Please wait a minute...
img

官方微信

遥感技术与应用  2019, Vol. 34 Issue (5): 998-1004    DOI: 10.11873/j.issn.1004-0323.2019.5.0998
模型与反演     
基于偏最小二乘的土壤重金属铜含量高光谱估算
贺军亮1,2(),崔军丽3,张淑媛1,李仁杰2,查勇4
1. 石家庄学院资源与环境科学学院, 河北 石家庄 050035
2. 河北师范大学 资源与环境科学学院/河北省环境演变与生态建设实验室, 河北 石家庄 050024
3. 河南大学 黄河文明与可持续发展研究中心, 河南 开封 475001
4. 南京师范大学 虚拟地理环境教育部重点实验室, 江苏 南京 210046
Hyperspectral Estimation of Heavy Metal Cu Content in Soil based on Partial Least Square Method
Junliang He1,2(),Junli Cui3,Shuyuan Zhang1,Renjie Li2,Yong Zha4
1. College of Resources and Environment Sciences, Shijiazhuang University, Shijiazhuang 050035, China
2. College of Resources and Environment Sciences/Hebei Key Laboratory of Environmental Change and Ecological Construction, Hebei Normal University, Shijiazhuang 050024, China
3. Key Research Institute of Yellow River Civilization and Sustainable Development, Henan University, Kaifeng 475001, China
4. Key Laboratory of Ministry of Education for Virtual Geographic Environment, Nanjing Normal University, Nanjing 210046, China
 全文: PDF(833 KB)   HTML
摘要:

为探究高光谱数据估算土壤重金属铜含量的可行性,以石家庄市水源保护区褐土为研究对象,对不同光谱变换数据与重金属铜含量做了相关分析,建立了土壤重金属铜的单光谱变换指标偏最小二乘模型和多光谱变换指标偏最小二乘模型。结果表明:光谱反射率(R)经倒数一阶微分(RTFD)变换后与铜含量的相关性有所提高;光谱敏感波段为418、427、435、446、490、673、1 909、1 920和2 221 nm,基本位于土壤氧化铁、粘土矿物的特征吸收区域;对土壤重金属铜含量估算效果最好的单光谱变换指标偏最小二乘模型为RTFD模型,其模型决定系数(R2)为0.649,均方根误差(RMSE)为1.477;多光谱变换指标偏最小二乘模型R2和RMSE分别为0.751和1.162,建模效果优于单光谱变换指标模型。研究结果可为北方地区褐土类型土壤重金属铜的高光谱估算提供借鉴。

关键词: 高光谱重金属铜倒数一阶微分多变换偏最小二乘模型    
Abstract:

In order to explore the feasibility of estimating the heavy metal Cu content in soil by hyperspectral data, based on the study of the cinnamon soil of the water source protected area in Shijiazhuang, the correlation analysis between the different spectral data and the heavy metal copper content was made. The univariate partial least squares model of soil heavy metal Cu and a partial least squares model of multivariate were established. The results showed that the correlation between the spectral reflectance and the Cu content was improved by the Reciprocal Transformation First Derivative (RTFD). The spectral sensitivity bands were 418, 427, 435, 446, 490, 673, 1 909, 1 920, 2 221 nm, which was located in the characteristic absorption region of soil iron oxide and clay minerals. The univariate partial least squares model with the best estimation effect on soil heavy metal Cu content was RTFD model, and its model determination coefficient R2 was 0.649, Root Mean Square Error (RMSE) was 1.477. The multivariate partial least squares model R2 and RMSE were 0.751 and 1.162, and the modeling effect was better than the univariate model. The research results can provide a reference for the hyperspectral estimation of heavy metal Cu in cinnamon soil in northern China.

Key words: Hyperspectral    Heavy metal copper    Reciprocal Transformation First Derivative (RTFD)    Multivariate Partial Least Squares model
收稿日期: 2018-07-24 出版日期: 2019-12-05
ZTFLH:  TP79  
基金资助: 国家自然科学基金青年科学基金项目(41201215);河北省自然科学基金项目(D2016106013)
作者简介: 贺军亮(1979-),男,河北新乐人,副教授,主要从事生态环境遥感研究。E-mail:hejunliang0927@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
贺军亮
崔军丽
张淑媛
李仁杰
查勇

引用本文:

贺军亮,崔军丽,张淑媛,李仁杰,查勇. 基于偏最小二乘的土壤重金属铜含量高光谱估算[J]. 遥感技术与应用, 2019, 34(5): 998-1004.

Junliang He,Junli Cui,Shuyuan Zhang,Renjie Li,Yong Zha. Hyperspectral Estimation of Heavy Metal Cu Content in Soil based on Partial Least Square Method. Remote Sensing Technology and Application, 2019, 34(5): 998-1004.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2019.5.0998        http://www.rsta.ac.cn/CN/Y2019/V34/I5/998

图1  研究区位置及采样点分布图
元素最大值最小值平均值标准差河北省背景值
Cu30.12120.68924.7572.40921.8
表1  土壤重金属铜含量的统计特征值(单位:mg/kg)
项目最大值最小值平均值0.7<P ≤1P >1
Cu1.3820.9491.136样点个数占比样点个数占比
812.7%5587.3%
表2  土壤重金属铜的污染指数统计分析
图2  研究区土壤样品的光谱曲线图
光谱变换指标最大相关波段/nm相关系数
R418-0.608**
FD446-0.563**
SD2 221-0.419**
RT4270.551**
AT4270.589**
RTFD490-0.648**
RTSD1 909-0.506**
ATFD673-0.559**
ATSD1 920-0.471**
CR435-0.457**
表3  土壤重金属铜含量与光谱指标的最大相关系数
光谱变换指标建模集验证集
R2RMSER2RMSE
R0.4851.7900.4421.908
FD0.3112.0700.2612.196
RT0.4361.8720.3941.989
AT0.4761.8050.4371.917
RTFD0.6491.4770.5691.677
ATFD0.2992.0890.2652.190
表4  单光谱变换指标偏最小二乘(U-PLS)模型结果
图3  RTFD-U-PLS模型验证集实测值与预测值的散点图
重金属建模集验证集
CuR2RMSER2RMSE
0.7511.1620.6861.247
表5  多光谱变换指标偏最小二乘(M-PLS)模型结果
图4  M-PLS模型验证集实测值与预测值的散点图
1 Guo Yunkai, Liu Ning, Liu Lei, et al. Hyper-spectral Inversion of Soil Cu Content based on BP Network Model[J]. Science of Surveying and Mapping, 2018,43(1): 135-139.郭云开, 刘宁, 刘磊,等. 土壤Cu含量高光谱反演的BP神经网络模型[J]. 测绘科学, 2018,43(1):135-139.
2 Liu Hua, Zhang Liquan. A Predictive Model for The Hyperspectral Character of Saltmarsh Soil to Its Heavy Metal Content at Chongming Dongtan[J]. Acta Ecologica Sinica, 2007, 27(8): 3427-3434.刘华, 张利权. 崇明东滩盐沼土壤重金属含量的高光谱估算模型[J]. 生态学报, 2007, 27(8):3427-3434.
3 Wu Dengwei, Wu Yunzhao, Ma Hongrui. Study on the Prediction of Soil Heavy Metal Elements Content based on Mid-Infrared Diffuse Reflectance Spectra[J]. Spectroscopy and Spectral Analysis, 2010, 30(6): 1498-1502.邬登巍, 吴昀昭, 马宏瑞. 基于中红外漫反射光谱的土壤重金属元素含量预测研究[J]. 光谱学与光谱分析, 2010, 30(6):1498-1502.
4 He Junliang, Jiang Jianjun, Sun Zhongwei, 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.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.
5 Gong Shaoqi, Wang Xin, Shen Runping, et al. Study on Heavy Metal Element Content in the Coastal Saline Soil by Hyperspectral Remote Sensing[J]. Remote Sensing Technology and Application, 2010, 25(2): 169-177.龚绍琦, 王鑫, 沈润平,等. 滨海盐土重金属含量高光谱遥感研究[J]. 遥感技术与应用, 2010, 25(2):169-177.
6 Wang Wei, Shen Runping, Ji Caoxiang. Study on Heavy Metal Cu based on Hyperspectral Remote Sensing [J]. Remote Sensing Technology and Application, 2011, 26(3): 348-354.王维, 沈润平, 吉曹翔. 基于高光谱的土壤重金属铜的反演研究[J]. 遥感技术与应用, 2011, 26(3):348-354.
7 Yuan Zhongqiang, Cao Chunxiang, Bao Daming, et al. Inversion on Contents of Heavy Metals in Soils of Wetlands in Zoigê Plateau based on Remote Sensing Data[J]. Wetland Science, 2016, 14(1): 113-116.袁中强, 曹春香, 鲍达明,等. 若尔盖湿地土壤重金属元素含量的遥感反演[J]. 湿地科学, 2016, 14(1):113-116.
8 Tu Yulong, Zou Bin, Jiang Xiaolu, et al. Hyperspectral Remote Sensing based Modeling of Cu Content in Mining Soil[J]. Spectroscopy and Spectral Analysis, 2018,38(2):575-581.涂宇龙, 邹滨, 姜晓璐,等. 矿区土壤Cu含量高光谱反演建模[J]. 光谱学与光谱分析, 2018,38(2):575-581.
9 Liu Zheng, Dang Hongyuan, Zhao Xuyang, et al. Study on the Evolution of Soil Erosion based on Landscape Pattern—Taking the Surface Water Source Protection Area in Shijiazhuang City as an Example[J]. Jiangsu Agricultural Science, 2013, 41(4): 299-303.刘征, 党宏媛, 赵旭阳,等. 基于景观格局的土壤侵蚀演变研究—以石家庄市地表水源保护区为例[J]. 江苏农业科学, 2013, 41(4):299-303.
10 Deng Nianwu, Xu Hui. Model of Simple Partial Least Squares Regression and Its Application [J]. Engineering Joumal of Wuhan University, 2001, 34(2): 14-16.邓念武, 徐晖. 单因变量的偏最小二乘回归模型及其应用[J]. 武汉大学学报(工学版), 2001, 34(2):14-16.
11 Zhao Qing, Liu Zheng, Zhao Xuyang. Study on Correlativity of Land Utilization Change and Water Quality in the Surface Headwaters Protection Area of Shijiazhuang[J]. Research of Soil and Water Conservation, 2013, 20(2): 121-126.赵晴, 刘征, 赵旭阳. 石家庄地表水源保护区土地利用变化与水质相关性研究[J]. 水土保持研究, 2013, 20(2):121-126.
12 Yao Na, Peng Kunguo, Liu Zugen, 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.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.
13 Fang Xiaobo, Shi Jian, Liao Xinfeng, et al. Heavy Metal Pollution Characteristics and Ecological Risk Analysis for Soil in Phyllostachys Praecox Stands of Lin'an[J]. Chinese Journal of Applied Ecology, 2015, 26(6): 1883-1891.方晓波, 史坚, 廖欣峰,等. 临安市雷竹林土壤重金属污染特征及生态风险评价[J]. 应用生态学报, 2015, 26(6):1883-1891.
14 Zhang Qiuxia, Zhang Hebing, Zhang Huijuan, et al. Hybrid Inversion Model of Heavy Metals with Hyperspectral Reflectance in Cultivated Soils of Main Grain Producing Areas[J]. Transactions of the Chinese Society of Agricultural Machinery, 2017, 48(3):148-155.张秋霞, 张合兵, 张会娟,等. 粮食主产区耕地土壤重金属高光谱综合反演模型[J]. 农业机械学报, 2017, 48(3):148-155.
15 Zhang Wei, Gao Xiaohong, Yang Yang, et al. Estimating Heavy Metal Contents for Topsoil based on Spectral Analysis: A Case Study of Yushu and Maduo Counties in the Three-River Source Region [J]. Soils, 2014, 46(6): 1052-1060.张威, 高小红, 杨扬,等. 基于光谱分析的土壤重金属含量估算研究——以三江源区玉树县和玛多县为例[J]. 土壤, 2014,46(6):1052-1060.
16 Cheng Xianfeng, Song Tingting, Chen Yu, 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.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.
17 Song Tingting, Fu Xiuli, Chen Yu, et al. Remote Sensing Inversion of Soil Zinc Pollution in Gejiu Mining Area of Yunnan, Yunnan Province[J]. Remote Sensing Technology and Application, 2018,33(1):88-95.宋婷婷, 付秀丽, 陈玉,等. 云南个旧矿区土壤锌污染遥感反演研究[J]. 遥感技术与应用, 2018,33(1):88-95.
18 Liu H J, Zhang Y Z, Zhang B. Novel Hyperspectral Reflectance Model for Estimating Black-soil Organic Matter in Northeast China[J]. Environmental Monitoring & Assessment, 2009, 154(1-4):147-154.
19 Hou Yanjun, Tiyip Tashpolat, Sawut Mamat, et al. Estimation Model of Desert Soil Organic Matter Content Using Hyperspectral Data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(16): 113-120.侯艳军, 塔西甫拉提·特依拜, 买买提·沙吾提,等. 荒漠土壤有机质含量高光谱估算模型[J]. 农业工程学报, 2014, 30(16):113-120.
20 Jiang Zhenlan, Yang Yusheng, Sha Jinming. Application of GWR Model in Hyperspectral Prediction of Soil Heavy Metals[J]. Acta Geographica Sinica, 2017, 72(3): 533-544.
20 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.
21 Xu Mingxing, Wu Shaohua, Zhou Shenglu, et al. Hyperspectral Reflectance Models for Retrieving Heavy Metal Content: Application in the Archaeological Soil[J]. Journal of Infrared Millimeter Waves, 2011, 30(2): 109-114.徐明星, 吴绍华, 周生路,等. 重金属含量的高光谱建模反演:考古土壤中的应用[J]. 红外与毫米波学报, 2011, 30(2):109-114.
22 Huang Changping, Liu Bo, Zhang Xia, et al. Study on Band Selection and Optimal Spectral Resolution for Prediction of Cu Contamination in Soils [J]. Remote Sensing Technology and Application, 2010, 25(3):353-357.黄长平, 刘波, 张霞,等. 土壤重金属Cu含量遥感反演的波段选择与最佳光谱分辨率研究[J]. 遥感技术与应用, 2010, 25(3):353-357.
23 Yu Lei, Hong Yongsheng, Geng Lei, 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.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.
[1] 许宁,胡玉新,耿修瑞. 凸体几何光谱解混研究进展及若干问题浅析[J]. 遥感技术与应用, 2019, 34(5): 1028-1039.
[2] 程雪,贺炳彦,黄耀欢,孙志刚,李鼎,朱婉雪. 基于无人机高光谱数据的玉米叶面积指数估算[J]. 遥感技术与应用, 2019, 34(4): 775-784.
[3] 周龙飞,张云鹤,成枢,顾晓鹤,杨贵军,孙乾,束美艳. 不同生育期倒伏胁迫下玉米叶面积指数高光谱响应解析[J]. 遥感技术与应用, 2019, 34(4): 766-774.
[4] 张晓光,姜子璇,孔繁昌. 滨海盐渍土可见近红外高光谱特征[J]. 遥感技术与应用, 2019, 34(4): 816-821.
[5] 王思恒, 黄长平, 张立福, 高显连, 付安民. 陆地生态系统碳监测卫星远红波段叶绿素荧光反演算法设计[J]. 遥感技术与应用, 2019, 34(3): 476-487.
[6] 李琼琼, 柳云龙. 城市居民区土壤重金属含量高光谱反演研究[J]. 遥感技术与应用, 2019, 34(3): 540-546.
[7] 林沂, 张萌丹, 张立福, 江淼. 高光谱激光雷达谱位合一的角度效应分析[J]. 遥感技术与应用, 2019, 34(2): 225-231.
[8] 丁海宁. 黄土高原土壤铁元素含量遥感反演方法 [J]. 遥感技术与应用, 2019, 34(2): 275-283.
[9] 牟多铎, 刘磊. ELM与SVM在高光谱遥感图像监督分类中的比较研究[J]. 遥感技术与应用, 2019, 34(1): 115-124.
[10] 皋厦, 申鑫, 代劲松, 曹林. 结合LiDAR单木分割和高光谱特征提取的城市森林树种分类[J]. 遥感技术与应用, 2018, 33(6): 1073-1083.
[11] 陈伟民,张凌,宋冬梅,王斌,丁亚雄,许明明,崔建勇. 基于AdaBoost改进随机森林的高光谱图像地物分类方法研究[J]. 遥感技术与应用, 2018, 33(4): 612-620.
[12] 苏阳,祁元,王建华,徐菲楠,张金龙. 基于航空高光谱影像的额济纳绿洲土地覆被提取[J]. 遥感技术与应用, 2018, 33(2): 202-211.
[13] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[14] 郭宇柏,卓莉,陶海燕,曹晶晶,王芳. 基于空谱初始化的非负矩阵光谱混合像元盲分解[J]. 遥感技术与应用, 2018, 33(2): 216-226.
[15] 刘爱林,郭宝平,李岩山 . 基于离散粒子群算法的凸多模态高光谱图像端元提取研究[J]. 遥感技术与应用, 2018, 33(2): 227-232.