基于支持向量机回归的水稻地重金属Fe含量估算  

The Prediction of the Heavy Metal Fe content in Rice Field Based on Support Vector Machine Regression

作　　者：郭云开[1,2] 刘磊 刘宁[1,2] 朱善宽[1,2] 李丹娜[1,2] 

机构地区：[1]长沙理工大学,交通运输工程学院,湖南长沙410076 [2]长沙理工大学,测绘遥感应用技术研究所,湖南长沙410076

出　　处：《北京测绘》2017年第6期10-13,共4页Beijing Surveying and Mapping

基　　金：国家自然科学基金面上项目(41471421,41671498)

摘　　要：本文利用地物光谱仪获取的土壤反射光谱,通过多元线性回归模型和支持向量机回归模型分别建立土壤铁含量的估算模型,并利用检验数据对模型进行验证。建模和估算决定系数为0.9855和0.7158,估算均方根误差为0.0601,结果表明利用支持向量机回归模型能够较好的进行土壤重金属含量的估算。In this paper,the reflectance spectra of soil was obtained by using the ground color spectrometer,and the prediction model of soil Fe content was established by multiple linear regression model and support vector regression model,and test these model.The coefficient of determination of the modeling and prediction are 0.9855 and 0.7158,the RMSE is 0.0601.The results showed that the support vector machine regression model could be used to predict the soil heavy metal content.

关 键 词：支持向量机 回归模型 水稻地 Fe含量 

分 类 号：P237[天文地球—摄影测量与遥感] TP18[天文地球—测绘科学与技术]