本文關(guān)鍵詞：基于改進(jìn)最小二乘支持向量機(jī)的小麥病蟲害遙感監(jiān)測(cè)研究　出處：《安徽大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 衛(wèi)星 遙感監(jiān)測(cè) 蚜蟲 白粉病 最小二乘支持向量機(jī)

【摘要】：中國(guó)作為一個(gè)農(nóng)業(yè)大國(guó),農(nóng)作物病蟲害發(fā)生種類多且影響范圍廣,給我國(guó)糧食生產(chǎn)造成了巨大的損失。區(qū)域尺度上準(zhǔn)確、及時(shí)地監(jiān)測(cè)農(nóng)作物病蟲害的發(fā)生情況有利于高效地指導(dǎo)防治工作,利用遙感技術(shù)對(duì)農(nóng)作物病蟲害信息進(jìn)行提取以及區(qū)域尺度上的作物病蟲害監(jiān)測(cè)已經(jīng)成為了熱門的研究課題。然而,如何選取合適有效的方法以及最大限度地挖掘遙感影像數(shù)據(jù)中有效的信息是研究者面臨的主要問題。本文以小麥的常見病蟲害—小麥白粉病和小麥蚜蟲為研究對(duì)象,以小麥白粉病和小麥蚜蟲在區(qū)域尺度上的監(jiān)測(cè)為研究主線,分別利用Landsat-8遙感衛(wèi)星影像數(shù)據(jù)和環(huán)境與災(zāi)害監(jiān)測(cè)預(yù)報(bào)小衛(wèi)星影像數(shù)據(jù)開展小麥病蟲害遙感監(jiān)測(cè)模型以及方法研究,具體研究?jī)?nèi)容和成果如下:(1)給出一種粒子群優(yōu)化最小二乘支持向量機(jī)的小麥白粉病監(jiān)測(cè)算法。以陜西省關(guān)中平原部分地區(qū)2014年發(fā)生的小麥白粉病為研究對(duì)象,利用Landsat-8衛(wèi)星OLI和TIRS數(shù)據(jù),提取出對(duì)小麥白粉病病情影響較大的小麥長(zhǎng)勢(shì)因子和田間環(huán)境因子共5項(xiàng),包括歸一化植被指數(shù)(NDVI)、比例植被指數(shù)(RVI)、綠度(GREENNESS)、濕度(WETNESS)和地表溫度(LST),利用最小二乘支持向量機(jī)(LSSVM)對(duì)小麥白粉病進(jìn)行監(jiān)測(cè),并用粒子群優(yōu)化算法(PSO)優(yōu)化模型參數(shù),將監(jiān)測(cè)結(jié)果與傳統(tǒng)最小二乘支持向量機(jī)和支持向量機(jī)(SVM)的監(jiān)測(cè)結(jié)果進(jìn)行對(duì)比分析。結(jié)果表明:經(jīng)過粒子群算法優(yōu)化的最小二乘支持向量機(jī)模型(PSO-LSSVM)的總體監(jiān)測(cè)精度達(dá)到92.8%,優(yōu)于傳統(tǒng)LSSVM的85.7%和SVM的71.4%,取得了較好的監(jiān)測(cè)效果。(2)給出一種基于最小二乘孿生支持向量機(jī)的小麥蚜蟲遙感監(jiān)測(cè)算法。以北京市通州區(qū)和順義區(qū)2010年發(fā)生的小麥蚜蟲為研究對(duì)象,基于環(huán)境與災(zāi)害監(jiān)測(cè)預(yù)報(bào)小衛(wèi)星HJ-CCD和HJ-IRS數(shù)據(jù),在區(qū)域尺度上對(duì)小麥蚜蟲的發(fā)生情況進(jìn)行遙感監(jiān)測(cè)。在小麥蚜蟲發(fā)生的關(guān)鍵生育期(灌漿期),提取對(duì)蚜蟲病情影響較大的小麥長(zhǎng)勢(shì)因子和生境因子。通過獨(dú)立樣本t檢驗(yàn)的方法并結(jié)合地面調(diào)查數(shù)據(jù)對(duì)提取的特征因子進(jìn)行篩選,最終選取置信度達(dá)到0.999水平的特征因子:紅波段反射率、歸一化植被指數(shù)(NDVI)、綠度歸一化植被指數(shù)(GNDVI)、表征土壤水分含量的垂直干旱指數(shù)(PDI)以及表征小麥生長(zhǎng)過程中田間溫度狀況的地表溫度(LST)作為監(jiān)測(cè)模型的輸入變量,最后利用最小二乘孿生支持向量機(jī)建立研究區(qū)域的小麥蚜蟲監(jiān)測(cè)模型,并與傳統(tǒng)支持向量機(jī)、Fisher線性判別分析和LVQ神經(jīng)網(wǎng)絡(luò)模型的監(jiān)測(cè)結(jié)果進(jìn)行對(duì)比。最后的研究結(jié)果表明:最小二乘孿生支持向量機(jī)模型的總體監(jiān)測(cè)精度達(dá)到86.4%,優(yōu)于傳統(tǒng)支持向量機(jī)模型(77.3%)、Fisher線性判別分析模型(77.3%)和LVQ神經(jīng)網(wǎng)絡(luò)模型(72.7%),取得了較好的監(jiān)測(cè)效果。
[Abstract]:China as an agricultural country, crop pest species and wide influence, caused huge losses to China's grain production. The accurate regional scale, timely monitoring the occurrence of pests and diseases to efficiently guide the prevention and control work, the use of remote sensing technology of crop diseases and insect pests on crop diseases and pests information extraction and on a regional scale pest monitoring has become a hot research topic. However, how to select the appropriate approach and maximize the effective information of remote sensing image data is the main problem faced by the researchers. Based on the common diseases of wheat powdery mildew and wheat aphid pest - as the research object, and with wheat powdery mildew wheat aphids on regional scale monitoring as the main line, respectively, using Landsat-8 satellite remote sensing image data and small environment and disaster monitoring The satellite image data to carry out wheat diseases and pests monitoring model and research method, the main research contents and results are as follows: (1) proposed a monitoring algorithm of Wheat Powdery Mildew in particle swarm optimization least squares support vector machine. In 2014 some region of Guanzhong Plain in Shaanxi province wheat powdery mildew as the research object, using Landsat-8 OLI and TIRS satellite data. Extract of wheat powdery mildew disease affecting wheat growth factor and field environment factor of 5, including the normalized difference vegetation index (NDVI), ratio vegetation index (RVI), green (GREENNESS), relative humidity (WETNESS) and surface temperature (LST), using the least squares support vector machine (LSSVM) monitoring of wheat powdery mildew, and by using particle swarm optimization (PSO) algorithm to optimize the parameters of the model, the monitoring results and the traditional least squares support vector machine and support vector machine (SVM) compared with the monitoring results The results show that the least squares analysis. Through particle swarm optimization model of support vector machine (PSO-LSSVM) monitoring the overall accuracy of 92.8%, better than the traditional LSSVM 85.7% and SVM 71.4%, achieved a good monitoring effect. (2) proposed a least squares twin support vector machine algorithm based on remote sensing monitoring of wheat aphids. Beijing City, Tongzhou District and Shunyi District in 2010 occurred in wheat aphids as the research object, the environment and disaster monitoring satellites HJ-CCD and HJ-IRS based on the data of occurrence of wheat aphids in regional scale remote sensing monitoring. In the key growth period of wheat aphids (the filling stage), extraction of large wheat growth factor and environmental factor effect on aphid disease. Through independent sample t test method and combined with the characteristic factor of the ground survey data on the extraction were screened, the final selection of confidence up to 0.999 water Eigenfactor flat: red band reflectance, normalized difference vegetation index (NDVI), green vegetation index (GNDVI), perpendicular drought index to characterize soil moisture content (PDI) and the growth process of wheat field temperature characterization of land surface temperature (LST) measurement model as input variables of supervision, the monitoring of wheat aphids the establishment of regional model of least squares twin support vector machine, and the traditional support vector machine, comparative analysis of monitoring results and LVQ neural network model Fisher linear discriminant. The final results show that: the overall precision of least squares twin support vector machine model reached 86.4%, better than the traditional support vector machine (77.3%), Fisher linear model (77.3%) the discriminant analysis model and LVQ neural network model (72.7%), good monitoring effect was obtained.

【學(xué)位授予單位】：安徽大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：S435.12;S127;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馬慧琴;黃文江;景元書;;遙感與氣象數(shù)據(jù)結(jié)合預(yù)測(cè)小麥灌漿期白粉病[J];農(nóng)業(yè)工程學(xué)報(bào);2016年09期

2 聶臣巍;袁琳;王保通;金秀良;黃文江;張競(jìng)成;楊貴軍;;綜合遙感與氣象信息的小麥白粉病監(jiān)測(cè)方法[J];植物病理學(xué)報(bào);2016年02期

3 祝佳;;Landsat8衛(wèi)星遙感數(shù)據(jù)預(yù)處理方法[J];國(guó)土資源遙感;2016年02期

4 唐翠翠;黃文江;羅菊花;梁棟;趙晉陵;黃林生;;基于相關(guān)向量機(jī)的冬小麥蚜蟲遙感預(yù)測(cè)[J];農(nóng)業(yè)工程學(xué)報(bào);2015年06期

5 徐涵秋;;新型Landsat8衛(wèi)星影像的反射率和地表溫度反演[J];地球物理學(xué)報(bào);2015年03期

6 謝巧云;黃文江;梁棟;彭代亮;黃林生;宋曉宇;張東彥;楊貴軍;;最小二乘支持向量機(jī)方法對(duì)冬小麥葉面積指數(shù)反演的普適性研究[J];光譜學(xué)與光譜分析;2014年02期

7 李旭文;牛志春;姜晟;金焰;彭露露;;Landsat8衛(wèi)星OLI遙感影像在生態(tài)環(huán)境監(jiān)測(cè)中的應(yīng)用研究[J];環(huán)境監(jiān)控與預(yù)警;2013年06期

8 袁琳;張競(jìng)成;趙晉陵;黃文江;王紀(jì)華;;基于葉片光譜分析的小麥白粉病與條銹病區(qū)分及病情反演研究[J];光譜學(xué)與光譜分析;2013年06期

9 馮偉;王曉宇;宋曉;賀利;王永華;郭天財(cái);;基于冠層反射光譜的小麥白粉病嚴(yán)重度估測(cè)[J];作物學(xué)報(bào);2013年08期

10 張玉君;;Landsat8簡(jiǎn)介[J];國(guó)土資源遙感;2013年01期

，

本文編號(hào)：1368534