species and distribution reflect aquatic ecosystem health. Remote sensing technology has been used to monitor plant distribution on a large scale. However, the fine identification of aquatic plants is a great challenge due to large temporal-spatial changes in optical properties of water bodies and small spectral differences among plant species. Here, the identification method of each aquatic plant was developed by constructing the decision tree file of the C4.5 algorithm based on the canopy spectra of 8 plants in the Changguangxi Wetland water area measured with hyperspectral remote sensing technology, and then the method was finally used to monitor the distribution of different plants in Changguangxi Wetland water area and two other water areas. The results show that the spectral characteristics of plants is enhanced by calculating the spectral index of aquatic plants, thereby improving the comparability among different species. The total recognition accuracy of the constructed decision tree file for 8 types of plants is 85.02%, among which the recognition accuracy of Nymphaea tetragona, Pontederia cordata, and Nymphoides peltatum is the highest, and the recognition accuracy of Eichhornia crassipes is the lowest. The specific species and distribution of aquatic plants are consistent with the water quality in the water area. The results can provide a reference for the accurate identification of aquatic plants in the same type of water area.