基于近红外光谱技术的水稻叶部病害诊断模型构建
摘要
本文主要研究了利用光谱数据诊断水稻胡麻斑病和水稻纹枯病叶片的理论和方法,通过对多种算法的比较分析研究,找出了最优的光谱预处理和分析算法,并建立了最优的病害严重度诊断模型和识别模型。为今后通过航空航天遥感平台大面积监测水稻胡麻斑病和水稻纹枯病提供了依据,也可以为水稻其他病害的遥感监测提供借鉴和参考。
本文的研究对象是自然条件下发病的水稻叶片,主要流程如下:
光谱数据采集阶段,比较了运用内置光源的反射探头和裸光纤测量水稻叶片光谱信息的优劣;通过比较不同宽度水稻叶片对光谱反射率的影响,发现宽度的变化对近红外区域水稻叶片光谱反射率影响较大;同时提出了水稻病害叶片光谱数据采集的注意事项,对进入预处理阶段的光谱进行了筛选,最后获取101个水稻病害叶片样本用于论文研究。
光谱数据预处理阶段,针对光谱数据存在噪声和散射的问题,主要研究了S-G平滑、kernel平滑、导数算法、多元散射校正等预处理算法。结果表明,平滑点数和多项式阶数需根据实际进行调整;kernel平滑比S-G平滑算法更优,但是处理速度较慢;光谱信息的一阶导数较二阶导数对噪声敏感度低,且能得出重要的光谱参数;多元散射校正能很好的消除基线的平移和偏移。
水稻病害光谱特征分析阶段,对水稻病害叶片光谱信息对比发现:在400～700nm范围内,随着胡麻斑病和纹枯病病害等级的增加反射率逐渐增高,纹枯病较胡麻斑病光谱反射率增高速度迅速;在700~1300 nm近红外区域,水稻胡麻斑病和纹枯病叶片反射率随病害等级的增加而逐渐降低;在1900nm~2000nm范围内,水稻纹枯病叶反射率随等级增加逐渐增高,而水稻胡麻斑病叶片反射率随等级增加而降低;而其他波段无明显规律。
特征提取阶段,针对近红外光谱的数据量大、波段众多的问题,先根据严重度与反射率的相关性数据,选取了水稻胡麻斑和纹枯病的敏感波段,再运用主成分分析的算法,选取累积贡献率达到85%以上的前2个分量,最终选取990nm、1850nm、660nm、1921nm、1933nm这5个主要的特征波段用于建模;原始光谱反射率经一阶导数处理后,选取与严重度相关性最好的红边面积作为区分健康与生病叶片的重要参数。
模型建立阶段,通过对得到的5个特征波段和红边面积参数分别建立水稻胡麻斑和纹枯病的严重度诊断模型,通过模型验证表明以下模型精度最高:(1)胡麻斑入选的组合反射率R1933nm- R990nm建立的模型y=11.4971x+5.0313, r=0.8912;(2)纹枯病入选的红边面积和组合反射率R660nm- R990nm建立的模型y=-11.1037x+3.5195,r=0.89502;y=6.2834x+2.8464,r=0.8920;运用逐步回归法和BP神经网络方法对水稻胡麻斑和纹枯病进行识别,其中60个样本用于建模,41个样本用于模型检验,结果表明,与逐步回归分析相比较,当对660nm、990nm、1933nm三个特征波段进行组合识别时,BP神经网络识别准确率比逐步回归分析的准确率高。
This paper studies the spectral data of rice flax leaf spot and sheath blight disease; find the optimal spectral pre-processing and analysis algorithms; and established the optimal diagnostic model and severity identify model; to provide theoretic foundation for further monitoring rice flax leaf spot and sheath blight disease at large scale using airborne and airspace remote sensing as flats and reference for monitoring rice other disease. In this study the works were completed as follows:
Spectral data acquisition stage, the influence of external environment, machine and sample to study fully considers for the spectral reflectance; use tools of blade grippers and naked fiber optic to measure rice leaf spectra data, and find which tool have the better result; find the change on the width of near infrared spectral reflectance have a big affect on rice leaf; also puts forward the matters needing attention when collect rice disease spectrum data, choose spectrum data for pre-processing stage.
Spectral data pretreatment stage, for the problem of spectra data have noise and scattering, this pepar studied the S-G smoothing, kernel smoothing, derivative algorithm, multiplicative scatter correction of the data pre-preprocessing algorithm, and compared the results of preprocessing algorithms, and ultimately to find suitable preprocessing algorithm of rice diseases.
Rice disease spectrum characteristic analysis stage, compared and analyzed rice leaves of normal and have difference disease which have the same width and variety, we found that: In the range of 400 ~ 700nm, with the level of flax leaf spot disease and the sheath blight disease was gradually increased to increase reflectivity, the increased speed are more rapid than flax spot; In the range of 700 ~ 1300 nm near-infrared region, with the level of flax spot disease and the sheath blight disease increase leaf reflectance gradually decreased; In the range of 1900nm ~ 2000nm, with the level of the sheath blight disease increase the leaf reflectance gradually increase, while the other band no law.
Feature extraction stage, for the problems of near infrared spectrum have large amount of data and band numerous, according to the correlation of severity and reflectivity data, select rice sensitive band of the spot and sheath blight, then using principal component analysis algorithm select two component which accumulated more than 85 percent contribution; finally select five main features bands used for modeling: 990nm, 1850nm, 660nm,1921nm, 1933nm; after the original spectral reflectance process with the first derivative, select the best correlation with the severity of red edge area as a health and sick leaves important parameter.
Model establishment stage, rice spot and sheath blight disease severity diagnosis model were established through 5 obtained the characteristic bands and the red edge parameters. Through the model validation showed that the following model has the highest: (1) rice spot, R1933nm- R990nm, y=11.4971x+5.0313, r=0.8912;(2) sheath blight, red edge area parameters and R660nm-R990nm, y=-11.1037x+3.5195,r=0.89502;y=6.2834x+2.8464, r=0.8920;use stepwise regression method and the BP neural network method to Identify the rice spot and sheath blight disease, including 60 samples used for modeling, 41 samples used to model test, the results show that compared to stepwise regression analysis, when 660nm, 990nm, 1933nm three features bands combined, the BP neural network identification accuracy than stepwise regression analysis.
本文的研究对象是自然条件下发病的水稻叶片,主要流程如下:
光谱数据采集阶段,比较了运用内置光源的反射探头和裸光纤测量水稻叶片光谱信息的优劣;通过比较不同宽度水稻叶片对光谱反射率的影响,发现宽度的变化对近红外区域水稻叶片光谱反射率影响较大;同时提出了水稻病害叶片光谱数据采集的注意事项,对进入预处理阶段的光谱进行了筛选,最后获取101个水稻病害叶片样本用于论文研究。
光谱数据预处理阶段,针对光谱数据存在噪声和散射的问题,主要研究了S-G平滑、kernel平滑、导数算法、多元散射校正等预处理算法。结果表明,平滑点数和多项式阶数需根据实际进行调整;kernel平滑比S-G平滑算法更优,但是处理速度较慢;光谱信息的一阶导数较二阶导数对噪声敏感度低,且能得出重要的光谱参数;多元散射校正能很好的消除基线的平移和偏移。
水稻病害光谱特征分析阶段,对水稻病害叶片光谱信息对比发现:在400～700nm范围内,随着胡麻斑病和纹枯病病害等级的增加反射率逐渐增高,纹枯病较胡麻斑病光谱反射率增高速度迅速;在700~1300 nm近红外区域,水稻胡麻斑病和纹枯病叶片反射率随病害等级的增加而逐渐降低;在1900nm~2000nm范围内,水稻纹枯病叶反射率随等级增加逐渐增高,而水稻胡麻斑病叶片反射率随等级增加而降低;而其他波段无明显规律。
特征提取阶段,针对近红外光谱的数据量大、波段众多的问题,先根据严重度与反射率的相关性数据,选取了水稻胡麻斑和纹枯病的敏感波段,再运用主成分分析的算法,选取累积贡献率达到85%以上的前2个分量,最终选取990nm、1850nm、660nm、1921nm、1933nm这5个主要的特征波段用于建模;原始光谱反射率经一阶导数处理后,选取与严重度相关性最好的红边面积作为区分健康与生病叶片的重要参数。
模型建立阶段,通过对得到的5个特征波段和红边面积参数分别建立水稻胡麻斑和纹枯病的严重度诊断模型,通过模型验证表明以下模型精度最高:(1)胡麻斑入选的组合反射率R1933nm- R990nm建立的模型y=11.4971x+5.0313, r=0.8912;(2)纹枯病入选的红边面积和组合反射率R660nm- R990nm建立的模型y=-11.1037x+3.5195,r=0.89502;y=6.2834x+2.8464,r=0.8920;运用逐步回归法和BP神经网络方法对水稻胡麻斑和纹枯病进行识别,其中60个样本用于建模,41个样本用于模型检验,结果表明,与逐步回归分析相比较,当对660nm、990nm、1933nm三个特征波段进行组合识别时,BP神经网络识别准确率比逐步回归分析的准确率高。
This paper studies the spectral data of rice flax leaf spot and sheath blight disease; find the optimal spectral pre-processing and analysis algorithms; and established the optimal diagnostic model and severity identify model; to provide theoretic foundation for further monitoring rice flax leaf spot and sheath blight disease at large scale using airborne and airspace remote sensing as flats and reference for monitoring rice other disease. In this study the works were completed as follows:
Spectral data acquisition stage, the influence of external environment, machine and sample to study fully considers for the spectral reflectance; use tools of blade grippers and naked fiber optic to measure rice leaf spectra data, and find which tool have the better result; find the change on the width of near infrared spectral reflectance have a big affect on rice leaf; also puts forward the matters needing attention when collect rice disease spectrum data, choose spectrum data for pre-processing stage.
Spectral data pretreatment stage, for the problem of spectra data have noise and scattering, this pepar studied the S-G smoothing, kernel smoothing, derivative algorithm, multiplicative scatter correction of the data pre-preprocessing algorithm, and compared the results of preprocessing algorithms, and ultimately to find suitable preprocessing algorithm of rice diseases.
Rice disease spectrum characteristic analysis stage, compared and analyzed rice leaves of normal and have difference disease which have the same width and variety, we found that: In the range of 400 ~ 700nm, with the level of flax leaf spot disease and the sheath blight disease was gradually increased to increase reflectivity, the increased speed are more rapid than flax spot; In the range of 700 ~ 1300 nm near-infrared region, with the level of flax spot disease and the sheath blight disease increase leaf reflectance gradually decreased; In the range of 1900nm ~ 2000nm, with the level of the sheath blight disease increase the leaf reflectance gradually increase, while the other band no law.
Feature extraction stage, for the problems of near infrared spectrum have large amount of data and band numerous, according to the correlation of severity and reflectivity data, select rice sensitive band of the spot and sheath blight, then using principal component analysis algorithm select two component which accumulated more than 85 percent contribution; finally select five main features bands used for modeling: 990nm, 1850nm, 660nm,1921nm, 1933nm; after the original spectral reflectance process with the first derivative, select the best correlation with the severity of red edge area as a health and sick leaves important parameter.
Model establishment stage, rice spot and sheath blight disease severity diagnosis model were established through 5 obtained the characteristic bands and the red edge parameters. Through the model validation showed that the following model has the highest: (1) rice spot, R1933nm- R990nm, y=11.4971x+5.0313, r=0.8912;(2) sheath blight, red edge area parameters and R660nm-R990nm, y=-11.1037x+3.5195,r=0.89502;y=6.2834x+2.8464, r=0.8920;use stepwise regression method and the BP neural network method to Identify the rice spot and sheath blight disease, including 60 samples used for modeling, 41 samples used to model test, the results show that compared to stepwise regression analysis, when 660nm, 990nm, 1933nm three features bands combined, the BP neural network identification accuracy than stepwise regression analysis.
引文
1.安虎,王海光,刘荣英,蔡成静,马占鸿.小麦条锈病单片病叶特征光谱的初步研究.中国植保导刊. 2005,11:8-11.
2.陈兵,李少昆,王克如,柏军华,隋学艳,白彩云.作物病虫害遥感监测研究进展.棉花学报. 2007,19(1):57-63.
3.陈兵,王克如,李少昆,肖春华,王静,王方勇,潘文超,王娜.棉花黄萎病冠层高光谱遥感监测技术研究.新疆农业科学.2007,44(6):740-745.
4.陈鹏程.地面高光谱遥感在棉叶螨监测中的应用研究[硕士学位论文].新疆:石河子大学,2006.
5.单潮龙等,BP人工神经网络的应用及其实现技术.海军工程大学学报, 2000,第四期
6.东华理工大学,长江学院.植被遥感. 2011-4-15取自http://wenku.baidu.com/view/f8cbe1886529647d272852c7.html
7.方慧,宋海燕,曹芳,何勇,裘正军.油菜叶片的光谱特征与叶绿素含量之间的关系研究.光谱学与光谱分析. 2007,09:1721-1734.
8.飞思科技产品研发中心,神经网络理论与MATLAB7实现.电子工业出版社, 2005:32-50.
9.冯洁,廖宁放,赵波,罗永道,李宝聚,戴志福.多光谱成像技术诊断植物病虫害的人工神经网络模型.光学技术.2008.9,34(5).
10.冯世杰,戴小鹏,王艳平.基于NIR-SVM对鸭梨褐变病果的识别.农业网络信息.2008,(3):133-135.
11.何霭如,郭建夫.水稻纹枯病的发生及防治.安徽农业科学2007,35(4):996-997.
12.何国金等.北京麦蚜虫害的光谱测量与分析.遥感技术与应用. 2006,3(17):119-124.
13.何绍桓,王福荣,赵顺赫,宋世春.塑料大棚培育水稻壮苗主要技术的研究.吉林农业大学学报. 1982, 4:68-72.
14.黄木易,黄文江,刘良云,黄义德,王纪华,赵春江,万安民.冬小麦条锈病单叶光谱特性及严重度反演.农业工程学报. 2004,1,20(1):176-180.
15.蒋金豹,陈云浩,黄文江,李京.冬小麦条锈病严重度高光谱遥感反演模型研究.南京农业大学学报.2007,30(3):63-67.
16.蒋金豹,陈云浩,黄文江.利用高光谱微分指数进行冬小麦条锈病病情的诊断研究.光学技术. 2007,7,33(4).
17.蒋金豹,陈云浩,黄文江.利用高光谱红边与黄边位置距离识别小麦条锈病.光谱学与光谱分析.2010,6(30):1614-1618.
18.李波,刘占宇,黄敬峰,张莉丽,周湾,石晶晶.基于PCA和PNN的水稻病虫害高光谱识别.农业工程学报. 2009, 9 25(9):143-147.
19.李广华,张爱民,张杭,吴炎. Savitzky-golay滤子在短路器在线检测处理中的应用.高压电器. 2005,6,41(3):225-227.
20.李培生,胡松,孙路石,孙学信.基于SG算法的燃煤微分热重曲线平滑去噪.华中科技大学学报(自然科学版). 2005,7,33(7):61-64.
21.刘立波,周国民.基于多层感知神经网络的水稻叶瘟病识别方法.农业工程学报(增刊). 2009年,25(10):213-217.
22.刘立波,周国民.人眼视觉特性在植物叶片图像提取中的应用.计算机工程与应用2009,45(19): 22-25.
23.刘伟东,项月琴,郑兰芬,童庆禧,吴长山.高光谱数据与水稻叶面积指数及叶绿素密度的相关分析.遥感学报. 2000,4(4):279-283.
24.刘兴库,李兆华.多光谱诊断植物病害的初步研究.东北林业大学学报.1993.3,21(2):106-110.
25.刘旭华,徐兴忠,何雄奎,张录达.有监督主成分回归法在近红外光谱定量分析中的应用研究.光谱学与光谱分析.2009,12,29(11): 2959-2961.
26.龙伟等.人工神经网络发展前景.机械,1998,第25卷第1期
27.芦永军,曲艳玲,宋敏.近红外相关光谱的多元散射校正处理研究.光谱学与光谱分析.2007,5,27(5):877-880.
28.孟德超,纪明山.辽宁地区水稻纹枯病拮抗细菌的分离和筛选.河南农业科学. 2009,04: 79-81.
29.农作物病害综合防治.农民致富之友.2000.8.
30.区靖祥,邱健德.多元数据的统计分析方法.北京:中国农业科学技术出版社, 2002:63-75.
31.石吉勇,邹小波,赵杰文,殷晓平.基于小波滤噪和ipls的草莓近红外光谱糖度检测模型.安徽农业科学.2009,37(12):5752-5754.
32.水稻病虫害. 2009-04-16取自中国种子拍卖网http://www.zzpmw.cn/Zinfo/Daolei/Bingc/20080416/160137.shtml
33.水稻病虫害.2011-4-15取自广西植物保护网http://www.gxzb.com/html/2009-4/20092009429163245698.html
34.水稻纹枯病. 2010-09-25取自百度百科http://baike.baidu.com/view/363661.htm
35.穗波信雄.根据图像提取农作物的生长信息.农业机械学会关西支部第6次支部研究资料.1989.10:1-12.
36.谭广发.水稻病害防治技术.植物保护. 2004, 170(4): 22-23.
37.檀根甲,李辉.水稻纹枯病不同分级标准病情指数间的关系.安徽农业大学学报. 1993, 20(3): 228-233.
38.唐延林,王人潮,王秀珍.对水稻微分光谱和植被指数的探讨.上海交通大学学报(农业科学版). 2003,21(3):199-204.
39.田庆久.高光谱遥感环境污染监测研究进展ppt.
40.田永超,杨杰,姚霞,朱艳,曹卫星.水稻高光谱红边位置与叶层氮浓度的关系.作物学报.2009,35(9):1681?1690.
41.万余庆,谭克龙,周日平.高光谱遥感应用研究.北京:科学出版社,2006:133-171.
42.王秀珍,王人潮,黄敬峰.微分光谱遥感及其在水稻农学参数测定上的应用研究.农业工程学报. 2002,18(1): 9-13.
43.王艳青.近年来中国水稻病虫害发生及趋势分析.中国农学通报. 2006, 22(2): 343-347.
44.吴曙雯,王人潮,陈晓斌,沈掌泉,史舟.稻叶瘟对水稻光谱特性的影响研究.上海交通大学学报(农业科学版).2002.3,20(1):73-76,84.
45.细菌性病害. 2006-12-29.取自百度百科http://baike.baidu.com/view/689853.htm
46.熊宇虹,温志渝,王命延,徐少平,王炜立,肖建.基于神经网络的光谱识别系统的设计与分析.光谱学与光谱分析. 2007,27(1):139-142.
47.仪器仪表交易网.从“沉睡”中醒来的近红外光谱技术. [2007-7-5]. http://www.testmart.cn/CN/News/NewsText/13029.html
48.张宝棣.水稻病害的识别与防治.宁夏科技报. 2004.5.25,第003版.
49.张秀琦,张红权,郑建斌,高鸿.小波傅里叶自去卷积用于示波信号中背景扣除的研究.分析化学. 2000, 3, 28:288-292.
50.张玉江,张汉友,李彩云,郑艳荣,贾光辉,于福安.水稻胡麻斑病发生原因、特点及防治措施.北方水稻. 2009, 39(5):38-40.
51.张左生.粮油作物病虫鼠害预测预报.上海:上海科技出版社,1995:52-66.
52.郑咏梅,张铁强,张军,陈星旦,申铉国.平滑、导数、基线校正对近红外光谱PLS定量分析的影响研究.光谱学与光谱分析.2004.12,24(12):1546-1548.
53.植被遥感. 2011-4-15取自http://kc.njnu.edu.cn/ygdxfx/page/jiaoan/ch7.htm
54.周启发,王人潮.水稻氮素营养水平与光谱特性的关系.浙江农业大学学报. 1993,19(9):40-45.
55.周志华,曹存根.神经网络及其应用.北京:清华大学出版社.2004:61-78.
56.逐步回归.2009-1-15取自百度百科http://baike.baidu.com/view/2137152.htm#sub2137152
57. Adams M L,Philpot W D,Norvell W A.Yellowness index:an application of spectral second derivatives to estimate chlorosis of leaves in stressed vegetation.Int.J.Remote Sensing. 1999,20:3663-3675.
58. Bair E,Hastie T,Paul D,Tibshirani R.Prediction by supervised principal components. J Am. Statist Assoc.2006,101:119-137.
59. Bare F,Champion I,Guyot et al.Monitoring wheat canopis with a high spectral resolution radiometer.Remote Sensing of Environment.1987,22:367-378.
60. Boochs F,Kupfer G,Dockter K,Kuhbauch W.Shape of the red edge as vitality indicator for plants. International Journal of Remote Sensing.1990,10(11):1741–1753.
61. CARTER G A,MILLER R L.Early detection of plant sress by digital imaging within narrow stress—sensitive wavebands.Remote Sensing of Environment,1994,50:295-302.
62. Cho M A,Skidmore A K.A new technique for extracting the red edge position from hyperspectral data:The linear extrapolation method. Remote Sensing of Environment. 2006,101(2):181–193.
63. Dawson T P,Curran P J.A new technique for interpolatin g the reflectance red edge position. International Journal of Remote Sensing.1998,19:2133–2139.
64. Emma S H,Anthon D W,Stephen J H. Anal.Chim. Acta,1997,337(1):191.
65. GAUSMAN H W,ALLEN W A,CARDENAS R,et al. Relation of light reflectance to histological and physical evaluation of cotton leaf maturity.Appl Optics,1970,9:545-552.
66. Geladi P,Kowalsk B R.Anal.Chim. Acta,1986,185 (1):1.
67. GELADI P,MACDOU GALL D,MARTENS H.Linearization and scatter-correction fornear-infrared reflectance spectra of meat . Appl. Spect rosc.,1985,39 (3):491-500.
68. General Least-Squares Smoothing and Differentiation by the Convolution (Savitzky-Golay) Method. Anal. Chem. 1990, 62(6): 570-573.
69. Gregory A,Carter,Rations of leaf reflectance in narrow wavebands as indicators of plant stress. Int.J.Remote sensing.1994,15(3):697-703.
70. Guan J,Nutter F W Jr.Quantifying the intrarater repeatability and interrater reliability of visual and remote-sensing disease-assessment methods in the alfalfa foliar pathosystem . Can.J.Plant Pathol. 2003,25:143-149.
71. Guyot G,Baret F,Jacquemoud S.Imaging spectroscopy for vegetation studies. In F.Toselli,& J.Bodechtel (Eds.), Imaging spectroscopy: Fundamentals and prospective applications. 1992. 145-165. Dordrecht, The Nethelands: Kluwer Academic.
72. Haaland D M,Robinson M R,Koepp G W.Appl.Spect roscopy,1992,46 (10):1575.
73. HAALAND D M,THOMAS E V.Partial least-squares methods for spectral analyses. Anal.Chem.1988,60 (11):1193-1217.
74. Harald Martens, Food Research & Data Analysis. Elsevier Applied Science.(1983.4).
75. Horler D N H,Dockray M,Barber J.The red edge of plant leaf reflectance. International Journal of Remote Sensing. 1983.4:273–288.
76. International rice testing program. Standard evaluatuion system for rice (2nd edition),1980,IRR2.
77. J.R.Miller,E.W.Hare,J.Wu.Quantitative characterization of the vegetation red edge reflectance 1.An inverted-Gaussian reflectance model. International Journal of Remote Sensing. 1990.10,10(11):1755-1773.
78. Kerr M K,Martin M ,Churchill G. A.Analysis of variance for gene expression microarray. Journal of Computational Biology. 2000,7:819-837.
79. Libo Liu , Guomin Zhou Study on Soil Nutrient Management and Fertilization Model in Ningxia County Territory with GIS The Second International Conference on Computer and Computing Technologies in Agriculture. Volume 1:223-231.
80. Malthus T J, M aderiaA C. High Resolution Spectroradiometry : Spectral Reflectance of Field Bean Leaves Infected by Botryt is Fabae. Remote Sens. Environ, 1993, 45:107-116.
81. Mardia K,Kent J,Bibby J.Multivariate Analysis,Academic Press,1979:157-180.
82. MCSHANE M J,COTE G L,SPIEGELMAN C H. Assessment of partial least-squares calibration and wavelength selection for complex near-infrared spectra .Appl.Spectrosc.,1998,52(6): 878-884.
83. Mehl P M,Chao K,Kim M,et al.Detection of defects on selected apple cultivars using hyperspectral and multispectral image analysis.Applied Engineering in Agriculture,2002,18(2):219-226.
84. Nguyen D V,Rocke D M. Tumor classification by partial least squares using microarray gene expression data. Bioinformatics. 2002,18:39-50.
85. Nilsson. H. E(1985). Remote sensing of 2-row barely infected by net blotch disease, Vol. 34. Vaxtskyddsrapporter-jordbruk, ppsala.
86. Nilsson.H.E.1985a. Remote sensing of oil seed rape infected by Sclerotinia stem rot andVerticillium wilt. Vaxtskyddsrapporter-jordbruk, vol.33,Uppsala.
87. Nutter F W Jr,Guan J,Gotlieb A R,et al. Quantifying alfalfa yield losses caused by foliar diseases in Iowa,Ohio, Wisconsin,and Vermont . Plant Disease,2002,86:269-277.
88. Nutter.F.W.Jr,Detection and measurement of plant disease gradients in peanut with a multispectral radiometer. Phytopathology. 1989,79:958-963.
89. Raymond H.Myers.Classical and Modern Regression with Applications (Duxbury Classic). Duxbury press. 1986,2,7:211-231.
90. RlNEHART G L,CATHOUN J H,SCHABBENBERGER O.Remote sensing of stripe patch and dillar spot on creeping bentgrass and annual bluegrass turfusing visible and near—infrared spectroscopy[R].Australian Turfgrass Management.2002.
91. Savitzky A. and Golay M. J. E. Analytical Chemistry,1964,36: 1627-1639.
92. Savitzky-Golay Methods. 2010,5,18取自http://www.casaxps.com/release/release2312_/CasaXPS.HLP/SpectrumProcessing/SavitzkyGolay.htm
93. SIMS D A,GAMON J A.Relationship between leaf pigment content and spectral reflectance across a wide range of species,leaf structure and developmental stages.Remote Sens Environ,2002,81:337-354.
94. SMlTH K L,STEVEN M D,COLLS J J.Use of hyperspectral derivative ratios in the red—region to identify plant stress responses to gas leaks.Remote Sensing Of Enviroment. 2004,92:207-217.
95. Steddom K , Heidel G , Jones D . et a1 . Remote detecfion of rhizomania in sugar beets. Phytopathology,2003,93:720-726.
96. Steinier, Jean; Termonia, Yves; Deltour, Jules. Comments on smoothing and differentiation of data by simplified least square procedure. Analytical Chemistry. 1972, 44 (11): 1906-1909.
97. T P Dawson, P J Curran, P R J North.The Propagation of Foliar Biochemical Absorption Features in Forest Canopy reflectance:a theoretica analysis.Remote Sensing of Environment,1999,67(2):147-l59.
98. Ward J K,Haaland D M,Robinson M R.Appl.Spect roscopy,1992,46(10):959.
99. William H.Press,Saul A.Teukolsky, William T. Vetterling, Brian P.Flannery .Numerical Recipes in C++: The Art of Scientific Computing, Second Edition . Cambridge University Press.2002,2:651-655.
100. Wold H.Soft Modelling by Latent Variables:The Nonlinear Iterative Partial Least Squares (NIPALS) Approach . In:Perspectives in Probability and Statistics,In Honor of Bartlett M S,1975.
2.陈兵,李少昆,王克如,柏军华,隋学艳,白彩云.作物病虫害遥感监测研究进展.棉花学报. 2007,19(1):57-63.
3.陈兵,王克如,李少昆,肖春华,王静,王方勇,潘文超,王娜.棉花黄萎病冠层高光谱遥感监测技术研究.新疆农业科学.2007,44(6):740-745.
4.陈鹏程.地面高光谱遥感在棉叶螨监测中的应用研究[硕士学位论文].新疆:石河子大学,2006.
5.单潮龙等,BP人工神经网络的应用及其实现技术.海军工程大学学报, 2000,第四期
6.东华理工大学,长江学院.植被遥感. 2011-4-15取自http://wenku.baidu.com/view/f8cbe1886529647d272852c7.html
7.方慧,宋海燕,曹芳,何勇,裘正军.油菜叶片的光谱特征与叶绿素含量之间的关系研究.光谱学与光谱分析. 2007,09:1721-1734.
8.飞思科技产品研发中心,神经网络理论与MATLAB7实现.电子工业出版社, 2005:32-50.
9.冯洁,廖宁放,赵波,罗永道,李宝聚,戴志福.多光谱成像技术诊断植物病虫害的人工神经网络模型.光学技术.2008.9,34(5).
10.冯世杰,戴小鹏,王艳平.基于NIR-SVM对鸭梨褐变病果的识别.农业网络信息.2008,(3):133-135.
11.何霭如,郭建夫.水稻纹枯病的发生及防治.安徽农业科学2007,35(4):996-997.
12.何国金等.北京麦蚜虫害的光谱测量与分析.遥感技术与应用. 2006,3(17):119-124.
13.何绍桓,王福荣,赵顺赫,宋世春.塑料大棚培育水稻壮苗主要技术的研究.吉林农业大学学报. 1982, 4:68-72.
14.黄木易,黄文江,刘良云,黄义德,王纪华,赵春江,万安民.冬小麦条锈病单叶光谱特性及严重度反演.农业工程学报. 2004,1,20(1):176-180.
15.蒋金豹,陈云浩,黄文江,李京.冬小麦条锈病严重度高光谱遥感反演模型研究.南京农业大学学报.2007,30(3):63-67.
16.蒋金豹,陈云浩,黄文江.利用高光谱微分指数进行冬小麦条锈病病情的诊断研究.光学技术. 2007,7,33(4).
17.蒋金豹,陈云浩,黄文江.利用高光谱红边与黄边位置距离识别小麦条锈病.光谱学与光谱分析.2010,6(30):1614-1618.
18.李波,刘占宇,黄敬峰,张莉丽,周湾,石晶晶.基于PCA和PNN的水稻病虫害高光谱识别.农业工程学报. 2009, 9 25(9):143-147.
19.李广华,张爱民,张杭,吴炎. Savitzky-golay滤子在短路器在线检测处理中的应用.高压电器. 2005,6,41(3):225-227.
20.李培生,胡松,孙路石,孙学信.基于SG算法的燃煤微分热重曲线平滑去噪.华中科技大学学报(自然科学版). 2005,7,33(7):61-64.
21.刘立波,周国民.基于多层感知神经网络的水稻叶瘟病识别方法.农业工程学报(增刊). 2009年,25(10):213-217.
22.刘立波,周国民.人眼视觉特性在植物叶片图像提取中的应用.计算机工程与应用2009,45(19): 22-25.
23.刘伟东,项月琴,郑兰芬,童庆禧,吴长山.高光谱数据与水稻叶面积指数及叶绿素密度的相关分析.遥感学报. 2000,4(4):279-283.
24.刘兴库,李兆华.多光谱诊断植物病害的初步研究.东北林业大学学报.1993.3,21(2):106-110.
25.刘旭华,徐兴忠,何雄奎,张录达.有监督主成分回归法在近红外光谱定量分析中的应用研究.光谱学与光谱分析.2009,12,29(11): 2959-2961.
26.龙伟等.人工神经网络发展前景.机械,1998,第25卷第1期
27.芦永军,曲艳玲,宋敏.近红外相关光谱的多元散射校正处理研究.光谱学与光谱分析.2007,5,27(5):877-880.
28.孟德超,纪明山.辽宁地区水稻纹枯病拮抗细菌的分离和筛选.河南农业科学. 2009,04: 79-81.
29.农作物病害综合防治.农民致富之友.2000.8.
30.区靖祥,邱健德.多元数据的统计分析方法.北京:中国农业科学技术出版社, 2002:63-75.
31.石吉勇,邹小波,赵杰文,殷晓平.基于小波滤噪和ipls的草莓近红外光谱糖度检测模型.安徽农业科学.2009,37(12):5752-5754.
32.水稻病虫害. 2009-04-16取自中国种子拍卖网http://www.zzpmw.cn/Zinfo/Daolei/Bingc/20080416/160137.shtml
33.水稻病虫害.2011-4-15取自广西植物保护网http://www.gxzb.com/html/2009-4/20092009429163245698.html
34.水稻纹枯病. 2010-09-25取自百度百科http://baike.baidu.com/view/363661.htm
35.穗波信雄.根据图像提取农作物的生长信息.农业机械学会关西支部第6次支部研究资料.1989.10:1-12.
36.谭广发.水稻病害防治技术.植物保护. 2004, 170(4): 22-23.
37.檀根甲,李辉.水稻纹枯病不同分级标准病情指数间的关系.安徽农业大学学报. 1993, 20(3): 228-233.
38.唐延林,王人潮,王秀珍.对水稻微分光谱和植被指数的探讨.上海交通大学学报(农业科学版). 2003,21(3):199-204.
39.田庆久.高光谱遥感环境污染监测研究进展ppt.
40.田永超,杨杰,姚霞,朱艳,曹卫星.水稻高光谱红边位置与叶层氮浓度的关系.作物学报.2009,35(9):1681?1690.
41.万余庆,谭克龙,周日平.高光谱遥感应用研究.北京:科学出版社,2006:133-171.
42.王秀珍,王人潮,黄敬峰.微分光谱遥感及其在水稻农学参数测定上的应用研究.农业工程学报. 2002,18(1): 9-13.
43.王艳青.近年来中国水稻病虫害发生及趋势分析.中国农学通报. 2006, 22(2): 343-347.
44.吴曙雯,王人潮,陈晓斌,沈掌泉,史舟.稻叶瘟对水稻光谱特性的影响研究.上海交通大学学报(农业科学版).2002.3,20(1):73-76,84.
45.细菌性病害. 2006-12-29.取自百度百科http://baike.baidu.com/view/689853.htm
46.熊宇虹,温志渝,王命延,徐少平,王炜立,肖建.基于神经网络的光谱识别系统的设计与分析.光谱学与光谱分析. 2007,27(1):139-142.
47.仪器仪表交易网.从“沉睡”中醒来的近红外光谱技术. [2007-7-5]. http://www.testmart.cn/CN/News/NewsText/13029.html
48.张宝棣.水稻病害的识别与防治.宁夏科技报. 2004.5.25,第003版.
49.张秀琦,张红权,郑建斌,高鸿.小波傅里叶自去卷积用于示波信号中背景扣除的研究.分析化学. 2000, 3, 28:288-292.
50.张玉江,张汉友,李彩云,郑艳荣,贾光辉,于福安.水稻胡麻斑病发生原因、特点及防治措施.北方水稻. 2009, 39(5):38-40.
51.张左生.粮油作物病虫鼠害预测预报.上海:上海科技出版社,1995:52-66.
52.郑咏梅,张铁强,张军,陈星旦,申铉国.平滑、导数、基线校正对近红外光谱PLS定量分析的影响研究.光谱学与光谱分析.2004.12,24(12):1546-1548.
53.植被遥感. 2011-4-15取自http://kc.njnu.edu.cn/ygdxfx/page/jiaoan/ch7.htm
54.周启发,王人潮.水稻氮素营养水平与光谱特性的关系.浙江农业大学学报. 1993,19(9):40-45.
55.周志华,曹存根.神经网络及其应用.北京:清华大学出版社.2004:61-78.
56.逐步回归.2009-1-15取自百度百科http://baike.baidu.com/view/2137152.htm#sub2137152
57. Adams M L,Philpot W D,Norvell W A.Yellowness index:an application of spectral second derivatives to estimate chlorosis of leaves in stressed vegetation.Int.J.Remote Sensing. 1999,20:3663-3675.
58. Bair E,Hastie T,Paul D,Tibshirani R.Prediction by supervised principal components. J Am. Statist Assoc.2006,101:119-137.
59. Bare F,Champion I,Guyot et al.Monitoring wheat canopis with a high spectral resolution radiometer.Remote Sensing of Environment.1987,22:367-378.
60. Boochs F,Kupfer G,Dockter K,Kuhbauch W.Shape of the red edge as vitality indicator for plants. International Journal of Remote Sensing.1990,10(11):1741–1753.
61. CARTER G A,MILLER R L.Early detection of plant sress by digital imaging within narrow stress—sensitive wavebands.Remote Sensing of Environment,1994,50:295-302.
62. Cho M A,Skidmore A K.A new technique for extracting the red edge position from hyperspectral data:The linear extrapolation method. Remote Sensing of Environment. 2006,101(2):181–193.
63. Dawson T P,Curran P J.A new technique for interpolatin g the reflectance red edge position. International Journal of Remote Sensing.1998,19:2133–2139.
64. Emma S H,Anthon D W,Stephen J H. Anal.Chim. Acta,1997,337(1):191.
65. GAUSMAN H W,ALLEN W A,CARDENAS R,et al. Relation of light reflectance to histological and physical evaluation of cotton leaf maturity.Appl Optics,1970,9:545-552.
66. Geladi P,Kowalsk B R.Anal.Chim. Acta,1986,185 (1):1.
67. GELADI P,MACDOU GALL D,MARTENS H.Linearization and scatter-correction fornear-infrared reflectance spectra of meat . Appl. Spect rosc.,1985,39 (3):491-500.
68. General Least-Squares Smoothing and Differentiation by the Convolution (Savitzky-Golay) Method. Anal. Chem. 1990, 62(6): 570-573.
69. Gregory A,Carter,Rations of leaf reflectance in narrow wavebands as indicators of plant stress. Int.J.Remote sensing.1994,15(3):697-703.
70. Guan J,Nutter F W Jr.Quantifying the intrarater repeatability and interrater reliability of visual and remote-sensing disease-assessment methods in the alfalfa foliar pathosystem . Can.J.Plant Pathol. 2003,25:143-149.
71. Guyot G,Baret F,Jacquemoud S.Imaging spectroscopy for vegetation studies. In F.Toselli,& J.Bodechtel (Eds.), Imaging spectroscopy: Fundamentals and prospective applications. 1992. 145-165. Dordrecht, The Nethelands: Kluwer Academic.
72. Haaland D M,Robinson M R,Koepp G W.Appl.Spect roscopy,1992,46 (10):1575.
73. HAALAND D M,THOMAS E V.Partial least-squares methods for spectral analyses. Anal.Chem.1988,60 (11):1193-1217.
74. Harald Martens, Food Research & Data Analysis. Elsevier Applied Science.(1983.4).
75. Horler D N H,Dockray M,Barber J.The red edge of plant leaf reflectance. International Journal of Remote Sensing. 1983.4:273–288.
76. International rice testing program. Standard evaluatuion system for rice (2nd edition),1980,IRR2.
77. J.R.Miller,E.W.Hare,J.Wu.Quantitative characterization of the vegetation red edge reflectance 1.An inverted-Gaussian reflectance model. International Journal of Remote Sensing. 1990.10,10(11):1755-1773.
78. Kerr M K,Martin M ,Churchill G. A.Analysis of variance for gene expression microarray. Journal of Computational Biology. 2000,7:819-837.
79. Libo Liu , Guomin Zhou Study on Soil Nutrient Management and Fertilization Model in Ningxia County Territory with GIS The Second International Conference on Computer and Computing Technologies in Agriculture. Volume 1:223-231.
80. Malthus T J, M aderiaA C. High Resolution Spectroradiometry : Spectral Reflectance of Field Bean Leaves Infected by Botryt is Fabae. Remote Sens. Environ, 1993, 45:107-116.
81. Mardia K,Kent J,Bibby J.Multivariate Analysis,Academic Press,1979:157-180.
82. MCSHANE M J,COTE G L,SPIEGELMAN C H. Assessment of partial least-squares calibration and wavelength selection for complex near-infrared spectra .Appl.Spectrosc.,1998,52(6): 878-884.
83. Mehl P M,Chao K,Kim M,et al.Detection of defects on selected apple cultivars using hyperspectral and multispectral image analysis.Applied Engineering in Agriculture,2002,18(2):219-226.
84. Nguyen D V,Rocke D M. Tumor classification by partial least squares using microarray gene expression data. Bioinformatics. 2002,18:39-50.
85. Nilsson. H. E(1985). Remote sensing of 2-row barely infected by net blotch disease, Vol. 34. Vaxtskyddsrapporter-jordbruk, ppsala.
86. Nilsson.H.E.1985a. Remote sensing of oil seed rape infected by Sclerotinia stem rot andVerticillium wilt. Vaxtskyddsrapporter-jordbruk, vol.33,Uppsala.
87. Nutter F W Jr,Guan J,Gotlieb A R,et al. Quantifying alfalfa yield losses caused by foliar diseases in Iowa,Ohio, Wisconsin,and Vermont . Plant Disease,2002,86:269-277.
88. Nutter.F.W.Jr,Detection and measurement of plant disease gradients in peanut with a multispectral radiometer. Phytopathology. 1989,79:958-963.
89. Raymond H.Myers.Classical and Modern Regression with Applications (Duxbury Classic). Duxbury press. 1986,2,7:211-231.
90. RlNEHART G L,CATHOUN J H,SCHABBENBERGER O.Remote sensing of stripe patch and dillar spot on creeping bentgrass and annual bluegrass turfusing visible and near—infrared spectroscopy[R].Australian Turfgrass Management.2002.
91. Savitzky A. and Golay M. J. E. Analytical Chemistry,1964,36: 1627-1639.
92. Savitzky-Golay Methods. 2010,5,18取自http://www.casaxps.com/release/release2312_/CasaXPS.HLP/SpectrumProcessing/SavitzkyGolay.htm
93. SIMS D A,GAMON J A.Relationship between leaf pigment content and spectral reflectance across a wide range of species,leaf structure and developmental stages.Remote Sens Environ,2002,81:337-354.
94. SMlTH K L,STEVEN M D,COLLS J J.Use of hyperspectral derivative ratios in the red—region to identify plant stress responses to gas leaks.Remote Sensing Of Enviroment. 2004,92:207-217.
95. Steddom K , Heidel G , Jones D . et a1 . Remote detecfion of rhizomania in sugar beets. Phytopathology,2003,93:720-726.
96. Steinier, Jean; Termonia, Yves; Deltour, Jules. Comments on smoothing and differentiation of data by simplified least square procedure. Analytical Chemistry. 1972, 44 (11): 1906-1909.
97. T P Dawson, P J Curran, P R J North.The Propagation of Foliar Biochemical Absorption Features in Forest Canopy reflectance:a theoretica analysis.Remote Sensing of Environment,1999,67(2):147-l59.
98. Ward J K,Haaland D M,Robinson M R.Appl.Spect roscopy,1992,46(10):959.
99. William H.Press,Saul A.Teukolsky, William T. Vetterling, Brian P.Flannery .Numerical Recipes in C++: The Art of Scientific Computing, Second Edition . Cambridge University Press.2002,2:651-655.
100. Wold H.Soft Modelling by Latent Variables:The Nonlinear Iterative Partial Least Squares (NIPALS) Approach . In:Perspectives in Probability and Statistics,In Honor of Bartlett M S,1975.