郭云开;刘宁;刘磊;李丹娜;朱善宽;

• 1:长沙理工大学交通运输工程学院
• 2:长沙理工大学测绘遥感应用技术研究所

摘要(Abstract)：

以高光谱数据为基础,针对传统土壤重金属反演模型拟合度低、预测效果差的缺点,提取光谱预处理后的特征波段数据进行相关性分析,选取860nm一阶微分光谱反射率建立基于Matlab的重金属Cu含量BP神经网络预测模型,模型的拟合优度为0.721,预测精度达82.3%,高于传统单元线性回归模型0.414的拟合优度与76.1%的预测精度。研究表明,BP神经网络模型具有良好的拟合优度与预测能力,能更有效预测土壤中重金属Cu的含量。

关键词(KeyWords)： 高光谱;土壤重金属;BP神经网络;单元线性回归;拟合优度

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金面上项目(41471421,41671498)

作者(Authors): 郭云开;刘宁;刘磊;李丹娜;朱善宽;

DOI: 10.16251/j.cnki.1009-2307.2018.01.023

参考文献(References)：

• [1]郭云开,谢琼,安冠星,等.土壤重金属污染灰色综合评价模型[J].测绘科学,2017,42(5):175-182.(GUO Yunkai,XIE Qiong,AN Guanxing,et al.Gray comprehensive evaluation model of heavy metal pollution in the soil[J].Science of Surveying and Mapping,2017,42(5):175-182.)
• [2]曹志平.土壤生态学[M].北京:化学工业出版社,2007.(CAO Zhiping.Soil ecology[M].Beijing:Chemical Industry Press,2007.)
• [3]BOCCA B,ALIMONTI A,PETRUCCI F,et al.Quantification of traceelements by sector field inductively coupled plasma spectrometryin urine,serum,blood and cerebrospinal fluid of patients withParkinson’s disease[J].Spectrochimica Acta Part B,2004,59(4):559-557.
• [4]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.(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.)
• [5]KOOISTRA L,WEHRENS R,LEUVEN R,et al.Possibilities of visible-near-infrared spec-troscopy for the assessment of soil contamination in river floodplains[J].Analytica Chimica Acta,2001,446(1/2):97-105.
• [6]KEMPER T,SOMMER S,Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy[J].Environmental Science and Technology,2002,36(12):2742-2747.
• [7]王俭,孙铁珩,李培军,等.基于人工神经网络的区域水环境承载力评价模型及其应用[J].生态学杂志,2007,26(1):139-144.(WANG Jian,SUN Tieheng,LI Peijun,et al.Evaluation model of regional water environment carrying capacity based on artificial neural network and its application in Liaoning Province[J].Chinese Journal of Ecology,2007,26(1):139-144.)
• [8]都莎莎,王红旗,刘妹媛,等.基于人工神经网络改进的地下水水质评价模型研究及应用[J].北京师范大学学报(自然科学版),2014,4:424-428.(DU Shasha,WANG Hongqi,LIU Meiyuan,et al.Improved model of groundwater quality evaluation based on artificial neural network[J].Journal of Beijing Normal University(Natural Science),2014,4:424-428.)
• [9]郭云开,周峰松,丁美青,等.水稻冠层与土壤高光谱反演土壤重金属对比研究[J].遥感信息,2017,32(2):173-179.(GUO Yunkai,ZHOU Fengsong,DING Meiqing,et al.Comparison of soil heavy metal retrieval between cultivated soil and rice canopy hyperspectral features[J].Remote Sensing Information,2017,32(2):173-179.)
• [10]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.(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.)
• [11]浦瑞良,宫鹏.高光谱遥感及其应用[M].北京:高等教育出版社,2000:99.(PU Ruiliang,GONG Peng.Hyperspectral remote sensing and its application[M].Beijing,Higher Education Press,2000:99.)
• [12]郭云开,曹小燕,谢琼,等.模拟多光谱的土壤重金属含量反演研究初探[J].测绘工程,2015(12):7-11.(GUO Yunkai,CAO Xiaoyan,XIE Qiong,et al.Primary research on the inversion model of soil heavy metal based on simulation multi-spectral data[J].Engineering of Surveying and Mapping,2015(12):7-11.)
• [13]姚付启,张振华,杨润亚,等.基于主成分分析和BP神将网络的法国梧桐叶绿素含量高光谱反演研究[J].测绘科学,2010,35(1):109-112.(YAO Fuqi,ZHANG Zhenhua,YANG Runya,et al.Application of mobile collocation method in the interpolation of nature abnormal[J].Science of Surveying and Mapping,2010,35(1):109-112.)
• [14]SCHENKEL EA.Optical classification of quartz lascas by artificial neural networks[J].Mineral Processing and Extractive Metallurgy Review,2015,36(5):281-287.
• [15]张文博,郭云开.基于BP神经网络的建筑物沉降预测模型研究[J].测绘工程,2013,22(22):52-56.(ZHANG Wenbo,GUO Yunkai.Prediction model of building settlement based on BP neural network[J].Engineering of Surveying and Mapping,2013,22(22):52-56.)