【摘要】：土壤高光譜數(shù)據(jù)量大、波段維數(shù)高,存在光譜信息無(wú)效、冗余和重疊現(xiàn)象,導(dǎo)致基于全波段構(gòu)建的土壤有機(jī)質(zhì)含量反演模型不穩(wěn)定、精度難以提升。因此,探尋篩選關(guān)鍵波長(zhǎng)變量的方法,通過(guò)濾除干擾、冗余、共線信息,提高模型預(yù)測(cè)性能,是目前土壤高光譜研究的熱點(diǎn)之一。該文對(duì)江漢平原公安縣的土壤樣本進(jìn)行室內(nèi)理化分析、光譜測(cè)量與處理等工作獲取了實(shí)證數(shù)據(jù),采用無(wú)信息變量消除法(uninformative variables elimination,UVE)剔除無(wú)效變量,利用競(jìng)爭(zhēng)性自適應(yīng)重加權(quán)算法(competitive adaptive reweighted sampling,CARS)濾除冗余變量,運(yùn)用連續(xù)投影算法(successive projections algorithm,SPA)消除共線變量,并嘗試將不同類(lèi)型的篩選方法進(jìn)行耦合篩選關(guān)鍵波長(zhǎng)變量,應(yīng)用偏最小二乘回歸(partial least squares regression,PLSR)分別建立土壤有機(jī)質(zhì)含量估算模型,對(duì)比各種變量篩選方法的優(yōu)缺點(diǎn),最終,構(gòu)建篩選土壤高光譜數(shù)據(jù)關(guān)鍵變量的方法體系。研究結(jié)果表明,除SPA方法的模型精度低于全波段外,其他6種變量篩選方法的建模效果均優(yōu)于全波段;在3種單個(gè)變量篩選方法中,CARS方法優(yōu)于UVE、SPA變量篩選方法,能有效地篩選出重要波長(zhǎng)變量,其預(yù)測(cè)集相對(duì)分析誤差RPD值為2.84;綜合比較各種變量篩選方法,發(fā)現(xiàn)CARS-SPA方法從全波段2 001個(gè)波長(zhǎng)中篩選出37個(gè)特征波長(zhǎng)建立的土壤有機(jī)質(zhì)含量的PLSR模型效果最好,其模型預(yù)測(cè)集的決定系數(shù)R2和相對(duì)分析誤差RPD值分別為0.92、3.60,所選波段僅為全波段的1.85%。CARS-SPA-PLSR模型簡(jiǎn)單、預(yù)測(cè)效果好,可作為該區(qū)域土壤有機(jī)質(zhì)含量估測(cè)的重要方法,對(duì)今后土壤近地傳感器設(shè)備的開(kāi)發(fā)具有一定的指導(dǎo)作用。
[Abstract]:Because of the large amount of soil hyperspectral data, high wave band dimension, invalid spectral information, redundant and overlapping phenomena, the inversion model of soil organic matter content based on the whole wave band is unstable and the precision is difficult to improve. Therefore, it is one of the hotspots of soil hyperspectral research to explore the method of screening key wavelength variables and improve the performance of model prediction by filtering interference, redundancy and collinear information. In this paper, the indoor physical and chemical analysis, spectral measurement and treatment of soil samples in Jianghan Plain were carried out, and the invalid variables were eliminated by (uninformative variables elimination without information variable. The competitive adaptive reweighting algorithm (competitive adaptive reweighted sampling cars) is used to filter redundant variables, and the continuous projection algorithm (successive projections algorithm is used to eliminate collinear variables. The estimation model of soil organic matter content was established by partial least square regression (partial least squares regression), and the advantages and disadvantages of various methods were compared. Finally, the method system of selecting the key variables of soil hyperspectral data was constructed. The results show that the model accuracy of the SPA method is lower than that of the full-band method, and the modeling effect of the other six variable selection methods is better than that of the full-band method, and the car method is better than the UVE-SPA variable selection method among the three single variable selection methods. The relative analysis error (RPD) of the prediction set is 2.84. It was found that the PLSR model of soil organic matter content established by CARS-SPA method was the best, and 37 characteristic wavelengths were selected from 2 001 wavelengths. The determination coefficient R2 and the relative analysis error RPD of the model prediction set are 0.92n3.60, respectively. The selected band is only 1.85. CARS-SPA-PLSR model is simple, and the prediction effect is good. It can be used as an important method to estimate the soil organic matter content in this region. It can be used to guide the development of soil near-earth sensor equipment in the future.
【作者單位】： 華中師范大學(xué)地理過(guò)程分析與模擬湖北省重點(diǎn)實(shí)驗(yàn)室;華中師范大學(xué)城市與環(huán)境科學(xué)學(xué)院;華中師范大學(xué)湖北經(jīng)濟(jì)與社會(huì)發(fā)展研究院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(41401232;41271534) 中央高�；究蒲袠I(yè)務(wù)費(fèi)專(zhuān)項(xiàng)資金項(xiàng)目(CCNU15A05006;CCNU15ZD001)
【分類(lèi)號(hào)】：S153.621;S127

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 白麗;王進(jìn);蔣桂英;楊朋;孫蜀江;;干旱區(qū)基于高光譜的棉花遙感估產(chǎn)研究[J];中國(guó)農(nóng)業(yè)科學(xué);2008年08期

2 盧巖;郭斗斗;孫成明;劉濤;陳瑛瑛;武威;;基于高光譜的水稻土有機(jī)質(zhì)含量估算研究[J];中國(guó)農(nóng)學(xué)通報(bào);2014年18期

3 江威;;武夷山地區(qū)土壤有機(jī)質(zhì)高光譜模型建立與評(píng)價(jià)[J];安徽農(nóng)業(yè)科學(xué);2012年22期

4 徐明星;周生路;丁衛(wèi);吳紹華;吳巍;;蘇北沿海灘涂地區(qū)土壤有機(jī)質(zhì)含量的高光譜預(yù)測(cè)[J];農(nóng)業(yè)工程學(xué)報(bào);2011年02期

5 盧艷麗;白由路;楊俐蘋(píng);王紅娟;孔慶波;;基于主成分回歸分析的土壤有機(jī)質(zhì)高光譜預(yù)測(cè)與模型驗(yàn)證[J];植物營(yíng)養(yǎng)與肥料學(xué)報(bào);2008年06期

6 盧艷麗;白由路;楊俐蘋(píng);王磊;王賀;;東北平原不同類(lèi)型土壤有機(jī)質(zhì)含量高光譜反演模型同質(zhì)性研究[J];植物營(yíng)養(yǎng)與肥料學(xué)報(bào);2011年02期

7 彭杰;向紅英;周清;張楊珠;王家強(qiáng);龐新安;;土壤氧化鐵的高光譜響應(yīng)研究[J];光譜學(xué)與光譜分析;2013年02期

8 陳紅艷;趙庚星;李希燦;朱西存;隋龍;王銀娟;;基于小波變換的土壤有機(jī)質(zhì)含量高光譜估測(cè)[J];應(yīng)用生態(tài)學(xué)報(bào);2011年11期

9 于士凱;姚艷敏;王德?tīng)I(yíng);司海青;;基于高光譜的土壤有機(jī)質(zhì)含量反演研究[J];中國(guó)農(nóng)學(xué)通報(bào);2013年23期

10 喬璐;陳立新;張杰;黃蘭英;;哈爾濱市土壤有機(jī)質(zhì)高光譜模型[J];東北林業(yè)大學(xué)學(xué)報(bào);2010年07期

相關(guān)會(huì)議論文 前1條

1 王進(jìn);白麗;蔣貴英;楊朋;孫蜀江;;干旱區(qū)基于高光譜的棉花遙感估產(chǎn)研究[A];中國(guó)氣象學(xué)會(huì)2008年年會(huì)衛(wèi)星遙感應(yīng)用技術(shù)與處理方法分會(huì)場(chǎng)論文集[C];2008年

相關(guān)碩士學(xué)位論文 前1條

1 吳斐;基于光譜反射率的耕地估產(chǎn)研究[D];華中師范大學(xué);2011年

，

本文編號(hào)：2133453