發(fā)布時(shí)間：2018-10-25 12:40

【摘要】：以土壤多樣化的陜西省橫山縣為研究區(qū)域,比較了3種基于高光譜數(shù)據(jù)的土壤有機(jī)質(zhì)含量反演模型,在實(shí)驗(yàn)室利用ASD Field Spec FR地物光譜儀對(duì)橫山縣野外采集的土壤樣品進(jìn)行光譜測(cè)定,并通過(guò)重鉻酸鉀氧化容量法測(cè)定土壤有機(jī)質(zhì)含量。然后對(duì)原始光譜反射率的倒數(shù)進(jìn)行微分運(yùn)算獲得其一階導(dǎo)數(shù)光譜,將原始光譜反射率、一階導(dǎo)數(shù)光譜分別與土壤有機(jī)質(zhì)含量進(jìn)行相關(guān)性分析,得到相關(guān)性系數(shù)r較高的特征波段的一階導(dǎo)數(shù)光譜,直接建立基于一階導(dǎo)數(shù)光譜的多元線性逐步回歸分析(MLSR)模型。同時(shí)針對(duì)這些相關(guān)性系數(shù)較高的特征波段的一階導(dǎo)數(shù)光譜進(jìn)行主成分分析(Principal component analysis,PCA),利用主成分分析得到的結(jié)果分別建立BP神經(jīng)網(wǎng)絡(luò)反演模型(PCA-BP)和多元線性逐步回歸分析模型(PCA-MLSR)。用上述3種方法進(jìn)行土壤有機(jī)質(zhì)含量反演,并對(duì)3種反演結(jié)果進(jìn)行精度驗(yàn)證與比較。實(shí)驗(yàn)分析結(jié)果表明:在3種模型中,基于主成分分析結(jié)果構(gòu)建的PCA-BP模型在土壤有機(jī)質(zhì)含量反演中決定系數(shù)(R2)最高,為0.893 0,均方根誤差(RMSE)為0.118 5%;其次為運(yùn)用全部主成分PCA分析結(jié)果構(gòu)建的多元線性逐步回歸模型,R2為0.740 7,RMSE為0.161 3%;而采用一階導(dǎo)數(shù)光譜反射率構(gòu)建的多元線性逐步回歸模型中,最佳反演模型R2僅為0.689 9,RMSE為0.171 0%。由此說(shuō)明,PCA-BP模型有機(jī)質(zhì)含量反演精度明顯高于多元線性逐步回歸模型,利用全部主成分進(jìn)行多元逐步回歸,其有機(jī)質(zhì)含量反演精度優(yōu)于僅用累計(jì)方差貢獻(xiàn)率大于90%的主成分進(jìn)行多元逐步回歸的精度,可以更好地反演土壤有機(jī)質(zhì)的含量。
[Abstract]:Taking Hengshan County of Shaanxi Province as the research area, three kinds of inversion models of soil organic matter content based on hyperspectral data were compared. The soil samples collected in Hengshan County were measured by ASD Field Spec FR ground object spectrometer and the content of soil organic matter was determined by potassium dichromate oxidation volumetric method. The first derivative spectrum is obtained by differential operation of reciprocal reflectance of original spectrum. The correlation between original spectral reflectance and soil organic matter content is analyzed respectively. The first derivative spectrum of the characteristic band with higher correlation coefficient r is obtained, and the multivariate linear stepwise regression (MLSR) model based on the first order derivative spectrum is established directly. At the same time, the first derivative spectra of these characteristic bands with high correlation coefficient are analyzed by principal component analysis (Principal component analysis,PCA). The BP neural network inversion model (PCA-BP) and the multivariate linear stepwise regression model (PCA-MLSR) are established by using the results of principal component analysis (PCA). The above three methods were used to invert the soil organic matter content, and the accuracy of the three inversion results was verified and compared. The experimental results show that, among the three models, the PCA-BP model based on principal component analysis (PCA) has the highest determining coefficient (R2) in soil organic matter content inversion. The root mean square error (RMS) is 0.893, the root mean square error (RMSE) is 0.118 5, the multivariate linear stepwise regression model based on the results of all principal component PCA analysis (R2 = 0.740 7), and the multivariate linear stepwise regression model based on the first derivative spectral reflectivity. The best inversion model R2 is only 0.689 9 and 0.171 0. It shows that the inversion accuracy of organic matter content in PCA-BP model is obviously higher than that in multivariate linear stepwise regression model, and multivariate stepwise regression is carried out by using all principal components. The inversion accuracy of organic matter content is better than that of multivariate stepwise regression with only the principal components whose cumulative variance contribution rate is more than 90%, and the content of soil organic matter can be retrieved better.
【作者單位】： 同濟(jì)大學(xué)測(cè)繪與地理信息學(xué)院;山東農(nóng)業(yè)大學(xué)信息科學(xué)與工程學(xué)院;
【基金】：上海市科學(xué)技術(shù)委員會(huì)科研計(jì)劃項(xiàng)目(13231203602)
【分類號(hào)】：S153.621

【相似文獻(xiàn)】

相關(guān)期刊論文 前5條

1 趙艷霞,秦軍,周秀驥;遙感信息與棉花模型結(jié)合反演模型初始值和參數(shù)的方法研究[J];棉花學(xué)報(bào);2005年05期

2 欒福明;張小雷;熊黑鋼;王芳;張芳;;基于TM影像的荒漠-綠洲交錯(cuò)帶土壤有機(jī)質(zhì)含量反演模型[J];中國(guó)沙漠;2014年04期

3 吳明珠;李小梅;沙晉明;;亞熱帶土壤鉻元素的高光譜響應(yīng)和反演模型[J];光譜學(xué)與光譜分析;2014年06期

4 宋開(kāi)山;劉殿偉;王宗明;呂冬梅;張柏;任春穎;杜嘉;;基于小波分析的玉米葉綠素a與LAI高光譜反演模型研究[J];農(nóng)業(yè)系統(tǒng)科學(xué)與綜合研究;2011年02期

5 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 王百合;劉代志;黃世奇;李義紅;;高光譜遙感中的植被光譜特征分析及參量反演模型研究進(jìn)展[A];國(guó)家安全地球物理叢書(shū)（八）——遙感地球物理與國(guó)家安全[C];2012年

相關(guān)博士學(xué)位論文 前1條

1 毛德強(qiáng);地下水反演模型解的唯一性和高精度反演方法研究[D];中國(guó)地質(zhì)大學(xué)（北京）;2013年

相關(guān)碩士學(xué)位論文 前6條

1 杜志紅;水稻葉綠素含量高光譜反演模型及尺度轉(zhuǎn)換方法研究[D];中國(guó)地質(zhì)大學(xué)(北京);2015年

2 牟蒙;基于高光譜遙感的翅堿蓬生物量反演模型研究[D];大連海洋大學(xué);2016年

3 楊伊欣;‘新新2號(hào)’核桃堅(jiān)果品質(zhì)葉片光譜反演模型[D];新疆農(nóng)業(yè)大學(xué);2016年

4 任超;基于低相干相位顯微鏡細(xì)胞納米結(jié)構(gòu)參數(shù)的反演模型研究[D];重慶大學(xué);2014年

5 邱冬梅;基于MODIS的主要積雪參數(shù)反演及其應(yīng)用研究[D];新疆大學(xué);2011年

6 蘇藝;基于高光譜信息的橡膠小苗葉片磷素含量的反演[D];海南大學(xué);2015年

，

本文編號(hào)：2293721