连续小波结合随机森林算法估算互花米草叶片叶绿素含量

doi:10.3964/j.issn.1000-0593(2024)10-2993-08

摘要
参考文献
相关文章 (15)

全文: PDF (12971 KB)
输出: BibTeX | EndNote (RIS)

摘要：叶绿素含量是检测植物生理状态的关键指标，精准估算互花米草叶绿素含量对于表征其组分含量性状与量化其生理状态具有重要的意义。以独流减河湿地互花米草实测高光谱反射率和叶绿素含量为数据源，采用连续投影算法（sequential projection algorithm，SPA）对原始光谱及其数学变换和连续小波变换光谱进行特征提取，基于随机森林回归（random forest regression，RFR）算法建立互花米草叶片叶绿素含量的高光谱估算模型。结果表明：（1）连续小波分解低尺度下互花米草光谱时间分辨率更精确且频率更高，对应的小波函数较窄，可以更好区分光谱间差异，突出特征光谱信息。（2）除倒数(1/R)和对数的一阶微分[(logR)′]外，光谱数学变换与连续小波分解方法可有效反应光谱细节特征，且小波分解效果总体上优于数学变换，小波分解L10尺度与一阶微分（R′）分别与叶绿素含量的相关性达到0.78和0.77。（3）一阶微分(R′)、倒数的一阶微分[(1/R)′]、对数(logR)变换和连续小波分解可提升光谱对互花米草叶片叶绿素含量的估算能力，其中基于一阶微分R′（R²=0.776，RMSE=0.510，RPD=1.893）和连续小波分解下L2、L3与L4多尺度相结合构建的模型（R²=0.871，RMSE=0.305，RPD=3.846）分别为两种处理下的最优模型。研究表明高光谱技术可以作为互花米草叶片叶绿素含量的无损检测手段，连续小波分解后多尺度结合建立的高光谱估算模型可更加准确估算互花米草叶片叶绿素含量。

关键词：互花米草；叶绿素含量；高光谱；连续小波分解；随机森林

Abstract：Chlorophyll content is a key indicator of the physiological status of plants, and accurate estimation of chlorophyll content is important for characterizing its component content traits and quantifying its physiological status. In this paper, the hyperspectral reflectance and chlorophyll content (SPAD) of Spartina alterniflora in the Duliu-river wetland were used as the data source, the original spectrum was mathematically transformed and processed with continuous wavelet transformation (CWT). The spectral features were extracted using Sequential Projection Algorithm (SPA). And the hyperspectral estimation model of leaf chlorophyll content of Spartina alterniflora was developed based on random forest regression (RFR) algorithm. The results showed that: (1) CWT had more accurate time resolution and higher frequency in the low scale spectra, corresponding to a narrow wavelet function, which could better distinguish the differences between the spectra and highlight the characteristic spectral information. (2) Except for reciprocal and logarithmic first derivative spectrals, the spectral mathematical transform and CWT methods could effectively respond to the spectral detail features. CWT was generally better than the spectral mathematical transform, and the correlation between L10 scale and first derivative spectral reached 0.78 and 0.77. (3) First derivative spectral, reciprocal first derivative spectral, logarithmic derivative spectral and CWT could enhance the ability of spectral estimation of Spartina alterniflora chlorophyll content. The RF models based on first derivative spectral (R²=0.776, RMSE=0.510, RPD=1.893) and CWT with the multiscale of L2, L3 and L4 (R²=0.871, RMSE=0.305, RPD=3.846) were the optimal models. This study shows that hyperspectral techniques could be used as a non-destructive means of detecting chlorophyll content in leaves of Spartina alterniflora, and that the hyperspectral estimation model built by combining multiple scales after continuous wavelet decomposition could more estimate chlorophyll content in leaves of Spartina alterniflora.

Key words：Spartina alterniflora; Chlorophyll content; Hyperspectral; Continuous wavelet decomposition; Random forest

收稿日期: 2023-07-18 修订日期: 2023-12-22

中图分类号:

X87

基金资助: 国家自然科学基金项目(41901375，42101393，52274166)，河北省自然科学基金项目(D2019209322，D2022209005)，河北省高等学校科学技术研究项目青年拔尖人才项目(BJ2020058)，唐山市科技计划重点研发项目(22150221J)资助

通讯作者: 刘明月 E-mail: liumy917@ncst.edu.cn

作者简介: 管铖，女，1997年生，华北理工大学矿业工程学院硕士研究生 e-mail: guancheng@stu.ncst.edu.cn

引用本文:

管铖，刘明月，满卫东，张永彬，张清文，方铧，李想，高汇锋. 连续小波结合随机森林算法估算互花米草叶片叶绿素含量[J]. 光谱学与光谱分析, 2024, 44(10): 2993-3000.
GUAN Cheng, LIU Ming-yue, MAN Wei-dong, ZHANG Yong-bin, ZHANG Qing-wen, FANG Hua, LI Xiang, GAO Hui-feng. Estimation of Chlorophyll Content in Spartina Alterniflora Leaves Based on Continous Wavelet Transformation and Random Forest Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(10): 2993-3000.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)10-2993-08 或 https://www.gpxygpfx.com/CN/Y2024/V44/I10/2993

[1] GENG Guo-biao(耿国彪). Green China(绿色中国), 2023, 4: 8.
[2] CHEN Pan, ZHANG Yan, ZHU Xiao-jing, et al(陈潘, 张燕, 朱晓静, 等). Acta Ecologica Sinica(生态学报), 2019, 39(7): 2282.
[3] YU Cai-fen, CHEN Peng-fei, LIU Chang-an, et al(于彩芬, 陈鹏飞, 刘长安, 等). Ocean Development and Management(海洋开发与管理), 2014, 31(8): 85.
[4] REN Hong, LUO Feng, XU Yan, et al(任红, 罗丰, 许彦，等). Journal of Anhui Agricultural Sciences(安徽农业科学), 2014, 40(3): 1455.
[5] SHU Tian, LI Rui-jun, CHEN Zhi-hu, et al(舒田，黎瑞君，陈智虎，等). Jiangsu Agricultural Sciences(江苏农业科学)，2023，51(9)：222.
[6] Guo T, Tan C, Li Q, et al. Journal of Ambient Intelligence and Humanized Computing, 2019, 10: 3239.
[7] Cheng J, Yang G, Xu W, et al. Agronomy, 2022, 12(7): 1497.
[8] ZHANG Xue-ru, FENG Mei-chen, YANG Wu-de, et al(张雪茹, 冯美臣, 杨武德, 等). Chinese Journal of Eco-Agriculture(中国生态农业学报), 2017, 25(9): 1351.
[9] GUO Chao-fan, GUO Xiao-yu(郭超凡, 郭逍宇). Acta Ecologica Sinica(生态学报), 2016, 36(20): 6538.
[10] LI Li-jie, YUE Yan-bin, WANG Yan-cang, et al(李莉婕, 岳延滨, 王延仓, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(11): 3538.
[11] PEI Hao-jie, FENG Hai-kuan, LI Chang-chun, et al(裴浩杰, 冯海宽, 李长春, 等). Jiangsu Agricultural Sciences(江苏农业科学), 2018, 46(17): 224.
[12] JI Wei-shuai, CHEN Hong-yan, WANG Shu-ting, et al(纪伟帅, 陈红艳, 王淑婷, 等). Chinese Agricultural Science Bulletin(中国农学通报), 2021, 37(22): 143.
[13] Shen R, Zhang B W. MATEC Web of Conference, 2018, 176: 01033.
[14] Sharifzadeh M, Sikinioti-Lock A, Shah N. Renewable and Sustainable Energy Reviews, 2019, 108: 513.
[15] Meacham-Hensold K, Montes C M, Wu J, et al. Remote Sensing of Environment, 2019, 231: 111176.
[16] Zhang J, Zhang D, Cai Z, et al. Computers and Electronics in Agriculture, 2022, 195: 106814.
[17] ZUO Xue-yan, CUI Li-juan, LI Wei, et al(左雪燕, 崔丽娟, 李伟, 等). Acta Ecologica Sinica(生态学报), 2021, 41(15): 6159.
[18] Tzenios N. ResearchBerg Review of Science and Technology, 2020, 3(1): 94.
[19] FENG Hai-kuan, YANG Fu-qin, YANG Gui-jun, et al(冯海宽, 杨福芹, 杨贵军, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2018, 34(6): 182.
[20] WANG Li-ai, MA Chang, ZHOU Xu-dong, et al(王丽爱, 马昌, 周旭东, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2015, 46(1): 259.
[21] CHAI Zi-wen, LEI Wei-pan, MO Xun-qiang, et al(柴子文, 雷维蟠, 莫训强, 等). Wetland Science(湿地科学), 2020, 18(6): 667.
[22] ZHOU Xiao-sheng, ZHOU Yue-qin, PANG Lei, et al(周小生，周月琴，庞磊，等). Journal of Anhui Agricultural University(安徽农业大学学报)，2012，39(1)：150.
[23] Huang L, Li T, Ding C, et al. Sensors, 2020, 20(10): 2887.
[24] ZHAO Hai-long, GAN Shu, YUAN Xi-ping, et al(赵海龙, 甘淑, 袁希平, 等). Acta Optica Sinica(光学学报), 2022, 42(22): 209.
[25] TIAN Fu-ying, SUN Ying(田福英, 孙迎). Journal of Biomedical Engineering(生物医学工程学杂志), 2015, 32(3): 514.
[26] WAN Tao-lei, CHANG Jun-jie(万陶磊, 常俊杰). Nondestructive Testing(无损检测), 2019, 41(11): 43.
[27] SUN Xing-liang, HAO Xiao-hua, WANG Jian, et al(孙兴亮, 郝晓华, 王建, 等). Journal of Glaciology and Geocryology(冰川冻土), 2022, 44(1): 147.
[28] LI Zhen, WANG Jia-qiang, LI Zi-qin, et al(李贞，王家强，李紫琴，等). Acta Agriculture Universitatis Jiangxiensis(江西农业大学学报)，2023，45(5)：1273.
[29] LI Wen-ya(李文雅). Molecular Plant Breeding(分子植物育种), 2022, 20(24): 8586.