發(fā)布時(shí)間：2018-05-04 11:38

  本文選題：葉綠素含量 + BP神經(jīng)網(wǎng)絡(luò)��； 參考：《中國地質(zhì)大學(xué)(北京)》2015年碩士論文

【摘要】：葉綠素是作物在進(jìn)行光合作用時(shí)的一類重要的色素,直接控制著作物能量傳遞和物質(zhì)循環(huán)過程,其含量的變化可以用來評價(jià)作物光合作用的能力、作物受重金屬污染脅迫的程度、以及作物的營養(yǎng)水平等。因此,作物葉綠素含量的監(jiān)測對于農(nóng)業(yè)的生產(chǎn)具有重要意義。本研究以長春的4塊水稻田作為采樣區(qū)域,通過地面實(shí)測的ASD光譜數(shù)據(jù)和實(shí)測的水稻葉綠素含量數(shù)據(jù),建立水稻葉綠素含量的高光譜反演模型。通過分析水稻光譜曲線的“峰-谷”形態(tài)特征,利用Hyperion影像,將已建立的模型進(jìn)行升尺度,并在區(qū)域尺度進(jìn)行應(yīng)用。本文主要工作及結(jié)論如下:(1)本文建立了基于BP神經(jīng)網(wǎng)絡(luò)算法的水稻葉綠素含量高光譜反演模型,其輸入變量為根據(jù)前人的研究成果和試驗(yàn)分析得到的4個(gè)植被指數(shù),隱含層個(gè)數(shù)為1,含有12個(gè)神經(jīng)元節(jié)點(diǎn),輸出變量為葉綠素含量數(shù)據(jù),模型結(jié)構(gòu)為4-12-1。決定系數(shù)R2=0.882,均方根誤差RMSE=2.958。(2)通過對已建立的水稻葉綠素含量高光譜反演模型的分析比較得到,基于BP神經(jīng)網(wǎng)絡(luò)算法建立的水稻葉綠素含量高光譜反演模型與其它的統(tǒng)計(jì)模型(基于原始光譜及其變體的各自的一階導(dǎo)數(shù)和植被指數(shù)的單變量和多變量統(tǒng)計(jì)模型)相比,其決定系數(shù)較高,均方根誤差值較低,能夠更好地對水稻葉綠素含量進(jìn)行監(jiān)測。(3)研究發(fā)現(xiàn),水稻的光譜曲線存在明顯的“峰-谷”形態(tài)特征,ASD實(shí)測光譜數(shù)據(jù)及Hyperion影像像元反射率數(shù)據(jù),均可以表示為以波長λ為自變量,反射率數(shù)據(jù)為因變量的分段函數(shù),且兩條曲線之間形狀相似,由數(shù)學(xué)知識我們可得,兩條曲線可以通過曲線的伸縮平移來進(jìn)行相互轉(zhuǎn)換。(4)本研究根據(jù)以光譜“峰-谷”形態(tài)特征為依據(jù)的分段函數(shù),建立ASD實(shí)測光譜反射率數(shù)據(jù)和Hyperion影像像元反射率數(shù)據(jù)之間的線性轉(zhuǎn)換關(guān)系,通過模型的尺度轉(zhuǎn)換,來進(jìn)行水稻葉綠素含量的區(qū)域監(jiān)測,達(dá)到利用Hyperion遙感影像進(jìn)行快速、無損的水稻葉綠素含量遙感監(jiān)測的目的。
[Abstract]:Chlorophyll is a kind of important pigments in photosynthesis, which directly control the energy transfer and material cycle of crops. The change of chlorophyll content can be used to evaluate the ability of crop photosynthesis. The degree of heavy metal pollution to crops and the nutrient level of crops. Therefore, the monitoring of crop chlorophyll content plays an important role in agricultural production. In this study, the hyperspectral inversion model of rice chlorophyll content was established by using four paddy fields in Changchun as sampling area, and based on the measured ASD spectral data and the measured chlorophyll content data of rice. By analyzing the "peak-valley" morphological characteristics of the spectral curve of rice, the established model was scaled up by using Hyperion image and applied to the regional scale. The main work and conclusions of this paper are as follows: (1) in this paper, a hyperspectral inversion model of rice chlorophyll content based on BP neural network algorithm is established. The input variables are four vegetation indices based on the previous research results and experimental analysis. The number of hidden layers is 1, there are 12 neuron nodes, the output variables are chlorophyll content data, and the model structure is 4-12-1. Based on the analysis and comparison of the established hyperspectral inversion model of chlorophyll content in rice, the determination coefficient is 0.882and the root mean square error (RMSE) is 2.958.2. The hyperspectral inversion model of rice chlorophyll content based on BP neural network algorithm is compared with other statistical models (univariate and multivariate statistical models based on the first derivative of the original spectrum and its variants and the vegetation index). Its determination coefficient is higher, the root mean square error is lower, and it can better monitor the chlorophyll content of rice. There are obvious "peak-valley" morphological characteristics in the spectral curve of rice. The measured spectral data and the pixel reflectivity data of Hyperion images can be expressed as piecewise functions with wavelength 位 as independent variable and reflectivity data as dependent variable. And the shapes of the two curves are similar, and we can get from the mathematical knowledge that the two curves can be converted to each other by means of the stretching and translation of the curves.) the present study is based on the piecewise functions based on the morphological characteristics of the spectral "peak-valley". The linear conversion relationship between spectral reflectance data measured by ASD and pixel reflectance data of Hyperion image was established. The regional monitoring of rice chlorophyll content was carried out by scale conversion of the model, and the rapid use of Hyperion remote sensing image was achieved. Objective of remote sensing monitoring of chlorophyll content in rice.
【學(xué)位授予單位】：中國地質(zhì)大學(xué)(北京)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：S511;S127

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 布和敖斯?fàn)?馬建文,王勤學(xué),金子正美,福山龍次;多傳感器不同分辨率遙感數(shù)字圖像的尺度轉(zhuǎn)換[J];地理學(xué)報(bào);2004年01期

2 王平;劉湘南;黃方;;受污染脅迫玉米葉綠素含量微小變化的高光譜反演模型[J];光譜學(xué)與光譜分析;2010年01期

3 欒海軍;田慶久;余濤;胡新禮;黃彥;劉李;杜靈通;魏曦;;定量遙感升尺度轉(zhuǎn)換研究綜述[J];地球科學(xué)進(jìn)展;2013年06期

4 潘蓓;趙庚星;朱西存;劉海騰;梁爽;田大德;;利用高光譜植被指數(shù)估測蘋果樹冠層葉綠素含量[J];光譜學(xué)與光譜分析;2013年08期

5 丁艷萍;陳吉芬;高穩(wěn)利;李維;;氮素對水稻產(chǎn)量的影響[J];現(xiàn)代農(nóng)業(yè)科技;2014年09期

6 陳小玉;張靜;;基于粗糙集-神經(jīng)網(wǎng)絡(luò)的變壓器故障診斷方法[J];制造業(yè)自動(dòng)化;2011年17期

7 鄭蘭芬,王晉年;成像光譜遙感技術(shù)及其圖像光譜信息提取的分析研究[J];環(huán)境遙感;1992年01期

8 童慶禧,鄭蘭芬,王晉年,王向軍,董衛(wèi)東,胡遠(yuǎn)滿,黨順行;濕地植被成象光譜遙感研究[J];遙感學(xué)報(bào);1997年01期

9 浦瑞良,宮鵬;森林生物化學(xué)與CASI高光譜分辨率遙感數(shù)據(jù)的相關(guān)分析[J];遙感學(xué)報(bào);1997年02期

10 吳長山,項(xiàng)月琴,鄭蘭芬,童慶禧;利用高光譜數(shù)據(jù)對作物群體葉綠素密度估算的研究[J];遙感學(xué)報(bào);2000年03期

相關(guān)博士學(xué)位論文 前1條

1 王平;農(nóng)作物重金屬污染脅迫遙感弱信息增強(qiáng)與計(jì)算[D];東北師范大學(xué);2010年

相關(guān)碩士學(xué)位論文 前3條

1 呂杰;基于Hyperion高光譜遙感數(shù)據(jù)的城市綠地信息提取方法的研究[D];中國地質(zhì)大學(xué)（北京）;2009年

2 劉川浩;作物葉面積指數(shù)遙感反演空間尺度變換建模研究[D];中國地質(zhì)大學(xué)（北京）;2013年

3 劉金鋒;基于多源遙感數(shù)據(jù)的青海湖流域植被指數(shù)研究[D];青海師范大學(xué);2014年

，

本文編號：1842904