张曼胤1, 3,,,
崔丽娟1, 2,
王贺年1, 3,
郭子良1, 3,
李伟1, 2,
魏圆云1, 3,
杨思1, 3,
龙颂元1, 3
1.中国林业科学研究院湿地研究所/湿地生态功能与恢复北京市重点实验室 北京 100091
2.北京汉石桥湿地生态系统国家定位观测研究站 北京 101399
3.河北衡水湖湿地生态系统国家定位观测研究站 衡水 053000
基金项目: 中央级公益性科研院所基本科研业务费专项CAFINT2014K05
详细信息
作者简介:李梦洁, 主要研究方向为湿地生态学。E-mail:993288528@qq.com
通讯作者:张曼胤, 主要研究方向为湿地生态学及湿地景观与规划设计。E-mail:cneco@126.com
中图分类号:X5计量
文章访问数:638
HTML全文浏览量:4
PDF下载量:598
被引次数:0
出版历程
收稿日期:2018-01-31
录用日期:2018-05-03
刊出日期:2018-11-01
Inversion of Hg content in reed leaf using continuous wavelet transformation and random forest
LI Mengjie1, 3,,ZHANG Manyin1, 3,,,
CUI Lijuan1, 2,
WANG Henian1, 3,
GUO Ziliang1, 3,
LI Wei1, 2,
WEI Yuanyun1, 3,
YANG Si1, 3,
LONG Songyuan1, 3
1. Institute of Wetland Research, Chinese Academy of Forestry/Beijing Key Laboratory of Wetland Services and Restoration, Beijing 100091, China
2. Hanshiqiao National Wetland Ecosystem Research Station, Beijing 101399, China
3. Heibei Hengshuihu National Wetland Ecosystem Research Station, Hengshui 053000, China
Funds: the Fundamental Research Funds of Central-level Nonprofit Research Institutes of ChinaCAFINT2014K05
More Information
Corresponding author:ZHANG Manyin, E-mail:cneco@126.com
摘要
HTML全文
图
参考文献
相关文章
施引文献
资源附件
访问统计
摘要
摘要:植物重金属污染是当今世界面临的重大生态环境问题之一，高光谱技术为快速、大面积监测植被重金属含量提供了可能性。本研究以重金属汞（Hg）和湿地植物芦苇为研究对象，采用连续小波变换（CWT）和随机森林（RF）算法相结合的方法建立芦苇叶片总汞含量反演模型，以期寻求一种较为精准的植物汞污染反演模型，未来可通过高光谱技术建立模型来无损、快速估测湿地植物重金属汞污染情况，为湿地生态系统的监测提供方法支持。结果表明：芦苇叶片总汞含量敏感波段主要分布在可见光波段419~522 nm、664~695 nm和724~876 nm以及近红外波段1 450~1 558 nm和1 972~2 500 nm；经CWT变换后，小波系数与叶片总汞含量的相关系数绝对值提高0.04~0.18，所构建的预测反演模型拟合效果R2提高0.107~0.177，模型精度RMSE提高0.008~0.013，其中利用经小波变换的去包络线光谱（CR-CWT）数据建立的RF模型对芦苇叶片总汞含量的反演精度和拟合效果最优（R2=0.713，RMSE=0.127）；同时在土壤总汞含量约为20 mg·kg-1时，采用CR-CWT数据构建RF模型的方法来反演芦苇叶片总汞含量更为准确和可靠（R2=0.825，RMSE=0.051）。因此，利用RF算法进行植被重金属含量的反演具有一定的现实可行性，而结合CWT后所构建的反演模型对指导植被重金属含量监测更具参考价值，应用前景广阔。
关键词:连续小波变换/
随机森林/
高光谱/
重金属汞/
芦苇叶片
Abstract:Heavy metal pollution of plants is one of the most important eco-environmental problems in the world. Rapid and large-scale monitoring of heavy metal content in plants has always been an international problem and a key research topic. Due to its high resolution, multiple band and abundant data, hyperspectral technology could offer a rapid and accurate determination of heavy metal pollution in plants. It can be used to detect the absorption, reflection and transmission characteristics of spectral bands corresponding to phytochemical components and to quantitatively analyze weak spectral differences for large-scale determination of the growth and health of plants. However, researchers mostly construct sensitive spectral parameters (e.g., vegetation index) through simple spectral transformation techniques and continuous removal methods. Most of the inversion models are of univariate regression, multiple stepwise regression, principal component regression and other empirical or semi-empirical models. There have also been uses of artificial networks and support vector machine models. These models not only require more training sets, but also easily over-fit. Thus continuous wavelet transform (CWT) and Random Forest (RF) algorithms are used as more accurate models for inverting heavy metal pollution in plants. While CWT model can more clearly characterize spectral signals, RF has strong fitting ability and also has shorter iteration time. It has higher calculation efficiency for large datasets such as hyperspectral data and is superior in model construction. The heavy metal mercury (Hg) and the wetland plant reed (Phragmites communis) were used in this research to test the effectiveness off the CWT and RF models. CWT was used to decompose continuous wavelength at different scales in the original spectral reflectivity (R), first-order derivative reflectivity (FD) and de-envelope reflectivity (CR). Correlation analysis was used to determine sensitive bands of R, FD, CR, the spectral reflectance by continuous wavelet transform (R-CWT), the first derivative reflectivity by continuous wavelet transform (FD-CWT) and de-envelope reflectivity by continuous wavelet transform based on the correlation with leaf total Hg content. Then the sensitive bands and RF algorithm were used to establish the inversion model of reed leaf total Hg content. The results showed that sensitive bands of leaf total Hg content were mainly distributed in the visible regions of 419-522 nm, 664-695 nm and 724-876 nm, and the near-infrared regions of 1 450-1 558 nm and 1 972-2 500 nm. After CWT transformation, the absolute value of correlation coefficient between wavelet coefficient and leaf total Hg content increased by 0.04-0.18, the fitting effect (R2) of the prediction inversion model increased by 0.107-0.177 and the accuracy (RMSE) of the prediction inversion model increased by 0.008-0.013. The RF model which used continuum removal reflectance after wavelet transformation (CR-CWT) had optimal inversion precision and fitting effect (R2=0.713, RMSE=0.127). At the same time, it was more accurate and reliable to use RF model with CR-CWT to retrieve leaf total Hg content when soil total Hg content was about 20 mg·kg-1 (R2=0.825, RMSE=0.051). Therefore, it was feasible to use RF algorithm to retrieve heavy metal content in plants. The inversion model constructed by CWT had a more reference value in terms of monitoring heavy metal content in plants. The model was widely used and provided methodological support for non-destructive and rapid monitoring of heavy metal pollution in ecosystems.
Key words:Continuous wavelet transformation/
Random forest/
Hyperspectral data/
Heavy metal mercury/
Reed leaf
HTML全文
图1芦苇叶片总汞含量与原始光谱反射率(a)、一阶导数光谱(b)、去包络线光谱(c)的相关性分析
Figure1.Correlation analysis of reed leaf total Hg content with reflectance (a), first derivative spectral reflectance (b) and continuum removal spectral reflectance (c)
下载: 全尺寸图片幻灯片
图2原始光谱小波系数(a)、一阶导数光谱小波系数(b)、去包络线光谱小波系数(c)与芦苇叶片总汞含量的相关系数图
Figure2.Correlation scalogram between total Hg content and reflectance wavelet coefficient (a), first derivative spectral reflectance wavelet coefficient (b) and continuum removal wavelet coefficient (c) of reed leaf
下载: 全尺寸图片幻灯片
图3原始光谱小波系数(a)、一阶导数光谱小波系数(b)、去包络线光谱小波系数(c)小波系数与芦苇叶片总汞含量的决定系数图
Figure3.Correlation of determination scalogram between total Hg content and reflectance wavelet coefficient (a), first derivative spectral reflectance wavelet coefficient (b) and continuum removal wavelet coefficient (c) of reed leaf
下载: 全尺寸图片幻灯片
图4利用原始光谱(a)、一阶导数光谱(b)、去包络线光谱(c)、原始光谱小波系数(d)、一阶导数光谱小波系数(e)以及去包络线小波系数(f)反演芦苇叶片总汞含量的实测值与预测值比较
Figure4.Comparisons of the measured values of reed leaf total Hg content with the estimated values by using reflectance (a), first derivative spectral reflectance (b), continuum removal spectral reflectance (c), reflectance wavelet coefficient (d), first derivative spectral reflectance wavelet coefficient (e) and continuum removal wavelet coefficient (f)
下载: 全尺寸图片幻灯片表1叶片总汞含量描述性统计特征
Table1.Descriptive statistics of leaf total Hg content
| 样本类型 Type of sample | 个数 Number | 最小值 Min.(mg·kg-1) | 最大值 Max.(mg·kg-1) | 平均值 Mean (mg·kg-1) | 标准差 Standard deviation (mg·kg-1) |
| 所有样本All samples | 169 | 0.016 | 0.610 0 | 0.215 | 0.154 |
| 建模集Modeling set | 101 | 0.016 | 0.061 0 | 0.174 | 0.151 |
| 检验集Test set | 68 | 0.016 | 0.061 0 | 0.274 | 0.147 |
下载: 导出CSV表2不同程度Hg污染水平下土壤总汞含量及芦苇叶片总汞含量和叶绿素a含量
Table2.Total Hg contents of soil and reed leaf and chlorophyll a contents in reed leaf under different levels of Hg pollution
| 汞浓度 Hg content (mg·kg-1) | 土壤总汞含量 Soil total Hg content (mg·kg-1) | 叶片总汞含量 Leaf total Hg content (mg·kg-1) | 叶片叶绿素a含量 Leaf chlorophyll a content (mg·g-1) |
| 0 | 2.380±3.203 | 0.154±0.136 | 1.444±0.419 |
| 10 | 9.707±2.599 | 0.179±0.103 | 1.439±0.467 |
| 20 | 19.125±7.777 | 0.180±0.126 | 1.417±0.404 |
| 40 | 38.496±8.864 | 0.214±0.144 | 1.415±0.438 |
| 60 | 57.293±13.655 | 0.224±0.202 | 1.374±0.387 |
| 80 | 76.949±18.336 | 0.231±0.152 | 1.319±0.602 |
| 100 | 96.997±10.388 | 0.255±0.160 | 1.313±0.463 |
| 160 | 157.556±21.678 | 0.283±0.187 | 1.292±0.421 |
下载: 导出CSV表3土壤总汞、叶片总汞及叶绿素a含量的相关性分析
Table3.Correlation analysis of soil total Hg, leaf total Hg and chlorophyll a content
| 生化指标 Biochemical index | 土壤总汞 含量Soil total Hg content | 叶片总汞 含量Leaf total Hg content | 叶片叶绿素a含量 Leaf chlorophyll a content |
| 土壤总汞含量Soil total Hg content | 1.000 | 0.968** | -0.944** |
| 叶片总汞含量Leaf total Hg content | 0.968** | 1.000 | -0.933** |
| 叶片叶绿素a含量Leaf chlorophyll a content | -0.944** | -0.933** | 1.000 |
| ??** P < 0.01 | |||
下载: 导出CSV表4芦苇叶片总汞反演模型的建模集和预测集结果
Table4.Calibration and validation results of estimation models for reed leaf total Hg content
| 模型 Model | 建模集 Calibration set | 检验集 Validation set | |||
| R2 | RMSE | R2 | RMSE | ||
| R | 0.440 | 0.123 | 0.584 | 0.138 | |
| FD | 0.585 | 0.100 | 0.566 | 0.129 | |
| CR | 0.530 | 0.105 | 0.536 | 0.141 | |
| R-CWT | 0.586 | 0.096 | 0.693 | 0.130 | |
| FD-CWT | 0.611 | 0.098 | 0.673 | 0.119 | |
| CR-CWT | 0.625 | 0.096 | 0.713 | 0.127 | |
下载: 导出CSV表5各土壤汞浓度梯度下去包络线光谱小波系数模型的反演精度
Table5.Inversion accuracies of continuum removal wavelet coefficient models under various soil Hg contents
| 汞浓度 Hg content (mg·kg-1) | R2 | RMSE |
| 0 | 0.631 | 0.091 |
| 10 | 0.560 | 0.079 |
| 20 | 0.825 | 0.051 |
| 40 | 0.668 | 0.056 |
| 60 | 0.745 | 0.090 |
| 80 | 0.616 | 0.098 |
| 100 | 0.747 | 0.078 |
| 120 | 0.506 | 0.118 |
下载: 导出CSV参考文献
| [1] | KEMPER T, SOMMER S. Maping and monitoring of residual heavy metal contamination and acidification risk after the Aznalcollar mining accident (Andalusia, Spain) using field and airborne hyperspectral data[C]//Proceedings of the 3rd EARSeL Workshop on Imaging Spectroscopy. Herrsching, 2003: 333-343 |
| [2] | REN H Y, ZHUANG D F, PAN J J, et al. Hyper-spectral remote sensing to monitor vegetation stress[J]. Journal of Soils and Sediments, 2008, 8(5):323-326 doi: 10.1007/s11368-008-0030-4 |
| [3] | SLONECKER T, HAACK B, PRICE S. Spectroscopic analysis of arsenic uptake in Pteris ferns[J]. Remote Sensing, 2009, 1(4):644-675 doi: 10.3390/rs1040644 |
| [4] | 陈圣波, 周超, 王晋年.黑龙江多金属矿区植物胁迫光谱及其与金属元素含量关系研究[J].光谱学与光谱分析, 2012, 32(5):1310-1315 doi: 10.3964/j.issn.1000-0593(2012)05-1310-06 CHEN S B, ZHOU C, WANG J N. Vegetation stress spectra and their relations with the contents of metal elements within the plant leaves in metal mines in Heilongjiang[J]. Spectroscopy and Spectral Analysis, 2012, 32(5):1310-1315 doi: 10.3964/j.issn.1000-0593(2012)05-1310-06 |
| [5] | DE OLIVEIRA M T G, ROLIM S B A, DE MELLO-FARIAS P C, et al. Industrial pollution of environmental compartments in the Sinos River Valley, RS, Brazil:Geochemical-biogeochemical characterization and remote sensing[J]. Water, Air, and Soil Pollution, 2008, 192(1/4):183-198 doi: 10.1007/s11270-008-9645-8 |
| [6] | 顾艳文, 李帅, 高伟, 等.基于光谱参数对小白菜叶片镉含量的高光谱估算[J].生态学报, 2015, 35(13):4445-4453 http://d.old.wanfangdata.com.cn/Periodical/stxb201513021 GU Y W, LI S, GAO W, et al. Hyperspectral estimation of the cadmium content in leaves of Brassica rapa chinesis based on the spectral parameters[J]. Acta Ecologica Sinica, 2015, 35(13):4445-4453 http://d.old.wanfangdata.com.cn/Periodical/stxb201513021 |
| [7] | 史钢强, 杨可明, 孙阳阳, 等.玉米叶片光谱红边位置的铜胁迫响应与污染监测[J].湖北农业科学, 2015, 54(13):3234-3239 http://d.old.wanfangdata.com.cn/Periodical/hbnykx201513043 SHI G Q, YANG K M, SUN Y Y, et al. Spectral red edge position responding and pollution monitoring of corn leaves stressed by heavy metal copper[J]. Hubei Agricultural Sciences, 2015, 54(13):3234-3239 http://d.old.wanfangdata.com.cn/Periodical/hbnykx201513043 |
| [8] | 刘美玲, 刘湘南, 李婷, 等.水稻锌污染胁迫的光谱奇异性分析[J].农业工程学报, 2010, 26(3):191-197 http://d.old.wanfangdata.com.cn/Periodical/nygcxb201003032 LIU M L, LIU X N, LI T, et al. Analysis of hyperspectral singularity of rice under Zn pollution stress[J]. Transactions of the CSAE, 2010, 26(3):191-197 http://d.old.wanfangdata.com.cn/Periodical/nygcxb201003032 |
| [9] | LIU M L, LIU X N, DING W C, et al. Monitoring stress levels on rice with heavy metal pollution from hyperspectral reflectance data using wavelet-fractal analysis[J]. International Journal of Applied Earth Observation and Geoinformation, 2011, 13(2):246-255 doi: 10.1016/j.jag.2010.12.006 |
| [10] | 邬登巍, 吴昀昭, 马宏瑞.植物污染胁迫遥感监测研究综述[J].遥感技术与应用, 2009, 24(2):238-245 http://d.old.wanfangdata.com.cn/Periodical/ygjsyyy200902019 WU D W, WU Y Z, MA H R. Review on remote sensing monitoring on contaminated plant[J]. Remote Sensing Technology and Application, 2009, 24(2):238-245 http://d.old.wanfangdata.com.cn/Periodical/ygjsyyy200902019 |
| [11] | 曹仕, 刘湘南, 刘清俊.利用独立变量分析与高光谱植被指数模型监测成熟期水稻中砷污染[J].农业环境科学学报, 2010, 29(5):881-886 http://d.old.wanfangdata.com.cn/Periodical/nyhjbh201005011 CAO S, LIU X N, LIU Q J. Monitor arsenic contamination in mature rice by the model based on the independent component analysis and hyperspectral vegetation indices[J]. Journal of Agro-Environment Science, 2010, 29(5):881-886 http://d.old.wanfangdata.com.cn/Periodical/nyhjbh201005011 |
| [12] | CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297 http://d.old.wanfangdata.com.cn/Periodical/hwyhmb200803006 |
| [13] | 李蜜, 刘湘南, 刘美玲.基于模糊神经网络的水稻农田重金属污染水平高光谱预测模型[J].环境科学学报, 2010, 30(10):2108-2115 http://d.old.wanfangdata.com.cn/Periodical/hjkxxb201010027 LI M, LIU X N, LIU M L. Fuzzy neural network model for predicting stress levels in rice fields polluted with heavy metals using hyperspectral data[J]. Acta Scientiae Circumstantiae, 2010, 30(10):2108-2115 http://d.old.wanfangdata.com.cn/Periodical/hjkxxb201010027 |
| [14] | 张龙, 潘家荣, 朱诚.基于近红外光谱的重金属汞、镉和铅污染水稻叶片鉴别[J].浙江大学学报:农业与生命科学版, 2013, 39(1):50-55 http://d.old.wanfangdata.com.cn/Periodical/zjdxxb-nyysm201301007 ZHANG L, PAN J R, ZHU C. Discrimination of mercury, cadmium and lead polluted rice leaves based on near infrared spectroscopy technology[J]. Journal of Zhejiang University:Agriculture & Life Sciences, 2013, 39(1):50-55 http://d.old.wanfangdata.com.cn/Periodical/zjdxxb-nyysm201301007 |
| [15] | 许吉仁, 董霁红, 杨源譞, 等.基于支持向量机的矿区复垦农田土壤-小麦镉含量高光谱估算[J].光子学报, 2014, 43(5):102-109 http://d.old.wanfangdata.com.cn/Periodical/gzxb201405018 XU J R, DONG Q H, YANG Y H, et al. Support vector machine model for predicting the cadmium concentration of soil-wheat system in mine reclamation farmland using hyperspectral data[J]. Acta Photonica Sinica, 2014, 43(5):102-109 http://d.old.wanfangdata.com.cn/Periodical/gzxb201405018 |
| [16] | 于雷, 洪永胜, 周勇, 等.连续小波变换高光谱数据的土壤有机质含量反演模型构建[J].光谱学与光谱分析, 2016, 36(5):1428-1433 http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201605032 YU L, HONG Y S, ZHOU Y, et al. Inversion of soil organic matter content using hyperspectral data based on continuous wavelet transformation[J]. Spectroscopy and Spectral Analysis, 2016, 36(5):1428-1433 http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201605032 |
| [17] | 李旭青, 刘湘南, 刘美玲, 等.水稻冠层氮素含量光谱反演的随机森林算法及区域应用[J].遥感学报, 2014, 18(4):923-945 http://d.old.wanfangdata.com.cn/Periodical/ygxb201404014 LI X Q, LIU X N, LIU M L, et al. Random forest algorithm and regional applications of spectral inversion model for estimating canopy nitrogen concentration in rice[J]. Journal of Remote Sensing, 2014, 18(4):923-945 http://d.old.wanfangdata.com.cn/Periodical/ygxb201404014 |
| [18] | 郑伟, 冯新斌, 李广辉, 等.硝酸水浴消解-冷原子荧光光谱法测定植物中的总汞[J].矿物岩石地球化学通报, 2006, 25(3):285-287 doi: 10.3969/j.issn.1007-2802.2006.03.012 ZHENG W, FENG X B, LI G H, et al. Determination of total mercury in plants by HNO3 digestion in the water bath coupled with cold vapor atomic fluorescence spectrometry[J]. Bulletin of Mineralogy, Petrology and Geochemistry, 2006, 25(3):285-287 doi: 10.3969/j.issn.1007-2802.2006.03.012 |
| [19] | CHENG T, RIVARD B, SáNCHEZ-AZOFEIFA G A, et al. Continuous wavelet analysis for the detection of green attack damage due to mountain pine beetle infestation[J]. Remote Sensing of Environment, 2010, 114(4):899-910 doi: 10.1016/j.rse.2009.12.005 |
| [20] | BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1):5-32 doi: 10.1023/A:1010933404324 |
| [21] | LIAW A, WIENER M. Classification and regression by random forest[J]. R News, 2002, 23(2/3):18-22 http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_d88a3126c226d093928dfa8c1306f92f |
| [22] | ZHANG J C, YUAN L, PU R L, et al. Comparison between wavelet spectral features and conventional spectral features in detecting yellow rust for winter wheat[J]. Computers and Electronics in Agriculture, 2014, 100:79-87 doi: 10.1016/j.compag.2013.11.001 |
| [23] | STOBART A K, GRIFFITHS W T, AMEEN-BUKHARI I, et al. The effect of Cd2+ on the biosynthesis of chlorophyll in leaves of barley[J]. Physiologia Plantarum, 1985, 63(3):293-298 doi: 10.1111/ppl.1985.63.issue-3 |
| [24] | 郁达, 沈宗根, 张恒泽, 等.汞对萝卜种子发芽及幼苗某些生理特性的影响[J].西北植物学报, 2004, 24(2):231-236 doi: 10.3321/j.issn:1000-4025.2004.02.008 YU D, SHEN Z G, ZHANG H Z, et al. Effects on some physiological characters of seedling and germination of radish seeds after treated with Hg2+[J]. Acta Botanica Boreali-Occidentalia Sinica, 2004, 24(2):231-236 doi: 10.3321/j.issn:1000-4025.2004.02.008 |
| [25] | GUPTA P, JAIN M, SARANGTHEM J, et al. Inhibition of 5-aminolevulinic acid dehydratase by mercury in excised greening maize leaf segments[J]. Plant Physiology and Biochemstry, 2013, 62:63-69 doi: 10.1016/j.plaphy.2012.10.008 |
| [26] | 宋开山, 张柏, 王宗明, 等.小波分析在大豆叶绿素含量高光谱反演中的应用[J].中国农学通报, 2006, 22(9):101-108 doi: 10.3969/j.issn.1000-6850.2006.09.026 SONG K S, ZHANG B, WANG Z M, et al. Application of wavelet transformation in in-situ measured hyperspectral data for soybean LAI estimation[J]. Chinese Agricultural Science Bulletin, 2006, 22(9):101-108 doi: 10.3969/j.issn.1000-6850.2006.09.026 |
| [27] | 宋开山, 张柏, 王宗明, 等.基于小波分析的大豆叶绿素a含量高光谱反演模型[J].植物生态学报, 2008, 32(1):152-160 doi: 10.3773/j.issn.1005-264x.2008.01.017 SONG K S, ZHANG B, WANG Z M, et al. Soybean chlorophyll a concentration estimation models based on wavelet-transformed, in situ collected, canopy hyperspectral data[J]. Journal of Plant Ecology, 2008, 32(1):152-160 doi: 10.3773/j.issn.1005-264x.2008.01.017 |
| [28] | 梁栋, 杨勤英, 黄文江, 等.基于小波变换与支持向量机回归的冬小麦叶面积指数估算[J].红外与激光工程, 2015, 44(1):335-340 doi: 10.3969/j.issn.1007-2276.2015.01.057 LIANG D, YANG Q Y, HUANG W J, et al. Estimation of leaf area index based on wavelet transform and support vector machine regression in winter wheat[J]. Infrared and Laser Engineering, 2015, 44(1):335-340 doi: 10.3969/j.issn.1007-2276.2015.01.057 |
| [29] | 方圣辉, 乐源, 梁琦.基于连续小波分析的混合植被叶绿素反演[J].武汉大学学报:信息科学版, 2015, 40(3):296-302 http://d.old.wanfangdata.com.cn/Periodical/whchkjdxxb201503002 FANG S H, LE Y, LIANG Q. Retrieval of chlorophyll content using continuous wavelet analysis across a range of vegetation species[J]. Geomatics and Information Science of Wuhan University, 2015, 40(3):296-302 http://d.old.wanfangdata.com.cn/Periodical/whchkjdxxb201503002 |
| [30] | CHENG T, RIVARD B, SáNCHEZ-AZOFEIFA A. Spectroscopic determination of leaf water content using continuous wavelet analysis[J]. Remote Sensing of Environment, 2011, 115(2):659-670 doi: 10.1016/j.rse.2010.11.001 |
| [31] | BLACKBURN G A. Wavelet decomposition of hyperspectral data:A novel approach to quantifying pigment concentrations in vegetation[J]. International Journal of Remote Sensing, 2007, 28(12):2831-2855 doi: 10.1080/01431160600928625 |
| [32] | BLACKBURN G A, FERWERDA J G. Retrieval of chlorophyll concentration from leaf reflectance spectra using wavelet analysis[J]. Remote Sensing of Environment, 2008, 112(4):1614-1632 doi: 10.1016/j.rse.2007.08.005 |
| [33] | 孙少波, 杜华强, 李平衡, 等.基于小波变换的毛竹叶片净光合速率高光谱遥感反演[J].应用生态学报, 2016, 27(1):49-58 http://d.old.wanfangdata.com.cn/Periodical/yystxb201601007 SUN S B, DU H Q, LI P H, et al. Retrieval of leaf net photosynthetic rate of moso bamboo forests using hyperspectral remote sensing based on wavelet transform[J]. Chinese Journal of Applied Ecology, 2016, 27(1):49-58 http://d.old.wanfangdata.com.cn/Periodical/yystxb201601007 |
| [34] | 王云飞, 庞勇, 舒清态.基于随机森林算法的橡胶林地上生物量遥感反演研究——以景洪市为例[J].西南林业大学学报, 2013, 33(6):38-45 doi: 10.3969/j.issn.2095-1914.2013.06.007 WANG Y F, PANG Y, SHU Q T. Counter-Estimation on aboveground biomass of Hevea brasiliensis plantation by remote sensing with random forest algorithm-A case study of Jinghong[J]. Journal of Southwest Forestry University, 2013, 33(6):38-45 doi: 10.3969/j.issn.2095-1914.2013.06.007 |
| [35] | 程立真, 朱西存, 高璐璐, 等.基于随机森林模型的苹果叶片磷素含量高光谱估测[J].果树学报, 2016, 33(10):1219-1229 http://cdmd.cnki.com.cn/Article/CDMD-10434-1017077332.htm CHENG L Z, ZHU X C, GAO L L, et al. Hyperspectral estimation of phosphorus content for apple leaves based on the random forest model[J]. Journal of Fruit Science, 2016, 33(10):1219-1229 http://cdmd.cnki.com.cn/Article/CDMD-10434-1017077332.htm |
| [36] | 高振东.基于水稻叶绿素含量变化的重金属污染胁迫遥感分析与评价[D].长春: 东北师范大学, 2015 http://cdmd.cnki.com.cn/Article/CDMD-10200-1015418062.htm GAO Z D. Analysis and evaluation of heavy-metal pollution stress based on chlorophyll content of rice using hyperspectral data[D]. Changchun: Northeast Normal University, 2015 http://cdmd.cnki.com.cn/Article/CDMD-10200-1015418062.htm |
