首页 | 本学科首页   官方微博 | 高级检索  
     

近红外光谱小波分析在土壤参数预测中的应用
引用本文:郑立华,李民赞,潘娈,孙建英,唐宁. 近红外光谱小波分析在土壤参数预测中的应用[J]. 光谱学与光谱分析, 2009, 29(6): 1549-1552. DOI: 10.3964/j.issn.1000-0593(2009)06-1549-04
作者姓名:郑立华  李民赞  潘娈  孙建英  唐宁
作者单位:中国农业大学现代精细农业系统集成研究教育部重点实验室,北京 100083
基金项目:国家高技术研究发展计划(863计划),国家自然科学基会项目 
摘    要:从田间采集了150个田间土壤样本,在分析了所有样本的土壤参数统计特征之后,对原始近红外光谱数据进行了聚类分析,分别得到了50个土壤全氮和50个土壤有机质的等价样本及其对应光谱。对样本光谱曲线进行8层Biorthogonal小波包分解,分解得到的最低低频[80]结点对应着土壤水分以及土壤质地的光谱变化趋势,最高高频[8 255]结点对应着土壤粒度、光谱仪精度等引起的高频震荡。对以上两个结点进行重构并从样本光谱曲线中剔除以上影响成分,得到了对应的土壤参数特征光谱。基于特征光谱建立了土壤参数偏最小二乘回归模型:全氮偏最小二乘预测模型的预测系数rc达到了0.960,验证系数rv达到了0.920;有机质偏最小二乘预测模型的预测系数rc达到0.922,验证系数rv达到0.883。模型精度明显提高,满足实际生产的需要。

关 键 词:光谱分析  土壤有机质  土壤全氮  小波分析  特征光谱  
收稿时间:2008-03-02

Application of Wavelet Packet Analysis in Estimating Soil Parameters Based on NIR Spectra
ZHENG Li-hua,LI Min-zan,PAN Luan,SUN Jian-ying,TANG Ning. Application of Wavelet Packet Analysis in Estimating Soil Parameters Based on NIR Spectra[J]. Spectroscopy and Spectral Analysis, 2009, 29(6): 1549-1552. DOI: 10.3964/j.issn.1000-0593(2009)06-1549-04
Authors:ZHENG Li-hua  LI Min-zan  PAN Luan  SUN Jian-ying  TANG Ning
Affiliation:Key Laboratory of Ministry of Education on Modern Precision Agriculture System Integration Research, China Agricultural University, Beijing 100083, China
Abstract:Using the method of wavelet analysis,the NIR spectra of soil samples were decomposed and reconstructed,and higher precision PLS models were established to estimate soil parameter(TN,SOM).One hundred fifty soil samples were collected from a winter wheat field and the NIR spectra of all samples were measured.Firstly,experiment statistic features were analyzed aiming at all soil samples,and the system clustering was carried out for TN and SOM respectively.Then 50 new TN samples and their corresponding spectra,...
Keywords:Spectral analysis  Soil organic matter  Soil total nitrogen  Wavelet packet analysis  Characteristic spectrum  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《光谱学与光谱分析》浏览原始摘要信息
点击此处可从《光谱学与光谱分析》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号