光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2014年
7期
1922-1926
,共5页
王延仓%杨贵军%朱金山%顾晓鹤%徐鹏%廖钦洪
王延倉%楊貴軍%硃金山%顧曉鶴%徐鵬%廖欽洪
왕연창%양귀군%주금산%고효학%서붕%료흠홍
有机质%离散小波%高光谱%偏最小二乘
有機質%離散小波%高光譜%偏最小二乘
유궤질%리산소파%고광보%편최소이승
Organic matter%Discrete wavelet%Hyperspectral%Partial least squares regression
基于北京市通州、顺义两区52个潮土样品高光谱数据,利用离散小波多尺度分析技术对其进行处理分析。首先将光谱按六种尺度进行分解,然后将各尺度分解数据与土壤有机质含量进行相关性分析,并筛选敏感波段,最后利用偏最小二乘法构建土壤有机质含量估测模型。结果表明:土壤光谱反射率经小波变换后,在参与建模的特征波段中,近红外波段居多,即近红外波段估测有机质含量的贡献高于可见光波段;低频信息对有机质含量的估测能力优于高频信息;高频信息对土壤有机质含量的估测精度随光谱分辨率降低而降低;与常用光谱变换算法相比,小波变换分析法在一定程度上提高了土壤光谱对有机质含量的估测能力,其低频信息与高频信息构建的最优模型预测精度均较高,低频信息的 R2=0.722,RMSE=0.221,高频信息的 R2=0.670,RMSE=0.255。
基于北京市通州、順義兩區52箇潮土樣品高光譜數據,利用離散小波多呎度分析技術對其進行處理分析。首先將光譜按六種呎度進行分解,然後將各呎度分解數據與土壤有機質含量進行相關性分析,併篩選敏感波段,最後利用偏最小二乘法構建土壤有機質含量估測模型。結果錶明:土壤光譜反射率經小波變換後,在參與建模的特徵波段中,近紅外波段居多,即近紅外波段估測有機質含量的貢獻高于可見光波段;低頻信息對有機質含量的估測能力優于高頻信息;高頻信息對土壤有機質含量的估測精度隨光譜分辨率降低而降低;與常用光譜變換算法相比,小波變換分析法在一定程度上提高瞭土壤光譜對有機質含量的估測能力,其低頻信息與高頻信息構建的最優模型預測精度均較高,低頻信息的 R2=0.722,RMSE=0.221,高頻信息的 R2=0.670,RMSE=0.255。
기우북경시통주、순의량구52개조토양품고광보수거,이용리산소파다척도분석기술대기진행처리분석。수선장광보안륙충척도진행분해,연후장각척도분해수거여토양유궤질함량진행상관성분석,병사선민감파단,최후이용편최소이승법구건토양유궤질함량고측모형。결과표명:토양광보반사솔경소파변환후,재삼여건모적특정파단중,근홍외파단거다,즉근홍외파단고측유궤질함량적공헌고우가견광파단;저빈신식대유궤질함량적고측능력우우고빈신식;고빈신식대토양유궤질함량적고측정도수광보분변솔강저이강저;여상용광보변환산법상비,소파변환분석법재일정정도상제고료토양광보대유궤질함량적고측능력,기저빈신식여고빈신식구건적최우모형예측정도균교고,저빈신식적 R2=0.722,RMSE=0.221,고빈신식적 R2=0.670,RMSE=0.255。
For improving the estimation accuracy of soil organic matter content of the north fluvo-aquic soil ,wavelet transform technology is introduced .The soil samples were collected from Tongzhou district and Shunyi district in Beijing city .And the data source is from soil hyperspectral data obtained under laboratory condition .First ,discrete wavelet transform efficiently decompo-ses hyperspectral into approximate coefficients and detail coefficients .Then ,the correlation between approximate coefficients , detail coefficients and organic matter content was analyzed ,and the sensitive bands of the organic matter were screened .Finally , models were established to estimate the soil organic content by using the partial least squares regression (PLSR) .Results show that the NIR bands made more contributions than the visible band in estimating organic matter content models ;the ability of ap-proximate coefficients to estimate organic matter content is better than that of detail coefficients ;The estimation precision of the detail coefficients fir soil organic matter content decreases with the spectral resolution being lower ;Compared with the commonly used three types of soil spectral reflectance transforms ,the wavelet transform can improve the estimation ability of soil spectral fir organic content ;The accuracy of the best model established by the approximate coefficients or detail coefficients is higher , and the coefficient of determination (R2 ) and the root mean square error (RMSE) of the best model for approximate coefficients are 0.722 and 0.221 ,respectively .The R2 and RMSE of the best model for detail coefficients are 0.670 and 0.255 ,respectively .