Please wait a minute...
浙江大学学报（农业与生命科学版）
浙江大学学报(农业与生命科学版)  2011, Vol. 37 Issue (3): 300-306    DOI: 10.3785/j.issn.1008-9209.2011.03.010
农业科学     
基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究
岑益郎,宋韬,何勇,鲍一丹
浙江大学生物系统工程与食品科学学院,浙江 杭州 310029
Rapid detection method of soil organic matter contents using visible/near infrared diffuse reflectance spectral data
CEN Yi-lang,SONG Tao,HE Yong,BAO Yi-dan
College of Biosystems Engineering and Food  Science , Zhejiang University , Hangzhou 310029 , China
 全文: PDF(823 KB)   HTML ( ) 
摘要： 为研究不同土壤颗粒粒径对可见/近红外光谱分析技术在土壤有机质含量快速检测应用中的影响,获取粒径为0.169～2mm 和＜ 0.169mm 的2种土壤样本(各53个)的可见/近红外光谱(325 ～1075 nm) ,分别建立各自的主成分-反向传播神经网络( PCA-BPNN) 、最小二乘-支持向量机(LS-SVM)和偏最小二乘法( PLS)土壤有机质含量检测模型.结果表明:当土壤粒径为0.169～2 mm 时,所建立模型的土壤有机质含量预测相关系数r 均在0.84以上,且预测均方根误差( RMSEP)都在0.20以下;而当土壤粒径＜0.169 mm 时,所建立模型的预测相关系数r 均不超过0.71,而RMSEP 都在0.23以上;对于相同粒径的土壤,PLS 模型对土壤有机质含量的预测效果优于LS-SVM 和PCA-BPNN 模型.说明不同土壤颗粒粒径会显著影响可见/近红外光谱对于土壤有机质含量的预测结果.
Abstract: The effect of different soil particle sizes on the visible/near infrared spectra to detect soil organic matter contents was analyzed . The visible/near infrared spectra of soil samples with the particle sizes of 0.169--2 mm and ＜ 0.169 mm were measured at the range of 325‐1075 nm . Then the principal component analysis-back propagation neural network ( PCA-BPNN ) , least squares‐support vector machine (LS-SVM) and partial least squares ( PLS) models were established to detect the soil organic matter contents . When the soil particle size range was from 0.169 to 2 mm , the correlation coefficients ( r) of prediction of all three models were above 0.84 and root mean square errors of prediction (RMSEP) were below 0.20 . When the soil particle size range was smaller than 0.169 mm , the r values of the models were below 0.71 and RMSEPs were above 0.23 . When either the soil particle size range was from 0.169 to 2 mm or smaller than 0.169 mm , PLS models obtained better results than LS-SVM and PCA-BPNN models . The overall results show that the difference of soil particle size can significantly affect the prediction results of visible/near infrared spectra to detect the soil organic matter contents .
出版日期: 2011-05-20
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　　
岑益郎
宋韬
何勇
鲍一丹

引用本文:

岑益郎,宋韬,何勇,鲍一丹. 基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究[J]. 浙江大学学报(农业与生命科学版), 2011, 37(3): 300-306.

CEN Yi-lang,SONG Tao,HE Yong,BAO Yi-dan. Rapid detection method of soil organic matter contents using visible/near infrared diffuse reflectance spectral data. Journal of Zhejiang University: Agric. & Life Sci., 2011, 37(3): 300-306.

链接本文:

http://www.zjujournals.com/agr/CN/10.3785/j.issn.1008-9209.2011.03.010    或    http://www.zjujournals.com/agr/CN/Y2011/V37/I3/300

No related articles found!