Modelling Wetland Vegetation Identification at Multiple Variational Mode Decomposition
LI Xuan2, YUAN Xi-ping1, 3*, GAN Shu2, 3, YANG Min1, GONG Wei-zhen2, PENG Xiang2
1. West Yunnan University of Applied Sciences, Key Laboratory of Mountain Real Scene Point Cloud Data Processing and Application for Universities, Dali 671006, China
2. Faculty of Land Resources and Engineering, Kunming University of Science and Technology, Kunming 650093, China
3. 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
Abstract：Hyperspectral data are characterized by high dimensionality and richer feature information. This high-dimensional data provides more opportunities to improve classification accuracy and precision in vegetation classification. Traditional feature wavelength modelling often results in poor classification accuracy due to too many input variables. To overcome this problem and improve the ability of the model to capture the subtle spectral differences of wetland vegetation, this paper explores the east coast of the Erhai Lake as the study area and hyperspectral data of three typical wetland vegetation (Mizuno, Ruscus, and Sophora japonica) are measured as the target samples.The sample spectral curves were SG smoothing as original spectra (OS), continuum removal transform (CR), and first-order differentiation (FD) and analyzed for spectral features; then, the original spectra were decomposed by Variational mode decomposition (VMD) into 8 scales. Next, the wavelengths selected by the Competitive adaptive reweighted sampling (CARS) algorithm were used as the characteristic wavelengths. Finally, the best combination of parameters found was used to put into the Bayesian algorithm optimized support vector machine (Bayes-SVM) for modeling. The results show that the number of feature wavelengths extracted by the CARS algorithm is reduced, and most of them are distributed in the absorption feature intervals of vegetation, and the effect of dimensionality reduction is significant; the model constructed by the 4th mode after decomposition (S4-CARS-Bayes-SVM) has the best classification effect, with a precision rate (PR) of 0.933 3, a recall rate (RR) of 0.888 9, an F1 score of 0.896 3, and AUC value of 0.928 6, i.e., this model has strong robustness as well as recognition performance.
[1] LIU Rui, GAO Chuan-yu, HAN Dong-xue, et al（刘 蕤, 高传宇, 韩冬雪，等）. Wetland Science(湿地科学). 2024, 22(2): 303.
[2] Costanza R, d'Arge R, de Groot R, et al. The Value of the World's Ecosystem Services and Natural Capital. Nature，1997, 387：253.
[3] ZHANG Qiang（张 强）. World Forestry Research（世界林业研究），2019, 32(3): 49.
[4] LIN Chuan, GONG Zhao-ning, ZHAO Wen-ji, et al（林 川, 宫兆宁, 赵文吉, 等）. Acta Ecologica Sinica（生态学报），2013, 33(4): 1172.
[5] Crasto N, Hopkinson C, Forbes D L, et al. Remote Sensing of Environment, 2015, 164: 90.
[6] KUANG Run-yuan, ZENG Shuai, ZHAO Zhe, et al（况润元, 曾 帅, 赵 哲, 等）. Journal of Lake Sciences(海洋科学)，2017, 29(6): 1485.
[7] XU Chen, LU Xia, SANG Yu, et al（许 晨, 卢 霞, 桑 瑜, 等）. Marine Sciences（海洋科学），2023, 47(7): 1.
[8] LUO Ning, RUAN Ren-zong, WANG Jun-hai（罗 宁, 阮仁宗, 王俊海）. Chinese Agricultural Science Bulletin（中国农学通报），2019, 35(13): 157.
[9] ZHOU Bei-bei, LI Heng-kai, LONG Bei-ping（周贝贝, 李恒凯, 龙北平）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2023, 43(12): 3946.
[10] Li Chige, Li Hengkai, Zhou Yanbing, et al. Sustainability，2024, 16：3582.
[11] Li Hengkai, Zhou Beibei, Xu Feng. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 4408412.
[12] TIAN Yu-qing, CHEN Xin, LÜ Chao-chao, et al（田玉清, 陈 欣, 吕超超, 等）. Journal of Lake Sciences（湖泊科学），2023, 35(3): 941.
[13] 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.
[14] DONG Shi, LONG Zhi-you, BI Jie-fu, et al（董 是, 龙志友, 毕洁夫, 等）. Bulletin of Surveying and Mapping(测绘通报)，2023, (9): 100.
[15] LUO Yi-yong, YAO Yi-bin, HUANG Cheng, et al（罗亦泳, 姚宜斌, 黄 城, 等）. Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版)，2020, 45(4): 612.
[16] ZHANG Nan-nan, ZHANG Xiao, BAI Tie-cheng, et al（张楠楠, 张 晓, 白铁成, 等）. Transactions of the Chinese Society for Agricultural Machinery，2023, 54(S1): 239.
[17] LAI Bao, WAN Ren-xia, ZHAO Jie, et al（赖 宝, 万仁霞, 赵 杰, 等）. Journal of Minnan Normal University(Natural Science)[闽南师范大学学报(自然科学版)]，2023, 36(3): 22.
