文献类型：期刊文献

英文题名：Plant identification of Beijing Hanshiqiao wetland based on hyperspectral data

作者：Cui, Lijuan[1,2,3] Zuo, Xueyan[1,2,3] Dou, Zhiguo[1,2,3] Huang, Yilan[1,2,3] Zhao, Xinsheng[1,2,3] Zhai, Xiajie[1,2,3] Lei, Yinru[1,2,3] Li, Jing[1,2,3] Pan, Xu[1,2,3] Li, Wei[1,2,3]

第一作者：Cui, Lijuan

通信作者：Li, W[1]

机构：[1]Chinese Acad Forestry, Inst Wetland Res, Beijing, Peoples R China;[2]Beijing Hanshiqiao Natl Wetland Ecosyst Res Stn, Beijing, Peoples R China;[3]Beijing Key Lab Wetland Ecol Funct & Restorat, Beijing, Peoples R China

年份：2021

卷号：54

期号：5

起止页码：381-394

外文期刊名：SPECTROSCOPY LETTERS

收录：;Scopus(收录号：2-s2.0-85107969432);WOS:【SCI-EXPANDED(收录号:WOS:000662090300001)】；

基金：This research was supported by China's Special Fund for Basic Scientific Research Business of Central Public Research Institutes under Grant [No. CAFYBB2017MA028].

语种：英文

外文关键词：Characteristic variables; classifiers; hyperspectral; identification; wetland plants

摘要：Hyperspectral data play an important role in monitoring and protecting wetlands because it not only offers high resolution and wide observation range but also reveal plant information. To explore the hyperspectral characteristics of wetland plants and their applicability in identification, in situ hyperspectral data for 15 species of wetland plants were collected from the Hanshiqiao Wetland Nature Reserve in Beijing, a constructed wetland. Then, first derivative, second derivative, and logarithmic transformation of the reciprocal of the hyperspectral reflectance data were performed using three data conversion methods (principal component analysis, vegetation index, and full-band spectrum) to identify characteristic hyperspectral variables. Four classifiers were compared, namely, support vector machine, decision tree, back-propagation neural network, and random forest. The results demonstrated that: (1) for a comprehensive comparison of the four spectral features data, logarithmic treatment of the reciprocal significantly improved the identification accuracy; (2) for the three data conversion methods for identifying spectral characteristics, the identification accuracy based on the full-band spectrum was better than the other two data forms, and the identification effectiveness of principal component analysis was better than that of the vegetation index; (3) because of differences in plant types and data formats, none of the four classifiers had obvious advantages or disadvantages over the others; and (4) the identification results for all plant statistics further verified the applicability of full-band spectrum data for plant identification. The results showed that the vegetation index and principal component variables reduced the calculation time but did not improve the identification accuracy. Overall, the spectral variables and classifiers examined in this study could meet the needs of wetland plant identification to a certain extent.