Spectral Characteristic and Identification Modelling of Three Typical Wetland Vegetation Along the Seashore of the East Coast of the Erhai Lake
LI Xuan1, GAN Shu1, 2*, YUAN Xi-ping2, 3, 4, YANG Min3, 4, GONG Wei-zhen1
1. Faculty of Land Resources and Engineering, Kunming University of Science and Technology, Kunming 650093, China
2. Application Engineering Research Center of Spatial Information Surveying and Mapping Technology in Plateau and Mountain-ous Areas Set by Universities in Yunnan Province, Kunming 650093, China
3. West Yunnan University of Applied Sciences，Dali 67100，China
4. West Yunnan University of Applied Sciences, Key Laboratory of Mountain Real Scene Point Cloud Data Processing and Application for Universities, Dali 671006，China
Abstract：The identification of wetland vegetation using hyperspectral data has traditionally been one of the focuses of vegetation remote sensing research. Hyperspectral remote sensing data contains more detailed spectral features of vegetation, providing a powerful means for identifying hyperspectral vegetation. In this paper, the hyperspectral data of three typical wetland vegetation species, Zizania latifolia; Phragmites australis Salvinia natans; They were measured as target samples in the study area of the east coast of Erhai Lake. The original spectra were transformed by first-order differentiation and envelope removal and analysed for their spectral features. The feature wavelengths in the original spectra and their transformed spectra were selected using two feature variable selection algorithms, namely, successive projection (SPA) and competitive adaptive reweighted sampling (CARS), and the support vector machine (SVM) and random forest (RF) were finally established based on the full-wavelength data as well as the feature wavelengths after the selection-Recognition models. The results show that both SPA and CARS algorithms have a good dimensionality reduction effect on hyperspectral data, and the number of selected feature wavelengths is between 5 and 18. Comparing the combination of different spectral transform processing and feature wavelength extraction methods for modelling experiments, the envelope removal-SPA-SVM model performs the best in identifying the three types of target samples, with a recognition accuracy of 0.937 5. At this time, the number of feature wavelengths selected for input modelling is only 10, which accounts for 4.7% of the full wavelength range, which greatly reduces the model's computation time and of the selected feature wavelengths, 70% of the selected characteristic wavelengths are located in the characteristic absorption bands. Their distribution can better reflect the spectral absorption characteristic law caused by the differences in the chemical composition of vegetation. The experimental results show that the hyperspectral vegetation identification modelled by spectral transformation and feature selection is feasible and can provide a reference for other wetland vegetation identification methods.
Key words：Hyperspectral; Wetland vegetation; Spectral transformation; Feature band selection; Support vector machine; Random forests
李 璇，甘 淑，袁希平，杨 敏，龚伟圳. 洱海东岸海滨三种典型湿地植被光谱特征分析与识别建模[J]. 光谱学与光谱分析, 2024, 44(09): 2439-2444.
LI Xuan, GAN Shu, YUAN Xi-ping, YANG Min, GONG Wei-zhen. Spectral Characteristic and Identification Modelling of Three Typical Wetland Vegetation Along the Seashore of the East Coast of the Erhai Lake. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(09): 2439-2444.
[1] Anand A, Pandey P C, Petropoulos G P, et al. Remote Sensing, 2020, 12(4): 597.
[2] SUN Wei-wei, LIU Wei-wei, WANG Yi-miao, et al(孙伟伟, 刘围围, 王煜淼, 等). National Remote Sensing Bulletin（遥感学报）, 2023, 27(6): 1281.
[3] ZHAO Chun-hui, WANG Li-guo, QI Bin. (赵春晖, 王立国, 齐 滨). Hyperspectral Remote Sensing Image Processing Methods and Applications(高光谱遥感图像处理方法及应用). Beijing: Electronic Industry Publishing House（北京：电子工业出版社）, 2016.
[4] WANG Mei-ling, JIAO Lin-lin, WANG Xiao-hong, et al(王美玲, 焦琳琳, 王晓红, 等). Acta Agriculturae Zhejiangensis(浙江农业学报), 2019, 31(6): 963.
[5] YANG Mai, LI Xiao-lin, ZHENG Yi, et al(杨 迈, 李晓琳, 郑 毅, 等). Journal of Southwest Forestry University(Natural Sciences)[西南林业大学学报(自然科学)], 2024, 44(3)：80.
[6] LI Shi-bo, LIN Hui, GE Miao(李世波, 林 辉, 葛 淼). Journal of Central South University of Forestry & Technology(中南林业科技大学学报), 2019, 39(11): 36.
[7] CAO Xia-yu, ZHANG Xiang, XIAO Yang, et al(曹夏禹, 张 翔, 肖 洋, 等). Yangtze River(人民长江), 2017, 48(5): 17.
[8] XIAO Yan-fang, ZHOU De-min, GONG Hui-li, et al(肖艳芳, 周德民, 宫辉力, 等). National Remote Sensing Bulletin(遥感学报), 2015, 19(3): 368.
[9] LI Yan-ping，WANG Sheng-rui, ZHAO Hai-chao, et al(李艳平, 王圣瑞, 赵海超, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(4): 1189.
[10] LI En-hua, WANG Xue-lei, CAI Xiao-bin，et al(厉恩华, 王学雷, 蔡晓斌, 等). Journal of Lake Sciences(湖泊科学), 2011, 23(5): 738.
[11] REN Yi-jie, YAN Chang-xiang, XU Jia-wei(任颐杰, 颜昌翔, 徐嘉蔚). Chinese Optics(中国光学), 2023, 16(6): 1273.
[12] LIU Li, TAO Hong-yan, FANG Jing, et al(刘 莉, 陶红燕, 方 静, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2022, 53(2): 221.
[13] ZHANG Yu-rong, DENG Yi-hao, CHU Hong-qiang, et al(张玉荣, 邓毅浩, 褚洪强, 等). Journal of Henan University of Technology(Natural Science Edition)[河南工业大学学报(自然科学版)], 2023, 44(6): 105.
[14] JIANG Pei-han, YANG Xiao-nan, YANG Chen-xu, et al(蒋沛含, 杨晓楠, 杨晨旭, 等). Journal of Agricultural Science and Technology(中国农业科技导报), 2024, 26(6): 91.
