本文選題：油菜菌核病 + 光譜技術(shù)��； 參考：《浙江大學》2017年碩士論文

【摘要】：油菜是我國最為主要的油料作物之一,但其產(chǎn)量和品質(zhì)往往因病害而出現(xiàn)大幅下降。因此,實現(xiàn)快速有效地病害檢測并制定合理的防治措施,對保障油菜的產(chǎn)量和品質(zhì)具有重要意義。傳統(tǒng)的病害檢測方法通常局限于實驗室環(huán)境下的微觀尺度檢測,不僅流程繁瑣、滯后性較強,同時會令研究樣本遭到破壞,很難滿足現(xiàn)代農(nóng)業(yè)對精準生產(chǎn)的要求。為克服傳統(tǒng)方法所存在缺陷,本研究以油菜作為研究對象,利用搭載高光譜成像儀和熱紅外成像儀的無人機模擬平臺,分別從冠層尺度和葉片尺度對健康及染病的油菜樣本實現(xiàn)了判別分析。主要研究內(nèi)容如下:(1)從冠層尺度獲取高光譜圖像數(shù)據(jù),對健康和染病油菜樣本進行了檢測研究。分別采用移動平均法(MAS)、多項式卷積平滑法(SG)、標準正態(tài)變量變換(SNV)、多元散射校正(MSC)及去趨勢化法(De-trending)對獲取到的冠層高光譜數(shù)據(jù)進行預處理,得到圖像中整株樣本的光譜反射值。其后,分別基于全波段和特征波長建立偏最小二乘法(PLS-DA)、支持向量機(SVM)、極限學習機(ELM)、K-近鄰分類算法(KNN)模型,進行健康和染病樣本的判別分析。在基于全波段信息的分析中,不同預處理方法和建模方法組合性能差異明顯,其中采用MSC預處理結(jié)合ELM建模方法得到的分類效果最優(yōu),建模集和預測集的結(jié)果達到100%。然后,分別采用連續(xù)投影算法(SPA)、二階導數(shù)(2ndDer)及遺傳算法-偏最小二乘法(GA-PLS)進行特征波長提取,并利用提取的特征波長建立PLS-DA、SVM、ELM及KNN模型進行分析。結(jié)果顯示基于SPA所選取特征波長結(jié)合ELM模型得到的分類效果最優(yōu),建模集和預測集的結(jié)果都達到100%。(2)基于光譜數(shù)據(jù)計算油菜植被指數(shù),通過相關(guān)性分析和單因素方差分析獲取優(yōu)選植被指數(shù),并分別基于單一及組合優(yōu)選后的植被指數(shù)對健康和染病樣本進行建模判別分析。結(jié)果顯示,優(yōu)選得到的DVI、TVI、RVSI、RDVI、CARI及OSAVI等指數(shù)與油菜健康與染病狀態(tài)相關(guān)性較好,可對其進一步建模分析。針對單一和組合優(yōu)選植被指數(shù)的判別結(jié)果顯示,組合建模條件下的分類效果優(yōu)于單一植被指數(shù)。(3)從葉片尺度獲取高光譜圖像數(shù)據(jù),對健康和染病油菜樣本進行檢測研究。分別采用MAS、SG、MSC、Detrending及SNV對獲取到的葉片高光譜數(shù)據(jù)進行預處理,得到葉片病斑區(qū)域的光譜反射值。其后,分別基于全波段和特征波長信息建立PLS-DA、SVM、ELM、KNN模型,進行健康和染病樣本的判別分析。在基于全波段信息的分析中,其中采用MSC預處理結(jié)合ELM建模方法得到的分類效果最優(yōu),建模集和預測集的結(jié)果達到100%。進一步地,在基于特征波長的分析中,分別采用SPA、2ndDer及GA-PLS進行特征波長提取,并利用提取的特征波長建立PLS-DA、SVM、ELM及KNN模型進行分析。結(jié)果顯示基于SPA方法所選取特征波長結(jié)合ELM模型得到的分類效果最優(yōu),建模集和預測集的結(jié)果達到100%。(4)從冠層尺度獲取熱紅外圖像數(shù)據(jù),對健康和染病油菜樣本進行早期的識別診斷。提取樣本冠層尺度的溫度值,并對其進行生理指數(shù)的監(jiān)測。然后利用平均溫度和最大溫差區(qū)分健康和染病油菜,并進行單因素方差分析。結(jié)果表明,健康和染病油菜的最大溫差差異明顯,且隨著天數(shù)的變化該差值基本保持不變;健康和染病植株的平均溫度差值起初無明顯變化,但隨著天數(shù)的變化差值逐漸增大。其單因素方差分析表明,最大溫差在油菜染病后第1天即存在顯著性差異(P0.01)。進一步地,分析油菜生理指數(shù)(氣孔導度、光合速率、二氧化碳濃度及蒸騰速率)隨染病程度的加重發(fā)生的變化,該變化可以直觀檢測出菌核病對油菜的染病程度,且發(fā)現(xiàn)健康油菜的生理指數(shù)高于比染病油菜,并對生理指數(shù)與溫度進行相關(guān)性分析。結(jié)果顯示,光合速率、二氧化碳濃度與蒸騰速率與溫度之間存在顯著相關(guān)性。(5)針對葉片尺度的熱紅外數(shù)據(jù)對健康和染病油菜樣本進行早期的識別診斷。獲取樣本中染病葉片健康區(qū)域和病斑區(qū)域的溫度信息。其中熱紅外圖像可以直觀的識別出病害侵染過程,并利用像素點的值來判別健康和染病區(qū)域的溫度差異。采用溫度信息中的最大溫度、最小溫度、平均溫度以及最大溫差對健康和染病油菜植株進行識別,根據(jù)以上溫度信息區(qū)分染病葉片的健康與染病區(qū)域,并對其進行單因素方差分析。結(jié)果表明,健康和染病區(qū)域的最大溫度、最小溫度、最大溫差以及平均溫度都存在較明顯的差異,且病斑區(qū)域溫度高于健康區(qū)域。其單因素方差分析表明,最大溫差在第1天即存在顯著性差異(P0.01),可以實現(xiàn)對油菜菌核病的早期診斷識別。
[Abstract]:Rapeseed is one of the most important oil crops in our country, but its yield and quality tend to decrease greatly because of disease. Therefore, it is of great significance to realize rapid and effective disease detection and make reasonable control measures to ensure the yield and quality of rapeseed. The traditional detection method of disease is usually limited to the microcosmic environment. In order to overcome the defects of the traditional methods, this study takes the rapeseed as the research object and uses the UAV simulation platform carrying hyperspectral imager and thermal infrared imager, respectively, from the canopy layer. The scale and leaf scale were used to discriminate the healthy and infected rapeseed samples. The main contents are as follows: (1) obtaining hyperspectral image data from the canopy scale, detecting healthy and infected rapeseed samples, using mobile averaging (MAS), polynomial convolution smoothing (SG), standard normal variable transformation (SNV), and multivariate analysis. The scattering correction (MSC) and detrending method (De-trending) preprocess the obtained canopy hyperspectral data and get the spectral reflectance of the whole plant samples. Subsequently, partial least squares (PLS-DA), support vector machine (SVM), ELM, and K- nearest neighbor classification algorithm (KNN) model are based on the full band and characteristic wavelengths respectively. Discriminant analysis of healthy and infected samples. In the analysis based on all band information, different preprocessing methods and modeling methods have obvious differences in performance, in which MSC preprocessing combined with ELM modeling method has the best classification effect, and the results of modeling set and prediction set reach 100%., and the continuous projection algorithm (SPA) is used respectively, two The order derivative (2ndDer) and genetic algorithm partial least squares (GA-PLS) are used to extract characteristic wavelengths, and the extracted characteristic wavelengths are used to establish PLS-DA, SVM, ELM and KNN models. The results show that the classification results based on the characteristic wavelengths selected based on SPA and ELM model are the best, and the results of the modeling set and the prediction set are all based on the 100%. (2) based on the model wavelengths. The optimum vegetation index was obtained by correlation analysis and single factor analysis of variance. The results showed that the selected indexes of DVI, TVI, RVSI, RDVI, CARI and OSAVI, and the health and dyeing of rape were obtained. The correlation of the disease status was better, and it could be further modeled and analyzed. According to the discriminant results of the single and combination optimization of the vegetation index, the classification results under the combined modeling condition were better than the single vegetation index. (3) the data of hyperspectral images were obtained from the blade scale, and the samples of healthy and infected oil and vegetables were detected. MAS, SG, MSC, Det were used respectively. Rending and SNV preprocessed the acquired hyperspectral data, and obtained spectral reflectance of the leaf spot area. Then, based on the whole band and characteristic wavelength information, PLS-DA, SVM, ELM, KNN models were established for discriminant analysis of healthy and infected samples. In the analysis based on all band information, MSC preprocessing combined with E. The LM modeling method has the best classification effect, and the results of modeling set and prediction set reach 100%. further. In the analysis of characteristic wavelengths, feature wavelengths are extracted with SPA, 2ndDer and GA-PLS respectively, and the extracted characteristic wavelengths are used to establish PLS-DA, SVM, ELM and KNN models. The results show that the SPA method is selected. The feature wavelength combined with the ELM model is the best. The results of the modeling set and the prediction set reach 100%. (4) to obtain the thermal infrared image data from the canopy scale, the early identification and diagnosis of the healthy and infected rape samples. The temperature values of the sample canopy scale are extracted and the physiological index is monitored. Then the average temperature is used. The difference of the maximum temperature difference between healthy and infected rapeseed was obvious, and the difference of the average temperature between healthy and infected plants remained unchanged, but the difference of average temperature between healthy and infected plants had no obvious change at first, but the difference increased with the change of days. The single factor analysis of variance showed that the maximum temperature difference was significantly different in first days after rape (P0.01). Further, the changes of the physiological index of rape (stomatal conductance, photosynthetic rate, carbon dioxide concentration and transpiration rate) were changed with the aggravation of the disease degree, which can directly detect the degree of disease of sclerotia to rape. The physiological index of healthy rapeseed was higher than that of infected rapeseed, and the correlation between physiological index and temperature was analyzed. The results showed that there was a significant correlation between photosynthesis rate, carbon dioxide concentration and transpiration rate and temperature. (5) early identification and diagnosis of healthy and infected rapeseed samples by thermal infrared data of leaf scale. The temperature information of the healthy area and the spot area of the infected leaves is obtained. The thermal infrared image can identify the infection process of the disease intuitively, and use the value of the pixels to distinguish the temperature difference between the healthy and the infected areas. The results showed that the maximum temperature, the minimum temperature, the maximum temperature difference and the average temperature were significantly different between the healthy and infected areas, and the temperature of the spot area was higher than that of the healthy area. The single factor ANOVA analysis showed that the maximum temperature difference had significant difference on the first day (P0.01), which could realize the early diagnosis and identification of Sclerotinia sclerotiorum.
【學位授予單位】：浙江大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：S435.654;S127

【相似文獻】

相關(guān)期刊論文 前10條

1 張立良,沈維冰,劉成社,任翠龍;油菜菌核病發(fā)生、危害與氣象因子的關(guān)系[J];安徽農(nóng)業(yè)科學;2000年06期

2 孫玉平;油菜菌核病的有效防治途徑[J];安徽農(nóng)業(yè);2000年08期

3 王中銀,姜春史,顧衛(wèi)忠;油菜菌核病發(fā)生特點及防治技術(shù)[J];湖北植保;2000年03期

4 石虹;油菜菌核病的發(fā)生及防治對策[J];河南農(nóng)業(yè);2000年03期

5 王健,張宏軍;“寧雜1號”油菜菌核病防治初報[J];上海農(nóng)業(yè)科技;2000年02期

6 ;使百克防治油菜菌核病[J];新農(nóng)業(yè);2000年12期

7 張信揚,彭連英;油菜菌核病發(fā)生規(guī)律研究[J];云南農(nóng)業(yè)大學學報;2000年03期

8 蔣耀培,王志通,林美新,顧寶根;上海地區(qū)油菜菌核病發(fā)生與品種、氣象等因素關(guān)系淺析[J];植保技術(shù)與推廣;2000年02期

9 王建強;使百克防治油菜菌核病效果好[J];植保技術(shù)與推廣;2000年02期

10 謝長文;油菜菌核病發(fā)生規(guī)律及春后防治方法[J];農(nóng)村經(jīng)濟與科技;2000年01期

相關(guān)會議論文 前10條

1 丁顏敏;姜小潔;劉天波;姜道宏;李國慶;黃俊斌;;油菜菌核病的發(fā)生規(guī)律與盾殼霉防治技術(shù)研究[A];中國植物病理學會2009年學術(shù)年會論文集[C];2009年

2 劉天波;覃黎;丁顏敏;姜道宏;李國慶;黃俊斌;;油菜菌核病早期診斷技術(shù)應用研究[A];中國植物病理學會2009年學術(shù)年會論文集[C];2009年

3 楊丹;呂博;姜道宏;李國慶;黃俊斌;;湖北省油菜菌核病菌株多樣性的初步研究[A];中國植物病理學會2009年學術(shù)年會論文集[C];2009年

4 孫祥良;王華弟;;油菜菌核病的發(fā)生傳播途徑與防治技術(shù)探討[A];中國植物病理學會2010年學術(shù)年會論文集[C];2010年

5 王華弟;孫祥良;朱黎明;;油菜菌核病發(fā)生與流行預測的研究[A];中國植物病理學會2010年學術(shù)年會論文集[C];2010年

6 吳春英;王海青;;油菜菌核病防治技術(shù)研究[A];江蘇省植物病理學會第九屆會員代表大會暨學術(shù)研討會論文集[C];1999年

7 張信揚;彭連英;;油菜菌核病發(fā)生規(guī)律研究[A];中國植病學會西南聯(lián)合學術(shù)年會論文集[C];2000年

8 任莉;方小平;陳坤榮;羅莉霞;;幾種藥劑防治油菜菌核病的潛力研究[A];中國植物病理學會2009年學術(shù)年會論文集[C];2009年

9 張夕林;張治;張建明;張谷豐;孫雪梅;;多菌靈防治油菜菌核病藥效下降原因及綜防對策[A];“植物保護21世紀展望”——植物保護21世紀展望暨第三屆全國青年植物保護科技工作者學術(shù)研討會文集[C];1998年

10 張少林;張谷豐;孫雪梅;羅蘿;嚴雪芳;;油菜菌核病抗藥性監(jiān)測與綜合治理研究初報[A];全國安全用藥技術(shù)研討會論文集[C];2001年

相關(guān)重要報紙文章 前10條

1 通訊員 李森林;濱海依托網(wǎng)絡 加強油菜菌核病防治[N];江蘇科技報;2007年

2 本報記者 于丹;油菜菌核病偏重發(fā)生[N];江蘇農(nóng)業(yè)科技報;2007年

3 記者 張愛虎邋周振富;專家支招防治油菜菌核病[N];湖北日報;2008年

4 記者 饒洪斌邋通訊員 洪海林;著力防控油菜菌核病[N];咸寧日報;2008年

5 記者 高琳;未來十天油菜菌核病可能偏重[N];中國氣象報;2013年

6 江華;油菜菌核病[N];農(nóng)資導報;2013年

7 黃耀新 科卞;當前如何防治油菜菌核病[N];江蘇科技報;2003年

8 張夕林;加強油菜菌核病防治[N];江蘇農(nóng)業(yè)科技報;2002年

9 本報記者　方秀;油菜菌核病防治三招[N];安徽日報;2006年

10 侯佐 侯銀娟;快防治油菜菌核病[N];寶雞日報;2006年

相關(guān)博士學位論文 前3條

1 鐘軍;蕓芥抗油菜菌核病分子基礎的研究[D];湖南農(nóng)業(yè)大學;2003年

2 高小寧;植物內(nèi)生細菌菌株Em7對油菜菌核病的防治研究[D];西北農(nóng)林科技大學;2012年

3 江木蘭;油菜內(nèi)生枯草芽孢桿菌BY-2的定殖生態(tài)、抗菌機制和防治菌核病的研究[D];華中農(nóng)業(yè)大學;2007年

相關(guān)碩士學位論文 前10條

1 王良吉;防治油菜菌核病的有效藥劑篩選及復配研究[D];安徽農(nóng)業(yè)大學;2014年

2 徐杰;苦膽鏈霉菌YJ1活性代謝產(chǎn)物的分離純化及其粗提物對油菜菌核病的生物防治[D];四川農(nóng)業(yè)大學;2015年

3 程光龍;苦膽鏈霉菌Streptomyces felleus的誘變選育及其對油菜菌核病的生物防治[D];四川農(nóng)業(yè)大學;2014年

4 徐從英;苯噻菌酯生物活性及防治油菜菌核病的應用研究[D];南京農(nóng)業(yè)大學;2015年

5 游景茂;芽孢桿菌WJ-1的鑒定及其對水稻紋枯病和油菜菌核病的防治研究[D];華中農(nóng)業(yè)大學;2010年

6 陳欣欣;基于低空遙感成像技術(shù)的油菜菌核病檢測研究[D];浙江大學;2017年

7 左葉信;陜西省油菜菌核病發(fā)生規(guī)律及菌核病菌對多菌靈抗藥性研究[D];西北農(nóng)林科技大學;2010年

8 孫光明;基于光譜和多光譜圖像技術(shù)的油菜菌核病識別[D];浙江大學;2010年

9 陳士華;寒地春油菜菌核病流行分析與監(jiān)測防御體系[D];福建農(nóng)林大學;2004年

10 李玉芳;油菜菌核病致病過程中酶活性及草酸含量變化的研究[D];湖南農(nóng)業(yè)大學;2007年

，

本文編號：2030745