基于叶绿素荧光光谱分析的温室黄瓜病虫害预警方法
|
摘要
高产量、优品质的工厂化生产是设施农业管理的最终目标，而在设施农业的日常生产中，为了刚性的达到高产量的要求，农药作为一种补偿性的手段得到了广泛的应用，使得作物的品质安全不能得到有效的保证。寻求快速、无损、准确地检测病虫害的新方法，成为设施农业研究的重点问题。本文结合国家高技术研究发展计划“植物生理信息检测激光诱导式传感器与诊断技术”（项目编号2007AA10Z203）和“全自动嫁接育苗关键技术与成套设备研究”（项目编号2012AA10A506），以及吉林省科技发展计划项目“吉林省水稻主产区重大病虫害数字监测预警系统的关键技术研究”（项目编号：20110217）的相关内容，以温室黄瓜为研究对象，通过提取光谱特征信息作为叶片健康状态的判别标准，利用植物生理信息模型作为叶片健康状态的辅助判别标准；建立健康叶片与病虫害叶片的分类诊断模型，以及霜霉病害、白粉病害和蚜虫害的预测模型，将温室内的环境条件与叶绿素荧光光谱相结合，设计温室黄瓜病虫害的监测体系和预警信息系统结构。
首先，从光谱参数角度出发，研究健康叶片与病虫害叶片的光谱差别，提取光谱特征信息，定性分析叶片的健康状态。以光谱的第二波峰发射波长685nm作为判别临界值，判断健康叶片的第二波峰发射波长小于685nm，病虫害叶片的第二波峰发射波长大于或等于685nm；以光谱的第一波谷强度0Counts作为判别临界值，判断健康叶片的第一波谷强度大于或等于0Counts，病虫害叶片的第一波谷强度值小于0Counts；以F512~F632波段的光谱曲线变化速率k=3作为判别临界值，将K<3的叶片判别为健康叶片，将k≥3的叶片判别为病虫害叶片。
利用叶片的生理信息作为判别指标，通过建立叶片的生理信息模型，进一步判断叶片的健康状态。利用荧光光谱指数与光合有效辐射建立叶片的净光合速率模型，得到预测集的相关系数为0.825，在0.01水平上显著相关；利用荧光光谱指数与叶片温度相结合，建立叶片水分利用效率模型，得到预测集的相关系数为0.984，在0.05水平上差异不显著；采用光谱分析与数据挖掘方法相结合，建立叶绿素含量SPAD模型，采用简单波段自相关选择方法筛选有效波段，利用主成分分析方法降低光谱维数，最后利用最小二乘支持向量机回归建立模型，得到预测集的相关系数为0.946。将叶片的净光合速率、水分利用效率与叶绿素含量作为判别叶片健康状态的辅助信息。
以健康叶片的叶绿素荧光光谱数据作为标准，利用叶绿素荧光光谱分析技术结合数据挖掘方法，建立了健康叶片与霜霉病害叶片、白粉病害叶片与蚜虫害叶片的分类诊断模型，通过对比最小二乘支持向量机、判别分析以及BP神经网络三种方法，以及主成分分析、小波变换的光谱降维方法，确定采用最小二乘支持向量机和主成分分析方法建立模型及降维处理，对得到的主成分得分值分别建立分类诊断模型，确定采用前10个主成分作为模型的输入变量，最终得到模型预测集的相关系数为0.939，均方差为0.389，准确率为93.3%。
通过分类模型的诊断后，分别对健康叶片与接种霜霉病菌的叶片光谱数据进行分析，通过对比最小二乘支持向量机、判别分析与BP神经网络三种建模方法，比较归一化、一阶导数、二阶导数、多元散射校正、一阶导数与多元散射校正光谱预处理方法，并对得到的光谱进行主成分分析与小波降噪降维处理，最后确定采用最小二乘支持向量机、一阶导数和主成分分析的方法建立霜霉病害预测模型，并对得到的主成分个数进行对比分析，得到前10个主成分作为模型输入变量时，建立的健康叶片、霜霉病菌侵染期叶片、病症初显期叶片及大面积流行期叶片得到的模型效果较好，最终得到的预测集的RMSEP为0.375，预测准确率为96.6%，预测集叶片样本的真实值与预测值的相关系数为0.946。
分别对健康叶片、白粉病菌侵染期叶片、病症初显期叶片、大面积流行期叶片的光谱数据进行分析，通过建模方法比较，确定采用最小二乘支持向量机作为建模方法，经过简单自相关波段选择方法筛选了61~70光谱波段区域作为优选光谱波段，经过主成分分析方法、小波降噪光谱降维方法的选择，并讨论不同的主成分个数对白粉病害预测模型的影响，确定采用主成分个数为8，建立白粉病害预测模型，最终得到的预测集的RMSEP为0.489，预测准确率为91.3%，预测集叶片样本的真实值与预测值的相关系数为0.890
利用叶绿素荧光光谱分析的方法，建立蚜虫害的预测模型。分别采集健康叶片、少量虫卵及成虫叶片、大量虫卵及成虫叶片、虫害大面积发生或全部覆盖叶片的荧光光谱数据，并对其进行分析，对比最小二乘支持向量机、判别分析与BP神经网络建模方法，确定采用最小二乘支持向量机作为模型建立的方法，利用波峰波谷所在波段筛选光谱的有效波段，确定采用F632波段作为光谱优选波段，并利用主成分分析的方法对光谱进行降维处理，讨论不同因子个数对模型的影响，确定采用前8个主成分作为模型输入变量，建立黄瓜蚜虫害预测模型，最终得到的预测集的RMSEP为0.569，预测准确率为97.5%，预测集叶片样本的真实值与预测值的相关系数为0.981。
此外，根据病虫害的发生规律与试验的实际情况，对比病虫害高发月份与低发月份的环境条件，确定病虫害发生的条件阈值。分别对最大温湿度、最小温湿度、温度与湿度差值与平均温湿度进行分析，确定采用日平均温度、日平均湿度作为病虫害发生的阈值，其温度、湿度范围为15℃≤Tmean≤25℃，40%≤RHmean≤70%；同时将温度与湿度参数相结合，对其进行判别分析；以病菌的侵染时间计算，取每天连续6小时的温度、湿度判断，得到温、湿度范围为15℃≤6hTmean≤30℃，50%≤6hRHmean≤100%。
综合运用本研究的相关技术，将温室的环境条件检测与叶片的叶绿素荧光光谱检测相结合，构建温室黄瓜病虫害的监测体系。首先通过分析温室内的环境条件数据，经过环境条件的阈值判断后，如果满足了病虫害的发生阈值，则进行叶绿素荧光光谱的检测并对数据进行分析，经过光谱特征点和生理信息模型的判断，将病虫害叶片的光谱信息代入至分类诊断模型，确定叶片发生病虫害的发生种类，并通过预测模型确定病虫害发生的程度，得出病虫害状况的监测及预测报告；利用预警信息系统对监测及预测报告进行判断，并将结果发送到主控室、温室与管理者，将数据保存，完成病虫害的预警。
The industrial production of high yield and excellent quality is the ultimate goal ofagricultural facilities management; however, in the daily production of facility agriculture, inorder to achieve the requirement of high yield rigidly, pesticides have been widely used as acompensatory method, which makes the crop quality safety not guaranteed. Seeking newmethods to check diseases and insect pests fast, nondestructively, and accurately becomesthe key problem of facility agriculture research. This word is supported by National HighTechnology Research and Development Program―Laser-induced Plant PhysiologicalInformation Detection Sensors and Diagnosis‖(2007AA10Z203), and―Full AutomaticGrafting and Growing Seedlings Key Technology and Complete Sets of EquipmentResearch‖(2012AA10A506), and Jilin Province’s Science and Technology DepartmentProgram―Key Technology Research on Major Diseases and Insect Pests Digital Monitoringand Early Warning System in Main Rice Growing Districts of Jilin Province‖(20110217),use the spectral characteristic information and plant physiological information changes toresearch greenhouse crop health status changes, with the study object of greenhousecucumber, which is the foundation to achieve plant factory manufacturing management.Chlorophyll fluorescence can reflect the plant physiological information, while this paperuses chlorophyll fluorescence spectroscopy analysis technology to reflect the physiologicalinformation changes and afterwards to reflect leaves’ status changes.
Starting with the spectral shape, study the distinction of healthy and verminous leaves, andextract spectral characteristic information: with the spectral second peak emissionwavelength685nm as discriminant critical value, judge that of healthy leaves to be smallerthan685nm, and that of verminous leaves greater than685nm; with the spectral first wavetrough intensity0Counts as discriminant critical value, judge that of healthy leaves to begreater than0Counts, and that of verminous leaves smaller tha n0counts. with theF512~F632wave band’s spectral curve change rate k=3as discriminant critical value, judgethe leave to be healthy whose change rate k is less than3, and to be verminous whose changerate k is more than3.
Use of the leaves of the physical information index, establish the leaves of the physicalinformation model, further judge the leaves of the health status. Use the fluorescence spectralindex and photosynthetic active radiation establish of leaf net photosynthetic rate model, toachieve the prediction set’s correlate coefficient of0.825, being evidently interrelated in thelevel of0.01; use the fluorescence spectral index connected to leaf temperature to establishleaf moisture availability model, to achieve the predictionset’s correlate coefficient of0.984, being evidently interrelated in the level of0.05; combined the spectral analysis with dataexcavation method, establish chlorophyll content SPAD model, use simple wave bandsautocorrelation method to screen the efficient, utilize the principal component analysismethod to reduce the spectral dimension, and finally use least squares support vectormachine regression to establish model, achieve the prediction set’s correlate coefficient of0.946. Regard leaves’ Net photosynthetic rate, moisture availability and chlorophyll contentas the auxiliary information judging leaves whether to be healthy.
With the leaves of the health chlorophyll fluorescence spectra data as standard, Usechlorophyll fluorescence analysis technique combined with data excavation method toestablish the classified diagnosis model of healthy and downy mildew disease leaves,powdery mildew disease and aphid disease leaves. By contrasting the three methods of leastsquares support vector machine, discriminant analysis and BP neural network, and theprincipal component analysis method and the spectral dimension reduction method ofwavelet change, define the method of utilizing the least squares support vector machine andprincipal component analysis to reduce the model’s dimension and establishing models, andrespectively establish the classified diagnosis model of gotten principal component figures,determine to use10principal components as the model input variables, at last achieve theprediction set’s correlate coefficient of0.939, mean square error of0.389, accuracy rate of93.3%.
Respectively analyze the spectral data of healthy and downy mildew disease leaves, bycontrasting the three method of least squares support vector machine, discriminant analysisand BP neural network, compare a derivative, two derivative, multiple scattering correction,derivative and multiple scattering correction of spectral pre-treatment methods, andprocessing the gotten spectrum by principal component analysis and wavelet noise anddimension reduction methods, finally define to use the methods of least squares supportvector machine, derivative and principal component analysis to establish downy mildewdisease prediction model, and make comparative analysis of the gotten principal componentnumber. Achieve10principal components variable number, and the effect of establishedmodels of healthy, downy mildew infection leaf, early downy mildew disease leaf, and leafwith large disease area is good, and the final RMSEP of the prediction set is0.375, accuracyrate is96.6%, correlate coefficient of the true value of prediction set leaf sample andpredictive value is0.949.
Respectively analyze the spectral data of healthy, powdery mildew infection leaf, earlypowdery mildew disease leaf, and leaf with large disease area, by the methods of leastsquares support vector machine, discriminant analysis and BP neutral network, use simplewave bands autocorrelation method to screen61~70spectral wave bands as the efficient.Through the choice of principal component analysis and wavelet noise and dimensionreduction methods, and the discussion of the different influence to powdery mildew diseaseleaves prediction model from different principal components number. Define to utilize8principal components, and establish powdery mildew disease leaves prediction model. The final RMSEP of the prediction set is0.489, accuracy rate is91.3%, correlate coefficient ofthe true value of prediction set leaf sample and predictive value is0.890.
Utilize chlorophyll fluorescence analysis method and establish aphid disease leavesprediction model. Respectively collect and analyze the fluorescence spectral data of healthy,a small amount of pest eggs and adult, large amount of pest eggs and adult leaves, and leafwith large disease area or filled with aphid disease, by contrasting the three method of leastsquares support vector machine, discriminant analysis and BP neural network, and define touse least squares support vector machine method. Use the wave bands with peak and troughto screen the efficient, make sure to use F632wave band as the efficient, and utilize principalcomponent analysis method to reduce spectral dimension. Discuss the influence to the modelfrom different factor number, define to use8principal components as input variables andestablish cucumber aphid disease prediction model. The final RMSEP of the prediction set is0.569, accuracy rate is97.5%, correlate coefficient of the true value of prediction set leafsample and predictive value is0.981.
In addition, by the regularity of disease outbreak and actual situation, plant diseases andinsect pests in high contrast with low in hair environmental conditions, Sure the occurrenceof pest and disease conditions threshold. Analyze the maximum, minimum, difference andaverage value of temperature and humidity, and define to utilize average temperature andhumidity as the nosopoietic threshold value. The scopes of temperature and humidity are15℃≤Tmean≤25℃，40%≤RHmean≤70%; moreover, combine and then analyze theparameter of temperature and humidity in June, September and July, August; according tothe calculation of pathogen infection time, judge the continues temperature and humility for6hours, and achieve the scopes of temperature and humility are15℃≤6hTmean≤30℃，50%≤6hRHmean≤100%.
Combine the survey of greenhouse environmental condition with chlorophyll fluorescencesurvey, and construct diseases and insect pests monitoring system of greenhouse cucumber.First of all, by analysing the environmental condition data and after monitoring the thresholdvalue of environmental condition, if the conditions of plant diseases and insect pests’occurrence are satisfied, monitor and analyze the chlorophyll fluorescence data. Accordingto the classified diagnosis model make sure of the occurrence type of plant diseases andinsect pests, and by the prediction model define the degree and situation, and achieve thereports of plant diseases and insect pests judging monitoring and calculating; utilize the earlywarming system to pinpoint monitoring and calculating reports, send the result to maincontrol room, greenhouse and managers, and preserve the data, then a process of earlywarming is accomplished.
首先，从光谱参数角度出发，研究健康叶片与病虫害叶片的光谱差别，提取光谱特征信息，定性分析叶片的健康状态。以光谱的第二波峰发射波长685nm作为判别临界值，判断健康叶片的第二波峰发射波长小于685nm，病虫害叶片的第二波峰发射波长大于或等于685nm；以光谱的第一波谷强度0Counts作为判别临界值，判断健康叶片的第一波谷强度大于或等于0Counts，病虫害叶片的第一波谷强度值小于0Counts；以F512~F632波段的光谱曲线变化速率k=3作为判别临界值，将K<3的叶片判别为健康叶片，将k≥3的叶片判别为病虫害叶片。
利用叶片的生理信息作为判别指标，通过建立叶片的生理信息模型，进一步判断叶片的健康状态。利用荧光光谱指数与光合有效辐射建立叶片的净光合速率模型，得到预测集的相关系数为0.825，在0.01水平上显著相关；利用荧光光谱指数与叶片温度相结合，建立叶片水分利用效率模型，得到预测集的相关系数为0.984，在0.05水平上差异不显著；采用光谱分析与数据挖掘方法相结合，建立叶绿素含量SPAD模型，采用简单波段自相关选择方法筛选有效波段，利用主成分分析方法降低光谱维数，最后利用最小二乘支持向量机回归建立模型，得到预测集的相关系数为0.946。将叶片的净光合速率、水分利用效率与叶绿素含量作为判别叶片健康状态的辅助信息。
以健康叶片的叶绿素荧光光谱数据作为标准，利用叶绿素荧光光谱分析技术结合数据挖掘方法，建立了健康叶片与霜霉病害叶片、白粉病害叶片与蚜虫害叶片的分类诊断模型，通过对比最小二乘支持向量机、判别分析以及BP神经网络三种方法，以及主成分分析、小波变换的光谱降维方法，确定采用最小二乘支持向量机和主成分分析方法建立模型及降维处理，对得到的主成分得分值分别建立分类诊断模型，确定采用前10个主成分作为模型的输入变量，最终得到模型预测集的相关系数为0.939，均方差为0.389，准确率为93.3%。
通过分类模型的诊断后，分别对健康叶片与接种霜霉病菌的叶片光谱数据进行分析，通过对比最小二乘支持向量机、判别分析与BP神经网络三种建模方法，比较归一化、一阶导数、二阶导数、多元散射校正、一阶导数与多元散射校正光谱预处理方法，并对得到的光谱进行主成分分析与小波降噪降维处理，最后确定采用最小二乘支持向量机、一阶导数和主成分分析的方法建立霜霉病害预测模型，并对得到的主成分个数进行对比分析，得到前10个主成分作为模型输入变量时，建立的健康叶片、霜霉病菌侵染期叶片、病症初显期叶片及大面积流行期叶片得到的模型效果较好，最终得到的预测集的RMSEP为0.375，预测准确率为96.6%，预测集叶片样本的真实值与预测值的相关系数为0.946。
分别对健康叶片、白粉病菌侵染期叶片、病症初显期叶片、大面积流行期叶片的光谱数据进行分析，通过建模方法比较，确定采用最小二乘支持向量机作为建模方法，经过简单自相关波段选择方法筛选了61~70光谱波段区域作为优选光谱波段，经过主成分分析方法、小波降噪光谱降维方法的选择，并讨论不同的主成分个数对白粉病害预测模型的影响，确定采用主成分个数为8，建立白粉病害预测模型，最终得到的预测集的RMSEP为0.489，预测准确率为91.3%，预测集叶片样本的真实值与预测值的相关系数为0.890
利用叶绿素荧光光谱分析的方法，建立蚜虫害的预测模型。分别采集健康叶片、少量虫卵及成虫叶片、大量虫卵及成虫叶片、虫害大面积发生或全部覆盖叶片的荧光光谱数据，并对其进行分析，对比最小二乘支持向量机、判别分析与BP神经网络建模方法，确定采用最小二乘支持向量机作为模型建立的方法，利用波峰波谷所在波段筛选光谱的有效波段，确定采用F632波段作为光谱优选波段，并利用主成分分析的方法对光谱进行降维处理，讨论不同因子个数对模型的影响，确定采用前8个主成分作为模型输入变量，建立黄瓜蚜虫害预测模型，最终得到的预测集的RMSEP为0.569，预测准确率为97.5%，预测集叶片样本的真实值与预测值的相关系数为0.981。
此外，根据病虫害的发生规律与试验的实际情况，对比病虫害高发月份与低发月份的环境条件，确定病虫害发生的条件阈值。分别对最大温湿度、最小温湿度、温度与湿度差值与平均温湿度进行分析，确定采用日平均温度、日平均湿度作为病虫害发生的阈值，其温度、湿度范围为15℃≤Tmean≤25℃，40%≤RHmean≤70%；同时将温度与湿度参数相结合，对其进行判别分析；以病菌的侵染时间计算，取每天连续6小时的温度、湿度判断，得到温、湿度范围为15℃≤6hTmean≤30℃，50%≤6hRHmean≤100%。
综合运用本研究的相关技术，将温室的环境条件检测与叶片的叶绿素荧光光谱检测相结合，构建温室黄瓜病虫害的监测体系。首先通过分析温室内的环境条件数据，经过环境条件的阈值判断后，如果满足了病虫害的发生阈值，则进行叶绿素荧光光谱的检测并对数据进行分析，经过光谱特征点和生理信息模型的判断，将病虫害叶片的光谱信息代入至分类诊断模型，确定叶片发生病虫害的发生种类，并通过预测模型确定病虫害发生的程度，得出病虫害状况的监测及预测报告；利用预警信息系统对监测及预测报告进行判断，并将结果发送到主控室、温室与管理者，将数据保存，完成病虫害的预警。
The industrial production of high yield and excellent quality is the ultimate goal ofagricultural facilities management; however, in the daily production of facility agriculture, inorder to achieve the requirement of high yield rigidly, pesticides have been widely used as acompensatory method, which makes the crop quality safety not guaranteed. Seeking newmethods to check diseases and insect pests fast, nondestructively, and accurately becomesthe key problem of facility agriculture research. This word is supported by National HighTechnology Research and Development Program―Laser-induced Plant PhysiologicalInformation Detection Sensors and Diagnosis‖(2007AA10Z203), and―Full AutomaticGrafting and Growing Seedlings Key Technology and Complete Sets of EquipmentResearch‖(2012AA10A506), and Jilin Province’s Science and Technology DepartmentProgram―Key Technology Research on Major Diseases and Insect Pests Digital Monitoringand Early Warning System in Main Rice Growing Districts of Jilin Province‖(20110217),use the spectral characteristic information and plant physiological information changes toresearch greenhouse crop health status changes, with the study object of greenhousecucumber, which is the foundation to achieve plant factory manufacturing management.Chlorophyll fluorescence can reflect the plant physiological information, while this paperuses chlorophyll fluorescence spectroscopy analysis technology to reflect the physiologicalinformation changes and afterwards to reflect leaves’ status changes.
Starting with the spectral shape, study the distinction of healthy and verminous leaves, andextract spectral characteristic information: with the spectral second peak emissionwavelength685nm as discriminant critical value, judge that of healthy leaves to be smallerthan685nm, and that of verminous leaves greater than685nm; with the spectral first wavetrough intensity0Counts as discriminant critical value, judge that of healthy leaves to begreater than0Counts, and that of verminous leaves smaller tha n0counts. with theF512~F632wave band’s spectral curve change rate k=3as discriminant critical value, judgethe leave to be healthy whose change rate k is less than3, and to be verminous whose changerate k is more than3.
Use of the leaves of the physical information index, establish the leaves of the physicalinformation model, further judge the leaves of the health status. Use the fluorescence spectralindex and photosynthetic active radiation establish of leaf net photosynthetic rate model, toachieve the prediction set’s correlate coefficient of0.825, being evidently interrelated in thelevel of0.01; use the fluorescence spectral index connected to leaf temperature to establishleaf moisture availability model, to achieve the predictionset’s correlate coefficient of0.984, being evidently interrelated in the level of0.05; combined the spectral analysis with dataexcavation method, establish chlorophyll content SPAD model, use simple wave bandsautocorrelation method to screen the efficient, utilize the principal component analysismethod to reduce the spectral dimension, and finally use least squares support vectormachine regression to establish model, achieve the prediction set’s correlate coefficient of0.946. Regard leaves’ Net photosynthetic rate, moisture availability and chlorophyll contentas the auxiliary information judging leaves whether to be healthy.
With the leaves of the health chlorophyll fluorescence spectra data as standard, Usechlorophyll fluorescence analysis technique combined with data excavation method toestablish the classified diagnosis model of healthy and downy mildew disease leaves,powdery mildew disease and aphid disease leaves. By contrasting the three methods of leastsquares support vector machine, discriminant analysis and BP neural network, and theprincipal component analysis method and the spectral dimension reduction method ofwavelet change, define the method of utilizing the least squares support vector machine andprincipal component analysis to reduce the model’s dimension and establishing models, andrespectively establish the classified diagnosis model of gotten principal component figures,determine to use10principal components as the model input variables, at last achieve theprediction set’s correlate coefficient of0.939, mean square error of0.389, accuracy rate of93.3%.
Respectively analyze the spectral data of healthy and downy mildew disease leaves, bycontrasting the three method of least squares support vector machine, discriminant analysisand BP neural network, compare a derivative, two derivative, multiple scattering correction,derivative and multiple scattering correction of spectral pre-treatment methods, andprocessing the gotten spectrum by principal component analysis and wavelet noise anddimension reduction methods, finally define to use the methods of least squares supportvector machine, derivative and principal component analysis to establish downy mildewdisease prediction model, and make comparative analysis of the gotten principal componentnumber. Achieve10principal components variable number, and the effect of establishedmodels of healthy, downy mildew infection leaf, early downy mildew disease leaf, and leafwith large disease area is good, and the final RMSEP of the prediction set is0.375, accuracyrate is96.6%, correlate coefficient of the true value of prediction set leaf sample andpredictive value is0.949.
Respectively analyze the spectral data of healthy, powdery mildew infection leaf, earlypowdery mildew disease leaf, and leaf with large disease area, by the methods of leastsquares support vector machine, discriminant analysis and BP neutral network, use simplewave bands autocorrelation method to screen61~70spectral wave bands as the efficient.Through the choice of principal component analysis and wavelet noise and dimensionreduction methods, and the discussion of the different influence to powdery mildew diseaseleaves prediction model from different principal components number. Define to utilize8principal components, and establish powdery mildew disease leaves prediction model. The final RMSEP of the prediction set is0.489, accuracy rate is91.3%, correlate coefficient ofthe true value of prediction set leaf sample and predictive value is0.890.
Utilize chlorophyll fluorescence analysis method and establish aphid disease leavesprediction model. Respectively collect and analyze the fluorescence spectral data of healthy,a small amount of pest eggs and adult, large amount of pest eggs and adult leaves, and leafwith large disease area or filled with aphid disease, by contrasting the three method of leastsquares support vector machine, discriminant analysis and BP neural network, and define touse least squares support vector machine method. Use the wave bands with peak and troughto screen the efficient, make sure to use F632wave band as the efficient, and utilize principalcomponent analysis method to reduce spectral dimension. Discuss the influence to the modelfrom different factor number, define to use8principal components as input variables andestablish cucumber aphid disease prediction model. The final RMSEP of the prediction set is0.569, accuracy rate is97.5%, correlate coefficient of the true value of prediction set leafsample and predictive value is0.981.
In addition, by the regularity of disease outbreak and actual situation, plant diseases andinsect pests in high contrast with low in hair environmental conditions, Sure the occurrenceof pest and disease conditions threshold. Analyze the maximum, minimum, difference andaverage value of temperature and humidity, and define to utilize average temperature andhumidity as the nosopoietic threshold value. The scopes of temperature and humidity are15℃≤Tmean≤25℃，40%≤RHmean≤70%; moreover, combine and then analyze theparameter of temperature and humidity in June, September and July, August; according tothe calculation of pathogen infection time, judge the continues temperature and humility for6hours, and achieve the scopes of temperature and humility are15℃≤6hTmean≤30℃，50%≤6hRHmean≤100%.
Combine the survey of greenhouse environmental condition with chlorophyll fluorescencesurvey, and construct diseases and insect pests monitoring system of greenhouse cucumber.First of all, by analysing the environmental condition data and after monitoring the thresholdvalue of environmental condition, if the conditions of plant diseases and insect pests’occurrence are satisfied, monitor and analyze the chlorophyll fluorescence data. Accordingto the classified diagnosis model make sure of the occurrence type of plant diseases andinsect pests, and by the prediction model define the degree and situation, and achieve thereports of plant diseases and insect pests judging monitoring and calculating; utilize the earlywarming system to pinpoint monitoring and calculating reports, send the result to maincontrol room, greenhouse and managers, and preserve the data, then a process of earlywarming is accomplished.
引文
[1]国家减灾网. Http://Zaiqing.Casm.Ac.Cn/.
[2]陈栋栋.我国启动农机深松作业补贴[J].农业开发与装备,2009,15(12):8.
[3] Yan’an W, Chunjiang Z, Chuanheng S, Xinting Y, Ming L, Daoliang L. Towards developing an earlywarning system for cucumber diseases for greenhouse in China[J]. Computer andComputing Technologies in Agriculture,2008,259(2):1375-1378.
[4]铁铮.北京温室病虫害应引起重视. Http://News.China-Flower.Com/Paper/Papernewsinfo.Asp?N_Id=111195.
[5]王翠英.温室番茄晚疫病的防治[J].山西农业：致富科技版,2007,15(1):43.
[6]高峰,俞立,卢尚琼,徐青香,于莉洁.国外设施农业的现状及发展趋势[J].浙江林学院学报,2009,23(02):279-285.
[7]张建忠,王学勤,喻景权.绿色环控设施农业:我国设施农业发展的必由之路[J].中国软科学,2007,22(09):17-20.
[8] Chowdhury A, Saswati P, Monidipta S, Nilanjan S. Impact of pesticides on soil microbiologicalparameters and possible bioremediation strategies[J]. Indian Journal of Microbiology,2008,48(1):114-127.
[9]武红敢,石进,蒋丽雅,叶勤文,马圣这,汪润.3S技术在安徽省森林病虫害监测与管理中的应用[C].中国四川成都：中国昆虫学会2001年学术年会:286-292.
[10]武红敢,张建军,王福贵,高树,曹晓东. GPS及其在森林资源管理中的应用前景[J].林业科技通讯,1998,41(08):27-28.
[11]吴坚，马小明，李志清，高树.航空录像遥感技术在森林病虫害监测中的应用[J].林业科学研究,1994,7(05):579-584.
[12]王川. GPS在病虫害监测中的应用[J].中国林业,2006,57(10):36.
[13]林育红,蔡卫群,陈升爱. GPS技术是林业有害生物防控的好助手[J].中国林业,2007,58(05):52.
[14]武红敢,吴坚.差分GPS及其在森林病虫害飞机防治中的研究进展[J].森林病虫通讯,1998,17(04):34-35.
[15] Wadwani A. Application of GPS/GIS technology in pest management[J]. Abstracts of Papers ofthe American Chemical Society,2001,221:49.
[16] Thomas C, Skinner P, Fox A, Greer C, Gubler W. Utilization of GIS/GPS-based informationtechnology in commercial crop decision making in California, Washington, Oregon, Idaho,and Arizona[J]. Journal of Nematology,2002,34(3):200-206.
[17] Li S, Qing Z, Xi C, Jun W, Anming B, Bin Z. Application of the integrated precision farming systemof cotton growing in Xinjiang Region[J]. Nongye Gongcheng Xuebao/Transactions of theChinese Society of Agricultural Engineering,2005,21(8):83-88.
[18] Majewski S. The practical use of GPS and digital maps by Polish State Forests in fire protectionand in pest control [M]. GIS and Databases in the Forest Protection in Central Europe, ed. W.Grodzki.2005.
[19]周定辉,武红敢,斯林,刘清旺. GPS森林病虫害监测数据处理模块设计与开发[J].中国森林病虫,2006,25(03):16-20.
[20]孙浩忠,周燕萍,兰桂芬,姚晓燕. GPS与GIS联合进行森林病虫害监测图件制作[J].农业网络信息,2008,23(11):25-28.
[21]庞月涛. GPS在林业病虫害调查监测中的应用[J].中国林业,2009,60(11):62.
[22] Yingjun X, Mingxia S, Xiangfu Z, Liang Z, Fengxian M. Navigation system for preventing pestsand diseases using agricultural aircraft[J]. Nongye Jixie Xuebao/Transactions of the ChineseSociety of Agricultural Machinery,2010,41(7):153-156+146.
[23] Diofantos G, Philimis P, Psimolophitis E, George K, Themistocleous k. A national system formonitoring the population of agricultural pests using an integrated approach of remotesensing data from in situ automated traps and satellite images [C].Remote Sensing forAgriculture, Ecosystems, and Hydrology XII.2010. Toulouse, France: SPIE, The Society ofPhoto-Optical Instrumentation Engineers (SPIE).
[24] Trond R, Knut S, Arild S, Lars F, Engravslia L. Open geospatial technology standards and theirpotential in plant pest risk management-GPS-enabled mobile phones utilising opengeospatial technology standards Web Feature Service Transactions support the fighting offire blight in Norway[J]. Computers and Electronics in Agriculture,2010,74(2):336-340.
[25]潘锦山.基于3G混合网络和GPS技术的果树移动专家系统（FMES）的构建[D].2010.
[26]朱云开,陈树人,王新忠.地理信息系统的发展及其在精确农业中的应用[J].农机化研究,2007,29(05):179-180.
[27]吴冬琴.基于GIS的小区物业管理系统[D].西安科技大学,2010.
[28]郝涛,钱庆,石道良.地理信息系统在我国森林病虫害信息管理中的应用[J].湖北林业科技,2005,34(03):46-49.
[29]周国娜,高宝嘉,黄选瑞,李帅英.地理信息系统在植物病虫害研究中的应用[J].河北农业大学学报,2003,5(S1):212-216.
[30] Tupper G, Worsley P, Bowler J, Freckelton D, Mcgowen J, Pradhan C, Roger R, Worsley M. Useof remote sensing and GIS technologies by New South Wales Agriculture for eme rgencymanagement[J].2000Intenational Geoscience and Remote Sensing Symposium (IGARSS2000),2000,4:1489-1491.
[31]杨毅,张珍荫,周汝良,周谷荣.基于GIS的森林病虫害防治系统的设计与实现[J].西南农业大学学报(自然科学版),2003,25(04):353-356.
[32] Guo Ying, Li Li, Zhijian Zhou, et al. A WebGIS-based Wide-domain Analysis on the Occurrenceand Development of Disease and Pest in Orchard[C]. International Conference onAgricultural Engineering. Beijing, China,2004:118.
[33]赵朋.基于GIS的苹果病虫害管理信息系统的研究与开发[D].中国农业大学,2005.
[34]司丽丽,曹克强,刘佳鹏,杨军玉,甄文超.基于地理信息系统的全国主要粮食作物病虫害实时监测预警系统的研制[J].植物保护学报,2006,33(03):282-286.
[35] Godelieve L, Petr Z, Christine B, Giuseppe D, Paul M, Paul S, Frans J. Cattle ticks of the generaRhipicephalus and Amblyomma of economic importance in Tanzania: distribution assessedwith GIS based on an extensive field survey[J]. Experimental and Applied Acarology,2007,43(4):303-319.
[36]林惠彬.基于GIS的福建烟草病虫害管理信息系统构建[D].福建农林大学,2008.
[37]宫彦萍,黄文江,王纪华,徐新刚,杨贵军,阎广建.集成GIS和RS技术的作物病虫害监测预报研究进展[J].农业工程学报,2008,24(S2):331-336.
[38]宫彦萍,黄文江,潘瑜春,等.基于WebGIS的作物病虫害监测预报系统构建[J].自然灾害学报,2008,17(06):36-41.
[39]罗菊花,黄文江,韦朝领,王纪华,潘瑜春.基于GIS的农作物病虫害预警系统的初步建立[J].农业工程学报,2008,24(12):127-131.
[40]覃传恒.基于GIS的广西森林病虫害管理信息系统研究[D].广西大学,2008.
[41] Nolte Kurt, John Palumbo, Judith Brown. Integrating GIS in the epidemiology and managementof the cucurbit yellow stunting disease virus (CYSDV)[J]. Hortscience,2008,43(4):1250-1251.
[42] Singh P, Kumar S, Srivastava S, Garg S, Singh V, Bhatnagar S, Singh R. GIS and Remote Sensing inAgriculture[J]. Vegetos,2008,21(1):11-27.
[43] Cheng Xiaoyan, Xiaoli Zhang, Fangyi Xie. Design and development of county-level informationmanagement system for diseases and pests of hebei province on GIS[J]. Computer andComputing Technologies in Agriculture Ii,2009,2:991-1000.
[44] Juhua L, Wenjiang H, Jihua W, Chaoling W. The crop disease and pest warning and predictionsystem[J]. Computer and Computing Technologies in Agriculture Ii,2009,2:937-945.
[45] Latchininsky V, Ramesh S. Locust habitat monitoring and rist assessment using remote sensingand GIS technologies[J]. Integrated Management of Arthropod Pests and Insect BorneDiseases,2010,5:163-188.
[46] Mingyang L, Milan L, Min L, Yunwei J. Prediction of Pine Wilt Disease in Jiangsu Province Basedon Web Dataset and GIS[J]. Web Information Systems and Mining,2010,6318:146-153.
[47] XiaoJun L, Jing C, Liang T, Weixing C, Yan Z. Development and Application of a Model andGIS-Based Decision Support System for Rice Production Management[J]. Zhongguo ShuidaoKexue,2010,24(3):297-302.
[48]刘向锋,孟志军,陈竞平,武文波.作物病虫害信息采集与远程诊断系统设计与实现[J].计算机工程与设计,2011,32(07):2361-2364+2408.
[49] Xinwei W, Guangwei Ren, Fanyu Kong. Development and application of the online managementinformation system in monitoring of tobacco diseases and insect pests [M].20116th IeeeConference on Industrial Electronics and Applications.2011,(6):2399-2402.
[50]易玲,杨小唤,江东,刘红辉.农作物病虫害遥感监测研究进展[J].甘肃科学学报,2003,15(03):58-63.
[51]张田,张晓丽,刘红伟,裴小节.遥感在森林病虫害监测中的应用研究(英文)[J]. PlantDiseases and Pests,2010,38(21):57-62.
[52]王蕾,骆有庆,张晓丽,马钦彦, Heliovaara K,贾林强.遥感技术在森林病虫害监测中的应用研究进展[J].世界林业研究,2008,21(05):37-43.
[53]张家良.遥感技术在农业环保上的应用[J].农业环境科学学报,1985,5(03):35-36+31.
[54]王坤,朱大洲,张东彦,马智宏,黄文江,杨贵军,王成.成像光谱技术在农作物信息诊断中的研究进展[J].光谱学与光谱分析,2011,31(03):589-594.
[55]赵春燕,杨志高.高光谱遥感技术及其在森林监测中的应用探讨[J].林业调查规划,2006,31(01):4-6.
[56]陈蜜,易尧华,刘志刚,李德仁,秦前清.基于分块特性的高光谱影像波段选择方法的研究[J].测绘通报,2006,52(3):24-27.
[57]乔红波.麦蚜、白粉病危害后冬小麦冠层高光谱的测量与分析[D].中国农业科学院,2004.
[58]乔红波,程登发,孙京瑞,田喆,陈林,林芙蓉.麦蚜对小麦冠层光谱特性的影响研究[J].植物保护,2005,43(02):21-26.
[59]乔红波,夏斌,马新明,程登发,周益林.冬小麦病虫害的高光谱识别方法研究[J].麦类作物学报,2010,30(04):770-774.
[60]陈鹏程.地面高光谱遥感在棉叶螨监测中的应用研究[D].石河子大学,2006.
[61]张永强,文丽萍,王振营.高光谱遥感在监测作物受病虫肥胁迫中的应用[C].中国北京：2006中国科协年会.
[62]李向阳.烟草高光谱特性与农艺、生理、品质指标关系和估测模型研究[D].河南农业大学,2007.
[63]赵丽芳.利用Hypeion高光谱遥感数据估测森林叶面积指数[D].北京林业大学,2007.
[64]齐静,程登发,张云慧,孙京瑞.马铃薯甲虫危害后马铃薯冠层光谱数据分析[C].中国湖北武汉：中国植物保护学会2009年学术年会.
[65]王植,曹均,曹庆昌,李红.高光谱遥感监测板栗病虫害的可行性初探[J].中国农学通报,2010,26(13):380-384.
[66]殷晓平.基于高光谱图像的黄瓜叶片叶绿素含量及其分布预测研究[D].江苏大学,2010.
[67]张杰.冬小麦倒伏遥感监测研究[D].山东师范大学,2011.
[68]宋瑜,宋晓东,郭青海,唐立娜.太湖藻华水体的遥感监测与预警[J].光谱学与光谱分析,2011,31(03):753-757.
[69]张东彦,张竞成,朱大洲,王纪华,罗菊花,赵晋陵,黄文江.小麦叶片胁迫状态下的高光谱图像特征分析研究[J].光谱学与光谱分析,2011,31(04):1101-1105.
[70]杨战国.曲古菌素A体外作用HeLa细胞的光谱学研究[D].郑州大学,2009.
[71]张瑞美,彭世彰,徐俊增.光谱技术在农业领域的应用与展望[J].节水灌溉,2006,31(05):1-5.
[72]张宏名,严衍禄,金瑞华,黄可训.苹果害螨为害叶等级的光谱鉴别法[J].植物保护学报,1991,30(03):221-224.
[73]聂志东,韩建国,张录达,李军会.近红外光谱技术(NIRS)在草地生态学研究中的应用[J].光谱学与光谱分析,2007,27(04):691-696.
[74]李书英,韩建国.近红外光谱技术在高尔夫草坪管理中的应用[J].光谱学与光谱分析,2008,28(07):1539-1543.
[75]任卫波,韩建国,张蕴薇,郭慧琴.近红外光谱分析原理及其在牧草航天育种的应用前景[J].光谱学与光谱分析,2008,28(02):303-307.
[76]冯洁,廖宁放,梁敏勇,赵波,戴志强.用于植物病虫害诊断的多光谱成像系统[J].光谱学与光谱分析,2009,29(04):1008-1012.
[77]冯洁,廖宁放,赵波,罗永道,李宝聚.常见黄瓜病害的多光谱诊断[J].光谱学与光谱分析,2009,29(02):467-470.
[78]邢东兴,常庆瑞.基于光谱反射率的果树病虫害级别定量化测评——以红富士苹果树黄叶病害、红蜘蛛虫害为例[J].西北农林科技大学学报(自然科学版),2009,74(11):143-148+155.
[79]周志艳,臧英,沈斌斌.多光谱视觉检测系统及其在稻飞虱发生早期检测中的应用[J].现代科学仪器,2010,17(02):10-14.
[80] Buonasera K, Lambreva M, Rea G, Touloupakis E, Giardi M. Technological applications ofchlorophyll a fluorescence for the assessment of environmental pollutants[J]. Analytical andBioanalytical Chemistry,2011,401(4):1139-1151.
[81] Ralph P, Smith R, Macinnis C, Seery C. Use of fluorescence-based ecotoxicological bioassays inmonitoring toxicants and pollution in aquatic systems: Review[J]. Toxicological andEnvironmental Chemistry,2007,89(1):589-607.
[82] Venediktov P, Kazimirko Y, Krendeleva T, Kukarskikh G, Makarova V, Yakovleva S, Rubin A.Assessing the physiological state of woody plants by parameters of chlorophyll fluorescencein the bark of annual shoots[J]. Ekologiya (Moscow),2000,(5):338-342.
[83] Bounfour M, Tanigoshi L, Chen C, Cameron S, Klauer S. Chlorophyll content and chlorophyllfluorescence in red raspberry leaves infested with Tetranychus urticae and Eotetranychuscarpini borealis (Acari: Tetranychidae)[J]. Environmental Entomology,2002,31(2):215-220.
[84] Bassanezi R, Amorim L, Bergamin F, Berger R. Gas exchange and emission of chlorophyllfluorescence during the monocycle of rust, angular leaf spot and anthracnose on beanleaves as a function of their trophic characteristics[J]. Journal of Phytopathology (Berlin),2002,150(1):37-47.
[85] Dewez D, Marchand M, Eullaffroy P, Popovic R. Evaluation of the effects of diuron and itsderivatives on Lemna gibba using a fluorescence toxicity index[J]. Environmental Toxicology,2002,17(5):493-501.
[86] Percival G, Gillian A. The influence of powdery mildew infection on photosynthesis, chlorophyllfluorescence, leaf chlorophyll and carotenoid content of three woody plant species[J].Arboricultural Journal,2002,26(4):333-346.
[87] Seguin F, Bihan F, Leboulanger C, Annette B. A risk assessment of pollution: induction ofatrazine tolerance in phytoplankton communities in freshwater outdoor mesocosms, usingchlorophyll fluorescence as an endpoint[J]. Water Research,2002,36(13):3227-3236.
[88] Eullaffroy P, Vernet G. The F684/F735chlorophyll fluorescence ratio: a potential tool for rapiddetection and determination of herbicide phytotoxicity in algae[J]. Water Research,2003,37(9):1983-1990.
[89] Korres N, Froud-Williams R, Moss S. Chlorophyll fluorescence technique as a rapid diagnostictest of the effects of the photosynthetic inhibitor chlorotoluron on two winter wheatcultivars[J]. Annals of Applied Biology,2003,143(1):53-56.
[90] Moya I, Camenen L, Evain S, Goulas Y, Cerovic Z, Latouche G, Flexas J, Ounis A. Latouche, J.Flexas, A. Ounis. A new instrument for passive remote sensing1. Measurements ofsunlight-induced chlorophyll fluorescence[J]. Remote Sensing of Environment,2004,91(2):186-197.
[91] Abbaspoor M, Streibig J. Clodinafop changes the chlorophyll fluorescence induction curve[J].Weed Science,2005,53(1):1-9.
[92] Schmitz A, Iryna I. Tartachnyk, Sebastian Kiewnick, Richard A. Sikora, Walter Kuehbauch.Detection of Heterodera schachdi infestation in sugar beet by means of laser-induced andpulse amplitude modulated chlorophyll fluorescence[J]. Nematology,2006,8:273-286.
[93] Francisco S, Maria J. Studying photosynthesis by measuring fluorescence[J]. Journal ofBiological Education,2006,41(1):34-37.
[94] Strom D, Ralph P, Stauber J. Development of a Toxicity Identification Evaluation Protocol UsingChlorophyll-a Fluorescence in a Marine Microalga[J]. Archives of EnvironmentalContamination and Toxicology,2009,56(1):30-38.
[95] Suarez A, Patricio G, Alvaro S, Jose J. HUMANN-based system to identify benzimidazolefungicides using multi-synchronous fluorescence spectra: An ensemble approach[J].Analytical and Bioanalytical Chemistry,2009,394(4):1059-1072.
[96] Gantner M, Wladyslaw M. Measurements of chlorophyll fluorescence as an auxiliary method inestimating susceptibility of cultivated hazel (Corylus L.) For filbertaphid (Myzocallis coryliGoetze)[J]. Acta Agrobotanica,2010,63(1):189-195.
[97] Jinjun X, Adnan M, Michael T, Haidikker M. Stink bug feeding induces fluorescence indeveloping cotton bolls[J]. Journal of biological engineering,2011,5(1):11.
[98]顾月清,陶宝祺,钱志余.激光诱导荧光及其应用[J].激光与光电子学进展,1996,7:22-24.
[99]陈莲花.表面活性剂对铜绿微囊藻生长及光合作用的影响[D].南昌大学,2008.
[100]彭菊芳,王水才,贺俊芳,蔡霞,刘晓,匡廷云.捕光天线LHC II的荧光光谱特性研究[J].光子学报,2004,33(1):56.
[101]于光辉.生殖生长期两优培九功能叶光反应特性[J].作物学报,2010,36(11):1959-1966.
[102]李鹏民,高辉远.快速叶绿素荧光诱导动力学分析在光合作用研究中的应用[J].植物生理与分子生物学学报,2005,31(6):559-566.
[103] Rohacek K, Bartak M. Technique of the modulated chlorophyll fluoreacence: basic concepts,useful parametern, and some applications[J]. Photosynthetic,1999,27(3):339-363.
[104] Polo C, Frisardi A, Resnik E, Schoua A, Batlle A. Factors influencing fluorescence spectra of freeporphyrins[J]. Clinical chemistry,1988,34(4):757-60.
[105] Patsayeva S, Reuter R. Temperature dependence of fluorescence spectra of natural organicmatter in seawater [M]. Geoinformation for European-Wide Integration, ed. T. Benes.2003.
[106] Mrozek J, Rzeska A, Guzow K, Karolczak J, Wiczk W. Influence of alkyl group on amide nitrogenatom on fluorescence quenching of tyrosine amide and N-acetyltyrosine amide[J].Biophysical Chemistry,2004,111(2):105-113.
[107]杨昊谕.基于叶绿素荧光光谱分析的植物生理信息检测技术研究[D].吉林大学,2010.
[108]荆卉婷.利用傅立叶变换求解压缩态光场的输出模[J].苏州科技学院学报,2009,26(3):17-19+28.
[109]杨勇兵.一种新型的快速模板匹配算法[J].电子工艺技术,2010,41(3):128-131.
[110]林振宇.几种化学计量学模型的建立及其应用研究[D].福州大学,2002.
[111] Chatni M, Yale G, Ryckeghem A. Frequency Domain Fluorescence Lifetime Microwell-PlatePlatform for Respirometry Measurements[J]. Smart Biomedical and Physiological SensorTechnologies Vii,2010.
[112]祝诗平.近红外光谱品质检测方法研究[D].中国农业大学,2003.
[113]李慷.道路养护支持信息系统的研究与开发[D].长安大学,2011.
[114]宋丽华.花生籽仁蛋白质含量近红外光谱模型的建立及育种应用[D].河北农业大学,2011.
[115]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[J].光谱学与光谱分析,2007,27(05):877-880.
[116]郭婷婷,邬文锦,苏谦,王守觉,安冬.近红外玉米品种鉴别系统预处理和波长选择方法[J].农业机械学报,2009,40(S1):87-92.
[117]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[J].光谱学与光谱分析,2004,24(12):1546-1548.
[118]赵环环,严衍禄.噪声对近红外光谱分析的影响及相应的数学处理方法[J].光谱学与光谱分析,2006,26(05):842-845.
[119]刘丽丽.基于超高压预处理的蔬菜农药残留近红外检测技术的初步研究[D].吉林大学,2009.
[120]王福民,黄敬峰,徐俊锋，王秀珍.基于光谱波段自相关的水稻信息提取波段选择[J].光谱学与光谱分析,2008,28(5):1098-1101.
[121] Thenkabail P, Enclona E, Ashton M. Plus Sensors in the Study of African Rainforests[J]. RemoteSensing of Environment,2004,90(1):23-43.
[122]苏荣国,梁生康,胡序朋,王修林.荧光光谱结合主成分分析对硅藻和甲藻的识别测定[J].海洋科学进展,2007,25(2):238-246.
[123]李静萍,谢邦国.多元统计分析：方法与应用,北京：中国人民大学出版社.2008.
[124]高荣强,范世福,严衍禄,赵丽丽.近红外光谱的数据预处理研究[J].光谱学与光谱分析,2004,24(12):1563-1565.
[125]杨苗,杨萍果.基于小波变换的光谱分析法预测土壤总氮含量[J].山西师范大学学报(自然科学版),2011,26(02):85-89.
[126]张旭.中国巨型城市的发展与动力研究[D].中山大学,2010.
[127]蒋骏,贾志宽,徐春明,刘玉华.苜蓿冠层温度与农艺性状的相关分析[J].干旱地区农业研究,2003,21(04):20-22.
[128]陈斌,王豪,林松,赵杰文.基于相关系数法与遗传算法的啤酒酒精度近红外光谱分析[J].农业工程学报,2005,21(07):99-102.
[129]秦蓓蕾,王文圣,丁晶.偏最小二乘回归模型在水文相关分析中的应用[J].四川大学学报(工程科学版),2003,7(04):115-118.
[130]李世欣,温建,邵孝侯,王晓亚,王玉英.偏最小二乘法与人工神经网络耦合的小流域产沙模型[J].河海大学学报(自然科学版),2010,54(02):149-153.
[131]李晓松,李增元,高志海,白黎娜,王琫瑜.基于NDVI与偏最小二乘回归的荒漠化地区植被覆盖度高光谱遥感估测[J].中国沙漠,2011,31(01):162-167.
[132]沈铁峰,黄德生,吴伟,关鹏,周宝森. Bayes判别分析在肾综合征出血热发病预测研究中的应用[J].中国媒介生物学及控制杂志,2009,16(02):147-150.
[133]胡小平,梁承华,杨之为,李振岐.植物病虫害BP神经网络预测系统的研制与应用[J].西北农林科技大学学报(自然科学版),2001,29(02):73-76.
[134]梁曼君，石竹，韩江洪.基于BP神经网络的棉花病虫害诊断系统[J].微电子学与计算机,1996,25(03):35-37+40.
[135]喻丽华,陆晓燕.神经网络知识获取及推理技术在番茄专家系统中的应用[J].贵州工业大学学报(自然科学版),2004(05):83-85+95.
[136]李华,魏开来,高捷,王华.人工神经网络在葡萄霜霉病预测中的应用[J].农机化研究,2008,30(08):160-162+166.
[137]陈怀亮,张弘,李有.农作物病虫害发生发展气象条件及预报方法研究综述[J].中国农业气象,2007,29(02):212-216.
[138]冯沈萍,孙凡.运用人工神经网络预测一代粘虫发生程度的研究[J].微型电脑应用,1999,16(10):45-47.
[139]吴小红,蒋星华.优化BP神经网络在森林病虫害预测中的应用[J].现代电子技术,2007,31(01):138-140.
[140]孙凡,陈汉容.稻瘿蚊发生趋势的BP网络预测模型[J].计算机仿真,2000,17(03):61-63.
[141]杨保俊,叶卫京.人工智能技术在桑病虫预测预报中的应用[J].蚕桑通报,2001,48(01):29-32.
[142]冯旭东,陈方.神经网络在病虫害诊断中的应用[J].电脑开发与应用,1999,15(01):26-28.
[143] Cortes C, Vapnik V. Machine Learning,1995,20(3):273.
[144] Vapnik V. The Nature of Statistical Learning Theory. New York:Springer-Verlag,1955.
[145] Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and OtherKerner-based Learning Methods.Beijing:Publishing House of Electronics Industry,2004.
[146] Naiyang D, Yingjie T. New Method of Data Minning Support Vector Machine.Beijing:SciencePress,2004.
[147]石晶晶,刘占宇,张莉丽,周湾,黄敬峰.基于支持向量机(SVM)的稻纵卷叶螟危害水稻高光谱遥感识别[J].中国水稻科学,2009,23(03):331-334.
[148]刘凯军.支持向量机研究及其在货币识别中的应用[D].西安理工大学,2004.
[149]刘婷.棉蚜天敌图像的分类识别研究[D].西北农林科技大学,2010.
[150]邵咏妮.水稻生长生理特征信息快速无损获取技术的研究[D].浙江大学,2010.
[151]雷冯,陈双双,冯斌,刘飞,何勇,楼兵干.基于光谱技术的大豆豆荚炭疽病早期鉴别方法[J].农业工程学报,2012,28(1):139-144.
[152] Bin L, Hongye S, Weihua H, Jian C. Temperature Prediction Control based on Least SquaresSupport Vector Machines [J]. Journal of Control Theory and Application,2004,8(4):365-370.
[153]孙光明,杨凯盛,张传清,吴迪,何勇,冯雷.基于多光谱成像技术的大麦赤霉病识别[J].农业工程学报,2009,25(S2):204-207.
[154]李先锋,朱伟兴,纪滨,刘波.基于特征优化和LS-SVM的棉田杂草识别[J].农业机械学报,2010,41(11):168-172.
[155]虞佳佳,邹伟,何勇,等.基于近红外反射光谱的外来入侵植物的辨识[J].光谱学与光谱分析,2009,29(11):2955-2958.
[156]徐新刚,赵春江,王纪华,徐正浩.新型光谱曲线特征参数与水稻叶绿素含量间的关系研究[J].光谱学与光谱分析,2011,31(01):188-191.
[157] Huimin W, Nianhui Z, Linfang D. Protein endogenous fluorescence to examine the influence ofsolution pH on PSII of two peripheral protein conformation [J]. Journal of Sichuan University (Natural Science Edit ion),2004,41(5):1059-1063.
[158]李霞,刘友良,焦德茂.不同高产水稻品种叶片的荧光参数的日变化和光适应特性的关系[J].作物学报,2002,28(2):145-153.
[159]潘瑞炽,植物生理学:北京：高等教育出版社.2004:63-64.
[160]林世青,许春辉,张其德,徐黎,毛大璋,匡廷云.叶绿素荧光动力学在植物抗性生理学、生态学和农业现代化中的应用[J].植物学报,1992,9(1):1-16.
[161]杨虎清,周存山,霍艳荣,庞林江,王允祥.利用叶绿素荧光预测水蜜桃果实冷害的研究[J].园艺学报,2008,35(7):945-950.
[162]徐彬彬,石晓日,李德成,周斌,沈玉其,朱永豪,张崇静,吴荣,刘南英.不同施肥条件下玉米的荧光光谱特征及其在遥感中应用的可能性[J].环境遥感,1992,7(S1):51-59.
[163]杨昊谕,于海业,张蕾,隋媛媛.基于激光诱导荧光光谱分析的黄瓜叶片叶绿素含量检测[J].农业机械学报,2009,40(10):169-172.
[164]苏荣国,胡序朋,张传松,王修林.基于活体荧光的藻类识别测定技术[J].热带海洋学报,2008,27(05):24-29.
[165]张永江,赵春江,刘良云,王纪华,马智宏,王人潮.被动荧光探测水分胁迫对玉米叶片影响的初步研究[J].农业工程学报,2006,23(09):39-43.
[166] Lichtenthaler K,王可玢.以体内叶绿素荧光检测植物的逆境因素[J].生物技术通报,1992,8(02):1-4.
[167] Schmuck G, Lichtenthaler H, Application of laser-induced chlorophyll-a fluorescence in theforest decline research[J]. International Geoscience and Remote Sensing Symposium(IGARSS).1986:1587-1590.
[168]庞金安,马德华,李淑菊.黄瓜光合作用的研究[J].天津农业科学,1997,3(4):8-15.
[169]许大全.气孔不均匀关闭与光合作用的非气孔限制[J].植物生理学通讯,1995,31(4):246-252.
[170]董振国,于沪宁.农田光合有效辐射观测与分析[J].气象,1983,7:23-24.
[171]郑健,蔡焕杰,王健,王燕.日光温室内光合有效辐射基本特征分析[J].农业机械学报,2009,42(12):164-168.
[172]李少昆.关于光合速率与作物产量关系的讨论（综述）[J].石河子大学学报（自然科学版）,1998,16(S1):117-126.
[173] Oweis T, Ahmed H, Mustafa P. Water use efficiency of winter-sown chickpea undersupplemental irrigation in a mediterranean environment[J]. Agricultural WaterManagement,2004,66:163-179.
[174] Kramer P, Kozlowski T. Physiology of woody plants [M]. London: Academic Press.1979:443-444.
[175]李荣生,许煌灿,尹光天,杨锦昌,李双忠.植物水分利用效率的研究进展[J].林业科学研究,2003,16(3):366-371.
[176]于晓芳,高聚林,宋国栋,王志刚,桑丹丹,叶君.玉米叶片水分利用效率与叶绿素a荧光参数的关系[J].玉米科学,2009,17(4):55-57.
[177] XiaoJuan T, Jun L, Qiang Y, Zhong Q. Ecosystem water use efficiency in an irrigated cropland inthe North China Plain[J]. Journal of Hydrology,2009,374(3):329-337.
[178] YongJiang Z, LiangYun L, MingYu H. Progress in remote sensing of vegetation chlorophyllfluorescence[J]. Journal of Remote Sensing,2009,13(5):963-970.
[179] Guifang W, Yong H. Identification of Varieties of Cashmere by Vis/NIR SpectroscopyTechnology Based on PCA SVM[J]. Spectroscopy and Spectral Analysis,2009,29(6):1541-1544.
[2]陈栋栋.我国启动农机深松作业补贴[J].农业开发与装备,2009,15(12):8.
[3] Yan’an W, Chunjiang Z, Chuanheng S, Xinting Y, Ming L, Daoliang L. Towards developing an earlywarning system for cucumber diseases for greenhouse in China[J]. Computer andComputing Technologies in Agriculture,2008,259(2):1375-1378.
[4]铁铮.北京温室病虫害应引起重视. Http://News.China-Flower.Com/Paper/Papernewsinfo.Asp?N_Id=111195.
[5]王翠英.温室番茄晚疫病的防治[J].山西农业：致富科技版,2007,15(1):43.
[6]高峰,俞立,卢尚琼,徐青香,于莉洁.国外设施农业的现状及发展趋势[J].浙江林学院学报,2009,23(02):279-285.
[7]张建忠,王学勤,喻景权.绿色环控设施农业:我国设施农业发展的必由之路[J].中国软科学,2007,22(09):17-20.
[8] Chowdhury A, Saswati P, Monidipta S, Nilanjan S. Impact of pesticides on soil microbiologicalparameters and possible bioremediation strategies[J]. Indian Journal of Microbiology,2008,48(1):114-127.
[9]武红敢,石进,蒋丽雅,叶勤文,马圣这,汪润.3S技术在安徽省森林病虫害监测与管理中的应用[C].中国四川成都：中国昆虫学会2001年学术年会:286-292.
[10]武红敢,张建军,王福贵,高树,曹晓东. GPS及其在森林资源管理中的应用前景[J].林业科技通讯,1998,41(08):27-28.
[11]吴坚，马小明，李志清，高树.航空录像遥感技术在森林病虫害监测中的应用[J].林业科学研究,1994,7(05):579-584.
[12]王川. GPS在病虫害监测中的应用[J].中国林业,2006,57(10):36.
[13]林育红,蔡卫群,陈升爱. GPS技术是林业有害生物防控的好助手[J].中国林业,2007,58(05):52.
[14]武红敢,吴坚.差分GPS及其在森林病虫害飞机防治中的研究进展[J].森林病虫通讯,1998,17(04):34-35.
[15] Wadwani A. Application of GPS/GIS technology in pest management[J]. Abstracts of Papers ofthe American Chemical Society,2001,221:49.
[16] Thomas C, Skinner P, Fox A, Greer C, Gubler W. Utilization of GIS/GPS-based informationtechnology in commercial crop decision making in California, Washington, Oregon, Idaho,and Arizona[J]. Journal of Nematology,2002,34(3):200-206.
[17] Li S, Qing Z, Xi C, Jun W, Anming B, Bin Z. Application of the integrated precision farming systemof cotton growing in Xinjiang Region[J]. Nongye Gongcheng Xuebao/Transactions of theChinese Society of Agricultural Engineering,2005,21(8):83-88.
[18] Majewski S. The practical use of GPS and digital maps by Polish State Forests in fire protectionand in pest control [M]. GIS and Databases in the Forest Protection in Central Europe, ed. W.Grodzki.2005.
[19]周定辉,武红敢,斯林,刘清旺. GPS森林病虫害监测数据处理模块设计与开发[J].中国森林病虫,2006,25(03):16-20.
[20]孙浩忠,周燕萍,兰桂芬,姚晓燕. GPS与GIS联合进行森林病虫害监测图件制作[J].农业网络信息,2008,23(11):25-28.
[21]庞月涛. GPS在林业病虫害调查监测中的应用[J].中国林业,2009,60(11):62.
[22] Yingjun X, Mingxia S, Xiangfu Z, Liang Z, Fengxian M. Navigation system for preventing pestsand diseases using agricultural aircraft[J]. Nongye Jixie Xuebao/Transactions of the ChineseSociety of Agricultural Machinery,2010,41(7):153-156+146.
[23] Diofantos G, Philimis P, Psimolophitis E, George K, Themistocleous k. A national system formonitoring the population of agricultural pests using an integrated approach of remotesensing data from in situ automated traps and satellite images [C].Remote Sensing forAgriculture, Ecosystems, and Hydrology XII.2010. Toulouse, France: SPIE, The Society ofPhoto-Optical Instrumentation Engineers (SPIE).
[24] Trond R, Knut S, Arild S, Lars F, Engravslia L. Open geospatial technology standards and theirpotential in plant pest risk management-GPS-enabled mobile phones utilising opengeospatial technology standards Web Feature Service Transactions support the fighting offire blight in Norway[J]. Computers and Electronics in Agriculture,2010,74(2):336-340.
[25]潘锦山.基于3G混合网络和GPS技术的果树移动专家系统（FMES）的构建[D].2010.
[26]朱云开,陈树人,王新忠.地理信息系统的发展及其在精确农业中的应用[J].农机化研究,2007,29(05):179-180.
[27]吴冬琴.基于GIS的小区物业管理系统[D].西安科技大学,2010.
[28]郝涛,钱庆,石道良.地理信息系统在我国森林病虫害信息管理中的应用[J].湖北林业科技,2005,34(03):46-49.
[29]周国娜,高宝嘉,黄选瑞,李帅英.地理信息系统在植物病虫害研究中的应用[J].河北农业大学学报,2003,5(S1):212-216.
[30] Tupper G, Worsley P, Bowler J, Freckelton D, Mcgowen J, Pradhan C, Roger R, Worsley M. Useof remote sensing and GIS technologies by New South Wales Agriculture for eme rgencymanagement[J].2000Intenational Geoscience and Remote Sensing Symposium (IGARSS2000),2000,4:1489-1491.
[31]杨毅,张珍荫,周汝良,周谷荣.基于GIS的森林病虫害防治系统的设计与实现[J].西南农业大学学报(自然科学版),2003,25(04):353-356.
[32] Guo Ying, Li Li, Zhijian Zhou, et al. A WebGIS-based Wide-domain Analysis on the Occurrenceand Development of Disease and Pest in Orchard[C]. International Conference onAgricultural Engineering. Beijing, China,2004:118.
[33]赵朋.基于GIS的苹果病虫害管理信息系统的研究与开发[D].中国农业大学,2005.
[34]司丽丽,曹克强,刘佳鹏,杨军玉,甄文超.基于地理信息系统的全国主要粮食作物病虫害实时监测预警系统的研制[J].植物保护学报,2006,33(03):282-286.
[35] Godelieve L, Petr Z, Christine B, Giuseppe D, Paul M, Paul S, Frans J. Cattle ticks of the generaRhipicephalus and Amblyomma of economic importance in Tanzania: distribution assessedwith GIS based on an extensive field survey[J]. Experimental and Applied Acarology,2007,43(4):303-319.
[36]林惠彬.基于GIS的福建烟草病虫害管理信息系统构建[D].福建农林大学,2008.
[37]宫彦萍,黄文江,王纪华,徐新刚,杨贵军,阎广建.集成GIS和RS技术的作物病虫害监测预报研究进展[J].农业工程学报,2008,24(S2):331-336.
[38]宫彦萍,黄文江,潘瑜春,等.基于WebGIS的作物病虫害监测预报系统构建[J].自然灾害学报,2008,17(06):36-41.
[39]罗菊花,黄文江,韦朝领,王纪华,潘瑜春.基于GIS的农作物病虫害预警系统的初步建立[J].农业工程学报,2008,24(12):127-131.
[40]覃传恒.基于GIS的广西森林病虫害管理信息系统研究[D].广西大学,2008.
[41] Nolte Kurt, John Palumbo, Judith Brown. Integrating GIS in the epidemiology and managementof the cucurbit yellow stunting disease virus (CYSDV)[J]. Hortscience,2008,43(4):1250-1251.
[42] Singh P, Kumar S, Srivastava S, Garg S, Singh V, Bhatnagar S, Singh R. GIS and Remote Sensing inAgriculture[J]. Vegetos,2008,21(1):11-27.
[43] Cheng Xiaoyan, Xiaoli Zhang, Fangyi Xie. Design and development of county-level informationmanagement system for diseases and pests of hebei province on GIS[J]. Computer andComputing Technologies in Agriculture Ii,2009,2:991-1000.
[44] Juhua L, Wenjiang H, Jihua W, Chaoling W. The crop disease and pest warning and predictionsystem[J]. Computer and Computing Technologies in Agriculture Ii,2009,2:937-945.
[45] Latchininsky V, Ramesh S. Locust habitat monitoring and rist assessment using remote sensingand GIS technologies[J]. Integrated Management of Arthropod Pests and Insect BorneDiseases,2010,5:163-188.
[46] Mingyang L, Milan L, Min L, Yunwei J. Prediction of Pine Wilt Disease in Jiangsu Province Basedon Web Dataset and GIS[J]. Web Information Systems and Mining,2010,6318:146-153.
[47] XiaoJun L, Jing C, Liang T, Weixing C, Yan Z. Development and Application of a Model andGIS-Based Decision Support System for Rice Production Management[J]. Zhongguo ShuidaoKexue,2010,24(3):297-302.
[48]刘向锋,孟志军,陈竞平,武文波.作物病虫害信息采集与远程诊断系统设计与实现[J].计算机工程与设计,2011,32(07):2361-2364+2408.
[49] Xinwei W, Guangwei Ren, Fanyu Kong. Development and application of the online managementinformation system in monitoring of tobacco diseases and insect pests [M].20116th IeeeConference on Industrial Electronics and Applications.2011,(6):2399-2402.
[50]易玲,杨小唤,江东,刘红辉.农作物病虫害遥感监测研究进展[J].甘肃科学学报,2003,15(03):58-63.
[51]张田,张晓丽,刘红伟,裴小节.遥感在森林病虫害监测中的应用研究(英文)[J]. PlantDiseases and Pests,2010,38(21):57-62.
[52]王蕾,骆有庆,张晓丽,马钦彦, Heliovaara K,贾林强.遥感技术在森林病虫害监测中的应用研究进展[J].世界林业研究,2008,21(05):37-43.
[53]张家良.遥感技术在农业环保上的应用[J].农业环境科学学报,1985,5(03):35-36+31.
[54]王坤,朱大洲,张东彦,马智宏,黄文江,杨贵军,王成.成像光谱技术在农作物信息诊断中的研究进展[J].光谱学与光谱分析,2011,31(03):589-594.
[55]赵春燕,杨志高.高光谱遥感技术及其在森林监测中的应用探讨[J].林业调查规划,2006,31(01):4-6.
[56]陈蜜,易尧华,刘志刚,李德仁,秦前清.基于分块特性的高光谱影像波段选择方法的研究[J].测绘通报,2006,52(3):24-27.
[57]乔红波.麦蚜、白粉病危害后冬小麦冠层高光谱的测量与分析[D].中国农业科学院,2004.
[58]乔红波,程登发,孙京瑞,田喆,陈林,林芙蓉.麦蚜对小麦冠层光谱特性的影响研究[J].植物保护,2005,43(02):21-26.
[59]乔红波,夏斌,马新明,程登发,周益林.冬小麦病虫害的高光谱识别方法研究[J].麦类作物学报,2010,30(04):770-774.
[60]陈鹏程.地面高光谱遥感在棉叶螨监测中的应用研究[D].石河子大学,2006.
[61]张永强,文丽萍,王振营.高光谱遥感在监测作物受病虫肥胁迫中的应用[C].中国北京：2006中国科协年会.
[62]李向阳.烟草高光谱特性与农艺、生理、品质指标关系和估测模型研究[D].河南农业大学,2007.
[63]赵丽芳.利用Hypeion高光谱遥感数据估测森林叶面积指数[D].北京林业大学,2007.
[64]齐静,程登发,张云慧,孙京瑞.马铃薯甲虫危害后马铃薯冠层光谱数据分析[C].中国湖北武汉：中国植物保护学会2009年学术年会.
[65]王植,曹均,曹庆昌,李红.高光谱遥感监测板栗病虫害的可行性初探[J].中国农学通报,2010,26(13):380-384.
[66]殷晓平.基于高光谱图像的黄瓜叶片叶绿素含量及其分布预测研究[D].江苏大学,2010.
[67]张杰.冬小麦倒伏遥感监测研究[D].山东师范大学,2011.
[68]宋瑜,宋晓东,郭青海,唐立娜.太湖藻华水体的遥感监测与预警[J].光谱学与光谱分析,2011,31(03):753-757.
[69]张东彦,张竞成,朱大洲,王纪华,罗菊花,赵晋陵,黄文江.小麦叶片胁迫状态下的高光谱图像特征分析研究[J].光谱学与光谱分析,2011,31(04):1101-1105.
[70]杨战国.曲古菌素A体外作用HeLa细胞的光谱学研究[D].郑州大学,2009.
[71]张瑞美,彭世彰,徐俊增.光谱技术在农业领域的应用与展望[J].节水灌溉,2006,31(05):1-5.
[72]张宏名,严衍禄,金瑞华,黄可训.苹果害螨为害叶等级的光谱鉴别法[J].植物保护学报,1991,30(03):221-224.
[73]聂志东,韩建国,张录达,李军会.近红外光谱技术(NIRS)在草地生态学研究中的应用[J].光谱学与光谱分析,2007,27(04):691-696.
[74]李书英,韩建国.近红外光谱技术在高尔夫草坪管理中的应用[J].光谱学与光谱分析,2008,28(07):1539-1543.
[75]任卫波,韩建国,张蕴薇,郭慧琴.近红外光谱分析原理及其在牧草航天育种的应用前景[J].光谱学与光谱分析,2008,28(02):303-307.
[76]冯洁,廖宁放,梁敏勇,赵波,戴志强.用于植物病虫害诊断的多光谱成像系统[J].光谱学与光谱分析,2009,29(04):1008-1012.
[77]冯洁,廖宁放,赵波,罗永道,李宝聚.常见黄瓜病害的多光谱诊断[J].光谱学与光谱分析,2009,29(02):467-470.
[78]邢东兴,常庆瑞.基于光谱反射率的果树病虫害级别定量化测评——以红富士苹果树黄叶病害、红蜘蛛虫害为例[J].西北农林科技大学学报(自然科学版),2009,74(11):143-148+155.
[79]周志艳,臧英,沈斌斌.多光谱视觉检测系统及其在稻飞虱发生早期检测中的应用[J].现代科学仪器,2010,17(02):10-14.
[80] Buonasera K, Lambreva M, Rea G, Touloupakis E, Giardi M. Technological applications ofchlorophyll a fluorescence for the assessment of environmental pollutants[J]. Analytical andBioanalytical Chemistry,2011,401(4):1139-1151.
[81] Ralph P, Smith R, Macinnis C, Seery C. Use of fluorescence-based ecotoxicological bioassays inmonitoring toxicants and pollution in aquatic systems: Review[J]. Toxicological andEnvironmental Chemistry,2007,89(1):589-607.
[82] Venediktov P, Kazimirko Y, Krendeleva T, Kukarskikh G, Makarova V, Yakovleva S, Rubin A.Assessing the physiological state of woody plants by parameters of chlorophyll fluorescencein the bark of annual shoots[J]. Ekologiya (Moscow),2000,(5):338-342.
[83] Bounfour M, Tanigoshi L, Chen C, Cameron S, Klauer S. Chlorophyll content and chlorophyllfluorescence in red raspberry leaves infested with Tetranychus urticae and Eotetranychuscarpini borealis (Acari: Tetranychidae)[J]. Environmental Entomology,2002,31(2):215-220.
[84] Bassanezi R, Amorim L, Bergamin F, Berger R. Gas exchange and emission of chlorophyllfluorescence during the monocycle of rust, angular leaf spot and anthracnose on beanleaves as a function of their trophic characteristics[J]. Journal of Phytopathology (Berlin),2002,150(1):37-47.
[85] Dewez D, Marchand M, Eullaffroy P, Popovic R. Evaluation of the effects of diuron and itsderivatives on Lemna gibba using a fluorescence toxicity index[J]. Environmental Toxicology,2002,17(5):493-501.
[86] Percival G, Gillian A. The influence of powdery mildew infection on photosynthesis, chlorophyllfluorescence, leaf chlorophyll and carotenoid content of three woody plant species[J].Arboricultural Journal,2002,26(4):333-346.
[87] Seguin F, Bihan F, Leboulanger C, Annette B. A risk assessment of pollution: induction ofatrazine tolerance in phytoplankton communities in freshwater outdoor mesocosms, usingchlorophyll fluorescence as an endpoint[J]. Water Research,2002,36(13):3227-3236.
[88] Eullaffroy P, Vernet G. The F684/F735chlorophyll fluorescence ratio: a potential tool for rapiddetection and determination of herbicide phytotoxicity in algae[J]. Water Research,2003,37(9):1983-1990.
[89] Korres N, Froud-Williams R, Moss S. Chlorophyll fluorescence technique as a rapid diagnostictest of the effects of the photosynthetic inhibitor chlorotoluron on two winter wheatcultivars[J]. Annals of Applied Biology,2003,143(1):53-56.
[90] Moya I, Camenen L, Evain S, Goulas Y, Cerovic Z, Latouche G, Flexas J, Ounis A. Latouche, J.Flexas, A. Ounis. A new instrument for passive remote sensing1. Measurements ofsunlight-induced chlorophyll fluorescence[J]. Remote Sensing of Environment,2004,91(2):186-197.
[91] Abbaspoor M, Streibig J. Clodinafop changes the chlorophyll fluorescence induction curve[J].Weed Science,2005,53(1):1-9.
[92] Schmitz A, Iryna I. Tartachnyk, Sebastian Kiewnick, Richard A. Sikora, Walter Kuehbauch.Detection of Heterodera schachdi infestation in sugar beet by means of laser-induced andpulse amplitude modulated chlorophyll fluorescence[J]. Nematology,2006,8:273-286.
[93] Francisco S, Maria J. Studying photosynthesis by measuring fluorescence[J]. Journal ofBiological Education,2006,41(1):34-37.
[94] Strom D, Ralph P, Stauber J. Development of a Toxicity Identification Evaluation Protocol UsingChlorophyll-a Fluorescence in a Marine Microalga[J]. Archives of EnvironmentalContamination and Toxicology,2009,56(1):30-38.
[95] Suarez A, Patricio G, Alvaro S, Jose J. HUMANN-based system to identify benzimidazolefungicides using multi-synchronous fluorescence spectra: An ensemble approach[J].Analytical and Bioanalytical Chemistry,2009,394(4):1059-1072.
[96] Gantner M, Wladyslaw M. Measurements of chlorophyll fluorescence as an auxiliary method inestimating susceptibility of cultivated hazel (Corylus L.) For filbertaphid (Myzocallis coryliGoetze)[J]. Acta Agrobotanica,2010,63(1):189-195.
[97] Jinjun X, Adnan M, Michael T, Haidikker M. Stink bug feeding induces fluorescence indeveloping cotton bolls[J]. Journal of biological engineering,2011,5(1):11.
[98]顾月清,陶宝祺,钱志余.激光诱导荧光及其应用[J].激光与光电子学进展,1996,7:22-24.
[99]陈莲花.表面活性剂对铜绿微囊藻生长及光合作用的影响[D].南昌大学,2008.
[100]彭菊芳,王水才,贺俊芳,蔡霞,刘晓,匡廷云.捕光天线LHC II的荧光光谱特性研究[J].光子学报,2004,33(1):56.
[101]于光辉.生殖生长期两优培九功能叶光反应特性[J].作物学报,2010,36(11):1959-1966.
[102]李鹏民,高辉远.快速叶绿素荧光诱导动力学分析在光合作用研究中的应用[J].植物生理与分子生物学学报,2005,31(6):559-566.
[103] Rohacek K, Bartak M. Technique of the modulated chlorophyll fluoreacence: basic concepts,useful parametern, and some applications[J]. Photosynthetic,1999,27(3):339-363.
[104] Polo C, Frisardi A, Resnik E, Schoua A, Batlle A. Factors influencing fluorescence spectra of freeporphyrins[J]. Clinical chemistry,1988,34(4):757-60.
[105] Patsayeva S, Reuter R. Temperature dependence of fluorescence spectra of natural organicmatter in seawater [M]. Geoinformation for European-Wide Integration, ed. T. Benes.2003.
[106] Mrozek J, Rzeska A, Guzow K, Karolczak J, Wiczk W. Influence of alkyl group on amide nitrogenatom on fluorescence quenching of tyrosine amide and N-acetyltyrosine amide[J].Biophysical Chemistry,2004,111(2):105-113.
[107]杨昊谕.基于叶绿素荧光光谱分析的植物生理信息检测技术研究[D].吉林大学,2010.
[108]荆卉婷.利用傅立叶变换求解压缩态光场的输出模[J].苏州科技学院学报,2009,26(3):17-19+28.
[109]杨勇兵.一种新型的快速模板匹配算法[J].电子工艺技术,2010,41(3):128-131.
[110]林振宇.几种化学计量学模型的建立及其应用研究[D].福州大学,2002.
[111] Chatni M, Yale G, Ryckeghem A. Frequency Domain Fluorescence Lifetime Microwell-PlatePlatform for Respirometry Measurements[J]. Smart Biomedical and Physiological SensorTechnologies Vii,2010.
[112]祝诗平.近红外光谱品质检测方法研究[D].中国农业大学,2003.
[113]李慷.道路养护支持信息系统的研究与开发[D].长安大学,2011.
[114]宋丽华.花生籽仁蛋白质含量近红外光谱模型的建立及育种应用[D].河北农业大学,2011.
[115]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[J].光谱学与光谱分析,2007,27(05):877-880.
[116]郭婷婷,邬文锦,苏谦,王守觉,安冬.近红外玉米品种鉴别系统预处理和波长选择方法[J].农业机械学报,2009,40(S1):87-92.
[117]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[J].光谱学与光谱分析,2004,24(12):1546-1548.
[118]赵环环,严衍禄.噪声对近红外光谱分析的影响及相应的数学处理方法[J].光谱学与光谱分析,2006,26(05):842-845.
[119]刘丽丽.基于超高压预处理的蔬菜农药残留近红外检测技术的初步研究[D].吉林大学,2009.
[120]王福民,黄敬峰,徐俊锋，王秀珍.基于光谱波段自相关的水稻信息提取波段选择[J].光谱学与光谱分析,2008,28(5):1098-1101.
[121] Thenkabail P, Enclona E, Ashton M. Plus Sensors in the Study of African Rainforests[J]. RemoteSensing of Environment,2004,90(1):23-43.
[122]苏荣国,梁生康,胡序朋,王修林.荧光光谱结合主成分分析对硅藻和甲藻的识别测定[J].海洋科学进展,2007,25(2):238-246.
[123]李静萍,谢邦国.多元统计分析：方法与应用,北京：中国人民大学出版社.2008.
[124]高荣强,范世福,严衍禄,赵丽丽.近红外光谱的数据预处理研究[J].光谱学与光谱分析,2004,24(12):1563-1565.
[125]杨苗,杨萍果.基于小波变换的光谱分析法预测土壤总氮含量[J].山西师范大学学报(自然科学版),2011,26(02):85-89.
[126]张旭.中国巨型城市的发展与动力研究[D].中山大学,2010.
[127]蒋骏,贾志宽,徐春明,刘玉华.苜蓿冠层温度与农艺性状的相关分析[J].干旱地区农业研究,2003,21(04):20-22.
[128]陈斌,王豪,林松,赵杰文.基于相关系数法与遗传算法的啤酒酒精度近红外光谱分析[J].农业工程学报,2005,21(07):99-102.
[129]秦蓓蕾,王文圣,丁晶.偏最小二乘回归模型在水文相关分析中的应用[J].四川大学学报(工程科学版),2003,7(04):115-118.
[130]李世欣,温建,邵孝侯,王晓亚,王玉英.偏最小二乘法与人工神经网络耦合的小流域产沙模型[J].河海大学学报(自然科学版),2010,54(02):149-153.
[131]李晓松,李增元,高志海,白黎娜,王琫瑜.基于NDVI与偏最小二乘回归的荒漠化地区植被覆盖度高光谱遥感估测[J].中国沙漠,2011,31(01):162-167.
[132]沈铁峰,黄德生,吴伟,关鹏,周宝森. Bayes判别分析在肾综合征出血热发病预测研究中的应用[J].中国媒介生物学及控制杂志,2009,16(02):147-150.
[133]胡小平,梁承华,杨之为,李振岐.植物病虫害BP神经网络预测系统的研制与应用[J].西北农林科技大学学报(自然科学版),2001,29(02):73-76.
[134]梁曼君，石竹，韩江洪.基于BP神经网络的棉花病虫害诊断系统[J].微电子学与计算机,1996,25(03):35-37+40.
[135]喻丽华,陆晓燕.神经网络知识获取及推理技术在番茄专家系统中的应用[J].贵州工业大学学报(自然科学版),2004(05):83-85+95.
[136]李华,魏开来,高捷,王华.人工神经网络在葡萄霜霉病预测中的应用[J].农机化研究,2008,30(08):160-162+166.
[137]陈怀亮,张弘,李有.农作物病虫害发生发展气象条件及预报方法研究综述[J].中国农业气象,2007,29(02):212-216.
[138]冯沈萍,孙凡.运用人工神经网络预测一代粘虫发生程度的研究[J].微型电脑应用,1999,16(10):45-47.
[139]吴小红,蒋星华.优化BP神经网络在森林病虫害预测中的应用[J].现代电子技术,2007,31(01):138-140.
[140]孙凡,陈汉容.稻瘿蚊发生趋势的BP网络预测模型[J].计算机仿真,2000,17(03):61-63.
[141]杨保俊,叶卫京.人工智能技术在桑病虫预测预报中的应用[J].蚕桑通报,2001,48(01):29-32.
[142]冯旭东,陈方.神经网络在病虫害诊断中的应用[J].电脑开发与应用,1999,15(01):26-28.
[143] Cortes C, Vapnik V. Machine Learning,1995,20(3):273.
[144] Vapnik V. The Nature of Statistical Learning Theory. New York:Springer-Verlag,1955.
[145] Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and OtherKerner-based Learning Methods.Beijing:Publishing House of Electronics Industry,2004.
[146] Naiyang D, Yingjie T. New Method of Data Minning Support Vector Machine.Beijing:SciencePress,2004.
[147]石晶晶,刘占宇,张莉丽,周湾,黄敬峰.基于支持向量机(SVM)的稻纵卷叶螟危害水稻高光谱遥感识别[J].中国水稻科学,2009,23(03):331-334.
[148]刘凯军.支持向量机研究及其在货币识别中的应用[D].西安理工大学,2004.
[149]刘婷.棉蚜天敌图像的分类识别研究[D].西北农林科技大学,2010.
[150]邵咏妮.水稻生长生理特征信息快速无损获取技术的研究[D].浙江大学,2010.
[151]雷冯,陈双双,冯斌,刘飞,何勇,楼兵干.基于光谱技术的大豆豆荚炭疽病早期鉴别方法[J].农业工程学报,2012,28(1):139-144.
[152] Bin L, Hongye S, Weihua H, Jian C. Temperature Prediction Control based on Least SquaresSupport Vector Machines [J]. Journal of Control Theory and Application,2004,8(4):365-370.
[153]孙光明,杨凯盛,张传清,吴迪,何勇,冯雷.基于多光谱成像技术的大麦赤霉病识别[J].农业工程学报,2009,25(S2):204-207.
[154]李先锋,朱伟兴,纪滨,刘波.基于特征优化和LS-SVM的棉田杂草识别[J].农业机械学报,2010,41(11):168-172.
[155]虞佳佳,邹伟,何勇,等.基于近红外反射光谱的外来入侵植物的辨识[J].光谱学与光谱分析,2009,29(11):2955-2958.
[156]徐新刚,赵春江,王纪华,徐正浩.新型光谱曲线特征参数与水稻叶绿素含量间的关系研究[J].光谱学与光谱分析,2011,31(01):188-191.
[157] Huimin W, Nianhui Z, Linfang D. Protein endogenous fluorescence to examine the influence ofsolution pH on PSII of two peripheral protein conformation [J]. Journal of Sichuan University (Natural Science Edit ion),2004,41(5):1059-1063.
[158]李霞,刘友良,焦德茂.不同高产水稻品种叶片的荧光参数的日变化和光适应特性的关系[J].作物学报,2002,28(2):145-153.
[159]潘瑞炽,植物生理学:北京：高等教育出版社.2004:63-64.
[160]林世青,许春辉,张其德,徐黎,毛大璋,匡廷云.叶绿素荧光动力学在植物抗性生理学、生态学和农业现代化中的应用[J].植物学报,1992,9(1):1-16.
[161]杨虎清,周存山,霍艳荣,庞林江,王允祥.利用叶绿素荧光预测水蜜桃果实冷害的研究[J].园艺学报,2008,35(7):945-950.
[162]徐彬彬,石晓日,李德成,周斌,沈玉其,朱永豪,张崇静,吴荣,刘南英.不同施肥条件下玉米的荧光光谱特征及其在遥感中应用的可能性[J].环境遥感,1992,7(S1):51-59.
[163]杨昊谕,于海业,张蕾,隋媛媛.基于激光诱导荧光光谱分析的黄瓜叶片叶绿素含量检测[J].农业机械学报,2009,40(10):169-172.
[164]苏荣国,胡序朋,张传松,王修林.基于活体荧光的藻类识别测定技术[J].热带海洋学报,2008,27(05):24-29.
[165]张永江,赵春江,刘良云,王纪华,马智宏,王人潮.被动荧光探测水分胁迫对玉米叶片影响的初步研究[J].农业工程学报,2006,23(09):39-43.
[166] Lichtenthaler K,王可玢.以体内叶绿素荧光检测植物的逆境因素[J].生物技术通报,1992,8(02):1-4.
[167] Schmuck G, Lichtenthaler H, Application of laser-induced chlorophyll-a fluorescence in theforest decline research[J]. International Geoscience and Remote Sensing Symposium(IGARSS).1986:1587-1590.
[168]庞金安,马德华,李淑菊.黄瓜光合作用的研究[J].天津农业科学,1997,3(4):8-15.
[169]许大全.气孔不均匀关闭与光合作用的非气孔限制[J].植物生理学通讯,1995,31(4):246-252.
[170]董振国,于沪宁.农田光合有效辐射观测与分析[J].气象,1983,7:23-24.
[171]郑健,蔡焕杰,王健,王燕.日光温室内光合有效辐射基本特征分析[J].农业机械学报,2009,42(12):164-168.
[172]李少昆.关于光合速率与作物产量关系的讨论（综述）[J].石河子大学学报（自然科学版）,1998,16(S1):117-126.
[173] Oweis T, Ahmed H, Mustafa P. Water use efficiency of winter-sown chickpea undersupplemental irrigation in a mediterranean environment[J]. Agricultural WaterManagement,2004,66:163-179.
[174] Kramer P, Kozlowski T. Physiology of woody plants [M]. London: Academic Press.1979:443-444.
[175]李荣生,许煌灿,尹光天,杨锦昌,李双忠.植物水分利用效率的研究进展[J].林业科学研究,2003,16(3):366-371.
[176]于晓芳,高聚林,宋国栋,王志刚,桑丹丹,叶君.玉米叶片水分利用效率与叶绿素a荧光参数的关系[J].玉米科学,2009,17(4):55-57.
[177] XiaoJuan T, Jun L, Qiang Y, Zhong Q. Ecosystem water use efficiency in an irrigated cropland inthe North China Plain[J]. Journal of Hydrology,2009,374(3):329-337.
[178] YongJiang Z, LiangYun L, MingYu H. Progress in remote sensing of vegetation chlorophyllfluorescence[J]. Journal of Remote Sensing,2009,13(5):963-970.
[179] Guifang W, Yong H. Identification of Varieties of Cashmere by Vis/NIR SpectroscopyTechnology Based on PCA SVM[J]. Spectroscopy and Spectral Analysis,2009,29(6):1541-1544.