發(fā)布時(shí)間：2018-02-27 16:17

  本文關(guān)鍵詞： 黑土 有機(jī)質(zhì) 高光譜 多元逐步回歸 偏最小二乘回歸 支持向量機(jī)　出處：《吉林大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：東北黑土是不可再生的寶貴資源，關(guān)系到東北地區(qū)乃至全國(guó)的糧食生產(chǎn)、經(jīng)濟(jì)發(fā)展以及生態(tài)環(huán)境，然而對(duì)黑土的過(guò)度開(kāi)發(fā)以及不合理的耕作方式等造成了土壤的貧瘠化，水土流失嚴(yán)重。因此有必要及時(shí)對(duì)土壤屬性進(jìn)行測(cè)定與質(zhì)量評(píng)價(jià)，保護(hù)黑土資源刻不容緩。高光譜遙感技術(shù)的發(fā)展為土壤理化參數(shù)的獲取提供了一種便捷、高效的手段。相比傳統(tǒng)方法，更省時(shí)省力，降低成本；相比常規(guī)多光譜遙感，能提高反演精度。其較高的光譜分辨率能為分析土壤表層情況、內(nèi)在屬性等提供詳細(xì)的數(shù)據(jù)，目前已經(jīng)在估測(cè)土壤有機(jī)碳、水分、氮、磷、鉀等相關(guān)元素含量方面有較為廣泛的應(yīng)用。 本文以東北典型黑土區(qū)的農(nóng)田土壤為研究對(duì)象，以68個(gè)黑土樣本的實(shí)測(cè)高光譜數(shù)據(jù)和有機(jī)質(zhì)含量為主要數(shù)據(jù)源。土壤光譜曲線是其各個(gè)屬性成分綜合作用的結(jié)果，分析土壤的反射光譜特征是進(jìn)行有機(jī)質(zhì)含量估測(cè)的基礎(chǔ)。在對(duì)黑土光譜數(shù)據(jù)進(jìn)行斷點(diǎn)校正、平滑去噪和變換處理后，首先比較分析了不同有機(jī)質(zhì)含量等級(jí)下、不同光譜分辨率下，黑土室內(nèi)光譜曲線特征的差異，并將室內(nèi)、野外黑土光譜進(jìn)行了對(duì)比，利用單相關(guān)分析，得出有機(jī)質(zhì)的響應(yīng)波段范圍。然后，基于光譜分析技術(shù)和統(tǒng)計(jì)學(xué)原理，利用黑土光譜數(shù)據(jù)及其變換形式分別建立了多元逐步回歸、偏最小二乘和支持向量機(jī)回歸模型來(lái)對(duì)有機(jī)質(zhì)含量進(jìn)行估測(cè)，并分析對(duì)比了各種模型的精度。主要得到以下結(jié)論： 黑土室內(nèi)光譜曲線整體光滑平緩，反射率隨著波長(zhǎng)增大而逐漸升高，屬于有機(jī)質(zhì)控制類型，有機(jī)質(zhì)影響著整個(gè)波段的光譜特征，尤其是可見(jiàn)光波段。室內(nèi)與野外的黑土光譜曲線特征基本相似，由于不受外在環(huán)境影響，，光譜曲線更加光滑規(guī)整，一些細(xì)節(jié)特征更加明顯。有機(jī)質(zhì)響應(yīng)波段范圍較寬，當(dāng)采樣間隔增至10nm時(shí)，曲線更為光滑，光譜特征幾乎沒(méi)有改變；當(dāng)采樣間隔大于20nm時(shí)，黑土光譜的吸收特征隨著光譜分辨率的降低逐漸削弱。有機(jī)質(zhì)含量與黑土光譜反射率呈負(fù)相關(guān)，顯著相關(guān)波段為550～680nm，吸光度一階微分變換對(duì)增強(qiáng)相關(guān)性的作用最大，在1274nm處，相關(guān)系數(shù)達(dá)到-0.8。 在多元逐步回歸模型中，吸光度一階微分及連續(xù)統(tǒng)去除一階微分的建模效果較好，將黑土有機(jī)質(zhì)含量的對(duì)數(shù)形式作為因變量后，每個(gè)模型的建模和預(yù)測(cè)精度都有提高。利用全光譜數(shù)據(jù)建立的偏最小二乘回歸模型，建模結(jié)果較多元逐步回歸有很大改善，其中吸光度光譜一階微分的PLSR模型結(jié)果最優(yōu)，RPD為2.664，有較好的預(yù)測(cè)能力。不同光譜分辨率下的PLSR模型，隨著光譜分辨率的降低，精度先提高后逐漸降低，在10nm采樣間隔時(shí)，模型效果最好，說(shuō)明重采樣后不僅保留了原始的光譜特征，還減少了數(shù)據(jù)的冗余，削弱了噪聲的影響。最小二乘支持向量機(jī)回歸建模結(jié)果要優(yōu)于前兩種線性模型，特別是通過(guò)PLS提取特征主成分后，不僅縮短了計(jì)算時(shí)間，模型穩(wěn)定性和預(yù)測(cè)能力都得到增強(qiáng)，R2C為0.993，RPD為3.682，縮小了建模和預(yù)測(cè)精度的差距。
[Abstract]:Northeast China is a valuable non renewable resources, related to the northeast region and the country's grain production, economic development and ecological environment, however, over exploitation of black soil and unreasonable tillage caused the impoverishment of soil, the soil erosion is serious. Therefore it is necessary to timely determination and quality evaluation of soil properties, protection the black soil resources is urgent. For the development of hyperspectral remote sensing technology for soil physicochemical parameters provides a convenient and efficient method. Compared with the traditional method, more time-saving, reduces the cost; compared with the conventional multi spectral remote sensing, can improve the inversion precision. Its high spectral resolution for analysis of surface soil, such as intrinsic property provide detailed data, has been in the estimation of soil organic carbon, water, nitrogen, phosphorus, is widely used on related elements content of potassium.
In this paper, farmland soil in typical black soil region of Northeast China as the research object, based on the measured hyperspectral data of 68 soil samples and organic matter content as the main data source. Soil spectral curve is the comprehensive result of each attribute composition, spectral characteristics analysis is based on estimation of soil organic matter content in the soil. The spectral data breakpoint correction, denoising and transform processing, the first comparative analysis of different organic content levels, different spectral resolution, different spectral characteristics of black soil indoors, and the indoor, compared with wild black soil spectra, using single correlation analysis, the organic matter and response wave band range. Spectral analysis and statistics, based on the principle of multiple stepwise regression were established using soil spectral data and the transformation form, the partial least squares regression model and support vector machine The content of organic matter is estimated, and the accuracy of various models is analyzed and compared. The following conclusions are obtained:
The indoor soil spectral curve overall smooth flat reflectivity with the wavelength gradually increases, which belongs to the type of organic matter control, organic matter affects the spectral characteristics of the band, especially the visible characteristics of black soil. The spectral curve of indoor and field similar to that by not subject to the impact of the external environment, spectral curve is more smooth, some the details of the more obvious characteristics of the organic matter. In response to a wide range of bands, as the sampling interval is increased to 10nm, the curve is more smooth, almost no change in spectral characteristics; when the sampling interval is greater than 20nm, soil absorption spectrum characteristics with reduced spectral resolution is gradually weakened. Organic matter content and soil reflectance was negatively correlated significantly the relevant band is 550 ~ 680nm, the absorbance of first order differential transform to enhance the relevance, at 1274nm, the correlation coefficient reached -0.8.
In the multivariate regression model, the first-order differential absorbance and continuum removal effect of modeling first-order differential is better, the logarithm of soil organic matter content as the dependent variables, modeling and prediction accuracy of each model are improved. Partial least squares regression model is established by using optical spectrum data, the modeling results are multiple stepwise regression is greatly improved, which results in the absorbance spectra of first order differential optimal PLSR model, RPD 2.664, has a good predictive ability. The PLSR model of different spectral resolution, with reduced spectral resolution, precision first increased and then decreased gradually, 10nm in the sampling interval, the best model, that not only re sampling retain the spectral features of the original, but also reduces the data redundancy, weaken the effect of noise. The least squares support vector machine regression modeling results are better than those of the first two kinds of linear models, especially After extracting feature principal components from PLS, the computation time is shortened, and the stability and prediction ability of the model are enhanced. R2C is 0.993 and RPD is 3.682, which reduces the gap between modeling and prediction accuracy.

【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：S153.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 顧曉鶴;王X;潘瑜春;蔡玉梅;黃文江;王慧芳;;基于HJ1A-HSI超光譜影像的耕地有機(jī)質(zhì)遙感定量反演[J];地理與地理信息科學(xué);2011年06期

2 周萍;王潤(rùn)生;閻柏琨;楊蘇明;王青華;;高光譜遙感土壤有機(jī)質(zhì)信息提取研究[J];地理科學(xué)進(jìn)展;2008年05期

3 董超華;楊軍;盧乃錳;楊忠東;施進(jìn)明;張鵬;劉玉潔;蔡斌;;風(fēng)云三號(hào)A星(FY-3A)的主要性能與應(yīng)用[J];地球信息科學(xué)學(xué)報(bào);2010年04期

4 謝伯承,薛緒掌,王紀(jì)華,王國(guó)棟;土壤參數(shù)的光譜實(shí)時(shí)分析[J];干旱地區(qū)農(nóng)業(yè)研究;2005年03期

5 劉蓉,陳文亮,徐可欣,邱慶軍,崔厚欣;奇異點(diǎn)快速檢測(cè)在牛奶成分近紅外光譜測(cè)量中的應(yīng)用[J];光譜學(xué)與光譜分析;2005年02期

6 劉煥軍;宇萬(wàn)太;張新樂(lè);馬強(qiáng);周樺;姜子紹;;黑土反射光譜特征影響因素分析[J];光譜學(xué)與光譜分析;2009年11期

7 劉煥軍;張新樂(lè);鄭樹(shù)峰;湯娜;胡言亮;;黑土有機(jī)質(zhì)含量野外高光譜預(yù)測(cè)模型[J];光譜學(xué)與光譜分析;2010年12期

8 劉煥軍;吳炳方;趙春江;趙云升;;光譜分辨率對(duì)黑土有機(jī)質(zhì)預(yù)測(cè)模型的影響[J];光譜學(xué)與光譜分析;2012年03期

9 趙葆常;楊建峰;常凌穎;陳立武;賀應(yīng)紅;薛彬;;嫦娥一號(hào)衛(wèi)星成像光譜儀光學(xué)系統(tǒng)設(shè)計(jì)與在軌評(píng)估[J];光子學(xué)報(bào);2009年03期

10 趙葆常;楊建峰;薛彬;喬衛(wèi)東;邱躍洪;;嫦娥一號(hào)干涉成像光譜儀的定標(biāo)[J];光子學(xué)報(bào);2010年05期

相關(guān)博士學(xué)位論文 前2條

1 鄭光輝;江蘇部分地區(qū)土壤屬性高光譜定量估算研究[D];南京大學(xué);2011年

2 李天奇;東北黑土區(qū)侵蝕溝成因與模型研究[D];中國(guó)科學(xué)院研究生院(東北地理與農(nóng)業(yè)生態(tài)研究所);2012年

本文編號(hào)：1543397