Please wait a minute...
 
Remote Sensing for Land & Resources    2019, Vol. 31 Issue (4) : 96-103     DOI: 10.6046/gtzyyg.2019.04.13
|
Research on indirect hyperspectral estimating model of heavy metal Cd based on partial least squares regression
Junliang HE1, Chaoshan HAN1, Rui WEI1, Zhiyong ZHOU2, Qiliang DONG2
1. College of Resources and Environment Sciences, Shijiazhuang University, Shijiazhuang 050035, China
2. Hebei Investigation Institute of Hydrogeology and Engineering Geology, Shijiazhuang 050021, China
Download: PDF(3006 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

In order to explore the feasibility of estimating the heavy metal cadmium (Cd) content in soil by hyperspectral data, the authors chose the cinnamon soil of Shijiazhuang water conservation area as the research object. Based on the multiple spectral transformation indexes corresponding to the sensitive bands of soil organic matter, the authors established the hyperspectral indirect inversion model of soil heavy metal Cd by partial least squares regression method. Some conclusions have been reached: the average Cd content of soil samples in the study area is 0.220 mg/kg, which is at the serious pollution level. There exists a significant correlation between organic matter content and Cd content, and there is a certain adsorption relationship. The sensitive band corresponding to the original spectral reflectance of organic matter is 797 nm. The correlation coefficient between the absorbance transform first derivative (ATFD) and the organic matter content is the largest among the various spectral transformations. The first derivative (FD) has the largest positive correlation with the organic matter. The modeling and verification sample analysis show that the multivariate partial least squares model is better than the univariate partial least squares model and multivariate linear stepwise regression model. The model explanatory variables are the absorbance transform second derivative (ATSD) of 1 409 nm and the FD of 1 396 nm, and the modeling and verification samples R 2 were 0.83 and 0.80. The research shows that it is feasible to estimate heavy metal Cd content indirectly by establishing multiple spectral transformation indexes estimation model based on spectral diagnostic features of organic matter. The optimal model can provide a reference for the rapid monitoring of heavy metal Cd in this area.

Keywords Cd      soil organic matter      hyperspectral      indirect estimating model      partial least squares regression     
:  TP79  
  S159  
Issue Date: 03 December 2019
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Junliang HE
Chaoshan HAN
Rui WEI
Zhiyong ZHOU
Qiliang DONG
Cite this article:   
Junliang HE,Chaoshan HAN,Rui WEI, et al. Research on indirect hyperspectral estimating model of heavy metal Cd based on partial least squares regression[J]. Remote Sensing for Land & Resources, 2019, 31(4): 96-103.
URL:  
https://www.gtzyyg.com/EN/10.6046/gtzyyg.2019.04.13     OR     https://www.gtzyyg.com/EN/Y2019/V31/I4/96
Fig.1  Sampling point distribution in the study area
统计量 总体样本 建模样本 验证样本
样本数/个 69 46 23
最大值/(mg·kg-1) 0.359 0.343 0.359
最小值/(mg·kg-1) 0.138 0.138 0.156
平均值/(mg·kg-1) 0.220 0.215 0.229
标准差/(mg·kg-1) 0.048 0.043 0.055
变异系数/% 21.73 19.83 24.14
Tab.1  Statistical characteristics of heavy metal Cd in soil
P [1,2) [2,3) [3,4) ≥4
样本个数 5 45 15 4
Tab.2  Statistical analysis of pollution index of heavy metal Cd in soil
光谱变量 敏感波段/nm 相关系数
R 797 -0.468**②
RT 797 0.437**
AT 797 0.448**
FD 1 396 0.721**
SD 1 408 -0.601**
RTFD 837 -0.670**
RTSD 2 204 -0.394**
ATFD 1 394 -0.766**
ATSD 1 409 0.676**
CR 1 909 0.666**
Tab.3  Maximum correlation coefficients of soil organic matter content and spectral variables
Fig.2  Scatter plots of the two sets of samples of fitting and testing for MLSR
参数 建模样本 验证样本
R2 0.81 0.75
RMSE 0.02 0.03
RPD 2.31 1.23
Tab.4  Results of MLSR model
Fig.3  Scatter plots of the two sets of samples of fitting and testing for ATSD-U-PLSR
参数 建模样本 验证样本
R2 0.78 0.80
RMSE 0.003 0.006
RPD 14.40 9.10
Tab.5  Results of ATSD-U-PLSR model
Fig.4  Scatter plots of the two sets of samples of fitting and testing for FD-U-PLSR
参数 建模样本 验证样本
R2 0.24 0.41
RMSE 0.005 0.010
RPD 7.79 5.76
Tab.6  Results of FD-U-PLSR model
Fig.5  Scatter plots of the two sets of samples of fitting and testing for M-PLSR
参数 建模样本 验证样本
R2 0.83 0.80
RMSE 0.02 0.006
RPD 2.46 9.32
Tab.7  Results of M-PLSR model
[1] 周际海, 黄荣霞, 樊后保 , 等. 污染土壤修复技术研究进展[J]. 水土保持研究, 2016,23(3):366-372.
[1] Zhou J H, Huang R X, Fan H B , et al. A review on the progresses of remediation technologies for contaminated soils[J]. Research of Soil and Water Conservation, 2016,23(3):366-372.
[2] 史舟, 王乾龙, 彭杰 , 等. 中国主要土壤高光谱反射特性分类与有机质光谱预测模型[J]. 中国科学(地球科学), 2014,44(5):978-988.
[2] Shi Z, Wang Q L, Peng J , et al. Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations[J]. Science China(Earth Sciences), 2014,44(5):978-988.
[3] 刘硕, 吴泉源, 曹学江 , 等. 龙口煤矿区土壤重金属污染评价与空间分布特征[J]. 环境科学, 2016,37(1):270-279.
[3] Liu S, Wu Q Y, Cao X J , et al. Pollution assessment and spatial distribution characteristics of heavy metals in soils of coal mining area in Longkou City[J]. Environmental Science, 2016,37(1):270-279.
[4] 王燕, 李贤庆, 宋志宏 , 等. 土壤重金属污染及生物修复研究进展[J]. 安全与环境学报, 2009,9(3):60-65.
[4] Wang Y, Li X Q, Song Z H , et al. Review on the research advances of the pollution and bioremediation of heavy metals in the soil[J]. Journal of Safety and Environment, 2009,9(3):60-65.
[5] 马文超, 刘媛, 孙晓灿 , 等. 镉在土壤-香根草系统中的迁移及转化特征[J]. 生态学报, 2016,36(11):3411-3418.
doi: 10.5846/stxb201506261297
[5] Ma W C, Liu Y, Sun X C , et al. Transfer and transformation characteristics of cadmium from soil to Vetiveria zizanioides[J]. Acta Ecologica Sinica, 2016,36(11):3411-3418.
[6] 阿尔达克·克里木, 张东 , 等. 基于高光谱的ASTER影像土壤盐分模型校正及验证[J]. 农业工程学报, 2016,32(12):144-150.
[6] Kelimu A, Zhang D , et al. Calibration and validation of soil salinity estimation model based on measured hyperspectral and ASTER image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016,32(12):144-150.
[7] 刘焕军, 张柏, 刘殿伟 , 等. 松嫩平原典型土壤高光谱定量遥感研究[J]. 遥感学报, 2008,12(4):647-654.
[7] Liu H J, Zhang B, Liu D W , et al. Study on quantitatively remote sensing typical soils in Songnen Plain,Northeast China[J]. Journal of Remote Sensing, 2008,12(4):647-654.
[8] Kemper T, Sommer S . Estimate of heavy metal contamination in soil after a mining accident using reflectance spectroscopy[J]. Environmental Science and Technology, 2002,36(12):2742-2747.
[9] 郭云开, 曹小燕, 石自桂 . 水稻冠层光谱变化特征的土壤重金属全量反演研究[J]. 遥感信息, 2015,30(3):116-123.
[9] Guo Y K, Cao X Y, Shi Z G . Inversion model of total amount of soil heavy metal based on spectral characteristics of rice canopy[J]. Remote Sensing Information, 2015,30(3):116-123.
[10] 程先锋, 宋婷婷, 陈玉 , 等. 滇西兰坪铅锌矿区土壤重金属含量的高光谱反演分析[J]. 岩石矿物学杂志, 2017,36(1):60-69.
[10] Cheng X F, Song T T, Chen Y , et al. Retrieval and analysis of heavy metal content in soil based on measured spectra in the Lanping Zn-Pb mining area,western Yunnan Province[J]. Acta Petrologica et Mineralogica, 2017,36(1):60-69.
[11] 吴昀昭 . 南京城郊农业土壤重金属污染的遥感地球化学基础研究[D]. 南京:南京大学, 2005.
[11] Wu Y Z . Heavy Metal Pollution in Suburban Soils of the Nanjing Area:A Feasibility Study of Remote-Sensing Geochemistry[D]. Nanjing:Nanjing University, 2005.
[12] Moros J, Vallejuelo F O D, Gredilla A ,et al.Use of reflectance infrared spectroscopy for monitoring the metal content of the estuarine sediments of the Nerbioi-Ibaizabal River (Metropolitan Bilbao,Bay of Biscay,Basque Country)[J]. Environmental Science and Technology, 2009,43(24):9314-9320.
[13] 贺军亮, 蒋建军, 孙中伟 , 等. 土壤重金属含量光谱估算模型的初步研究[J]. 农机化研究, 2009,31(9):22-25.
[13] He J L, Jiang J J, Sun Z W , et al. Studying on retrieval of soil heavy metal content using the organic matter identification index[J]. Journal of Agricultural Mechanization Research, 2009,31(9):22-25.
[14] 兰泽英, 刘洋 . 乐安河流域土壤重金属含量高光谱间接反演模型及其空间分布特征研究[J]. 地理与地理信息科学, 2015,31(3):26-31.
[14] Lan Z Y, Liu Y . Research on indirect hyperspectral estimating model and the spatial distribution characteristics of heavy metal contents in basin soil of Lean River[J]. Geography and Geo-Information Science, 2015,31(3):26-31.
[15] 王菲, 曹文涛, 康日斐 , 等. 基于野外实测光谱的金矿区土壤重金属铬监测研究[J]. 环境污染与防治, 2016,38(2):13-18.
[15] Wang F, Cao W T, Kang R F , et al. Study on monitoring of soil heavy metal Cr in golden mining areas based on field measured spectrum[J]. Environmental Pollution and Control, 2016,38(2):13-18.
[16] 江振蓝, 杨玉盛, 沙晋明 . GWR模型在土壤重金属高光谱预测中的应用[J]. 地理学报, 2017,72(3):533-544.
doi: 10.11821/dlxb201703013
[16] Jiang Z L, Yang Y S, Sha J M . Application of GWR model in hyperspectral prediction of soil heavy metals[J]. Acta Geographica Sinica, 2017,72(3):533-544.
[17] 乔星星, 冯美臣, 杨武德 , 等. 变换光谱数据对土壤氮素PLSR模型的影响研究[J]. 地球信息科学学报, 2016,18(8):1123-1132.
doi: 10.3724/SP.J.1047.2016.01123
[17] Qiao X X, Feng M C, Yang W D , et al. Effect of spectral transformation processes on the PLSR models of soil nitrogen[J]. Journal of Geo-Information Science, 2016,18(8):1123-1132.
[18] 于雷, 洪永胜, 耿雷 , 等. 基于偏最小二乘回归的土壤有机质含量高光谱估算[J]. 农业工程学报, 2015,31(14):103-109.
[18] Yu L, Hong Y S, Geng L , et al. Hyperspectral estimation of soil organic matter content based on partial least squares regression[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(14):103-109.
[19] 刘伟, 赵众, 袁洪福 , 等. 光谱多元分析校正集和验证集样本分布优选方法研究[J]. 光谱学与光谱分析, 2014,34(4):947-951.
url: http://www.opticsjournal.net/Articles/Abstract?aid=OJ140409000473kQmTpW
[19] Liu W, Zhao Z, Yuan H F , et al. An optimal selection method of samples of calibration set and validation set for spectral multivariate analysis[J]. Spectroscopy and Spectral Analysis, 2014,34(4):947-951.
[20] 洪永胜, 于雷, 耿雷 , 等. 应用DS算法消除室内几何测试条件对土壤高光谱数据波动性的影响[J]. 华中师范大学学报(自然科学版), 2016,50(2):303-308.
[20] Hong Y S, Yu L, Geng L , et al. Using direct standardization algorithm to eliminate the effect of laboratory geometric parameters on soil hyperspectral data fluctuate characteristic[J]. Journal of Central China Normal University (Natural Sciences), 2016,50(2):303-308.
[21] 宋静宜, 傅开道, 苏斌 , 等. 澜沧江水系底沙重金属含量空间分布及其污染评价[J]. 地理学报, 2013,68(3):389-397.
doi: 10.11821/xb201303010
[21] Song J Y, Fu K D, Su B , et al. Spatial distribution of heavy metal concentrations and pollution assessment in the bed loads of the Lancang River System[J]. Acta Geographica Sinica, 2013,68(3):389-397.
[22] 姚娜, 彭昆国, 刘足根 , 等. 石家庄北郊土壤重金属分布特征及风险评价[J]. 农业环境科学学报, 2014,33(2):313-321.
[22] Yao N, Peng K G, Liu Z G , et al. Distribution and risk assessment of soil heavy metals in the north suburb of Shijiazhuang City[J]. Journal of Agro-Environment Science, 2014,33(2):313-321.
[23] 张娟娟, 田永超, 朱艳 , 等. 不同类型土壤的光谱特征及其有机质含量预测[J]. 中国农业科学, 2009,42(9):3154-3163.
doi:
[23] Zhang J J, Tian Y C, Zhu Y , et al. Spectral characteristics and estimation of organic matter contents of different soil types[J]. Scientia Agricultura Sinica, 2009,42(9):3154-3163.
[1] WANG Qian, REN Guangli. Application of hyperspectral remote sensing data-based anomaly extraction in copper-gold prospecting in the Solake area in the Altyn metallogenic belt, Xinjiang[J]. Remote Sensing for Natural Resources, 2022, 34(1): 277-285.
[2] QU Haicheng, WAND Yaxuan, SHEN Lei. Hyperspectral super-resolution combining multi-receptive field features with spectral-spatial attention[J]. Remote Sensing for Natural Resources, 2022, 34(1): 43-52.
[3] CHEN Jie, ZHANG Lifu, ZHANG Linshan, ZHANG Hongming, TONG Qingxi. Research progress on online monitoring technologies of water quality parameters based on ultraviolet-visible spectra[J]. Remote Sensing for Natural Resources, 2021, 33(4): 1-9.
[4] GAO Wenlong, ZHANG Shengwei, LIN Xi, LUO Meng, REN Zhaoyi. The remote sensing-based estimation and spatial-temporal dynamic analysis of SOM in coal mining[J]. Remote Sensing for Natural Resources, 2021, 33(4): 235-242.
[5] JIANG Yanan, ZHANG Xin, ZHANG Chunlei, ZHONG Chengcheng, ZHAO Junfang. Classification of remote sensing images based on multi-scale feature fusion using local binary patterns[J]. Remote Sensing for Natural Resources, 2021, 33(3): 36-44.
[6] ZANG Chuankai, SHEN Fang, YANG Zhengdong. Aquatic environmental monitoring of inland waters based on UAV hyperspectral remote sensing[J]. Remote Sensing for Natural Resources, 2021, 33(3): 45-53.
[7] WANG Hua, LI Weiwei, LI Zhigang, CHEN Xueye, SUN Le. Hyperspectral image classification based on multiscale superpixels[J]. Remote Sensing for Natural Resources, 2021, 33(3): 63-71.
[8] LIU Yongmei, FAN Hongjian, GE Xinghua, LIU Jianhong, WANG Lei. Estimation accuracy of fractional vegetation cover based on normalized difference vegetation index and UAV hyperspectral images[J]. Remote Sensing for Natural Resources, 2021, 33(3): 11-17.
[9] SHU Huiqin, FANG Junyong, LU Peng, GU Wanfa, WANG Xiao, ZHANG Xiaohong, LIU Xue, DING Lanpo. Research on fine recognition of site spatial archaeology based on multisource high-resolution data[J]. Remote Sensing for Land & Resources, 2021, 33(2): 162-171.
[10] XIAO Yan, XIN Hongbo, WANG Bin, CUI Li, JIANG Qigang. Hyperspectral estimation of black soil organic matter content based on wavelet transform and successive projections algorithm[J]. Remote Sensing for Land & Resources, 2021, 33(2): 33-39.
[11] HU Xinyu, XU Zhanghua, CHEN Wenhui, CHEN Qiuxia, WANG Lin, LIU Hui, LIU Zhicai. Construction and application effect of normalized shadow vegetation index NSVI based on PROBA/CHRIS image[J]. Remote Sensing for Land & Resources, 2021, 33(2): 55-65.
[12] HAN Yanling, CUI Pengxia, YANG Shuhu, LIU Yekun, WANG Jing, ZHANG Yun. Classification of hyperspectral image based on feature fusion of residual network[J]. Remote Sensing for Land & Resources, 2021, 33(2): 11-19.
[13] WU Qian, JIANG Qigang, SHI Pengfei, ZHANG Lili. The estimation of soil calcium carbonate content based on Hyperspectral data[J]. Remote Sensing for Land & Resources, 2021, 33(1): 138-144.
[14] SUN Ke. Remote sensing image classification based on super pixel and peak density[J]. Remote Sensing for Land & Resources, 2020, 32(4): 41-45.
[15] WANG Ruijun, ZHANG Chunlei, SUN Yongbin, WANG Shen, DONG Shuangfa, WANG Yongjun, YAN Bokun. Application of hyperspectral spectroscopy to constructing polymetallic prospecting model in Hongshan, Gansu Province[J]. Remote Sensing for Land & Resources, 2020, 32(3): 222-231.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech