高光谱遥感数据具有光谱分辨率高，信息量丰富的优势，被广泛应用于小麦条锈病遥感监测，但也存在数据冗余，波段间相关性高的问题，因此从众多的变量中优选光谱特征是一个重要环节。目前研究中用到的以一次建模为主的特征选择方法，数据处理易受样本数量的影响，建模时难以达到最佳结果，针对这一问题，本研究基于模型集群分析（Model Population Analysis，MPA）思想的特征选择方法从叶片和冠层两个尺度优选了对小麦条锈病敏感的光谱特征，该方法弥补了一次性建模分析的缺点，可以充分地利用样本信息，通过随机采样生成大量的子模型进行统计分析并提取信息。然后利用优选出的特征构建小麦条锈病遥感监测模型，评价MPA特征选择方法的有效性，以期为高光谱数据优选特征变量进行病虫害遥感监测提供参考，具体研究内容与结论如下：

（1）在叶片尺度上，分析了小麦条锈病叶片光谱响应特性和适合病害监测的光谱特征，采用传统的相关系数法（Correlation Coefficient，CC）、独立样本T检验法（Independent T-test，T-test）和基于MPA思想的子窗口重排分析（Subwindow Permutation Analysis，SPA）和随机蛙跳（Random Frog，RF）特征选择算法优选原始波段和光谱指数作为对小麦叶片条锈病敏感的特征，然后采用费氏线性判别分析（Fisher Linear Discrimination Analysis，FLDA）方法构建病情程度判别模型并进行对比分析。结果表明，基于SPA和RF算法优选特征变量构建的SPA-FLDA、RF-FLDA模型精度均高于CC、T-test方法，并大大降低了优选的特征变量数目，提高了运行效率，其中以RF算法优选的光谱反射率波段和光谱指数所建立的模型精度差异最小，判别精度均达到80%以上，实现了对小麦条锈病病情程度区分的目的，可认为RF算法是优选小麦叶片条锈病敏感特征的最佳方法。

（2）在冠层尺度上，分析了小麦在不同条锈病病情严重度下的光谱响应规律，通过与叶片尺度进行对比发现两者在近红外波段处的反射率曲线存在差异，光谱指数特征与病情指数（Disease Index，DI）的相关性也表现出了不同的效果。同样利用CC法和基于MPA思想的竞争性自适应重加权采样法（Competitive Adaptive Reweighted Sampling，CARS）、变量组合集群分析法（Variable Combination Population Analysis，VCPA）和自主软收缩（Bootstrapping Soft Shrinkage，BOSS）三种特征选择算法提取敏感光谱特征，并利用偏最小二乘回归（Partial Least Squares Regression，PLSR）算法构建了小麦条锈病DI估测模型。结果表明，基于MPA算法优选的特征变量建立估测模型的精度较全波段和CC法均有不同程度的提高，且极大的减少了特征变量数，其中基于BOSS-PLSR模型的预测结果最优，RPD均大于2，其次是VCPA-PLSR模型。当利用CC法与MPA算法联合优选特征变量时，CC-CARS和CC-VCPA均表现出了更好的联合效果，精度得到了提高，其中CC-VCPA-PLSR模型表现最好，说明该联合方式是一种有效可行的特征变量选择方法。

（3）日光诱导叶绿素荧光（Solar-Induced Chlorophyll Fluorescence，SIF）包含非常丰富的光合作用信息，光化学反射率指数（Photochemical Reflectance Index，PRI）能敏感捕捉外界胁迫条件下非光化学猝灭（Non-Photochemical Quenching，NPQ）的变化状况，但两者在冠层尺度上均受到作物群体生物量的干扰，为了减弱其带来的影响，综合利用反射率光谱在作物生化参数方面的优势和冠层SIF、PRI对光合生理敏感的优势，构建了协同SIF和PRI的光谱指数（Synergistic Spectral Index of SIF and PRI，SISP），并评价其在监测小麦条锈病时的有效性。结果表明，与传统反射率光谱指数构建的模型精度相比，利用SISP指数构建模型的精度更高。以SISP和反射率光谱指数为自变量构建的PLSR、多元线性回归（Multiple Linear Regression，MLR）和径向基神经网络（Radial Basis Function Neural Network，RBFN）模型的精度均高于仅利用反射率光谱指数构建的模型精度，由此可知SISP指数能够显著提高对小麦条锈病的监测精度，在三种建模方法中基于RBFN模型的精度最高。

Hyperspectral remote sensing data has the advantages of high spectral resolution and rich information. It is widely used in the remote sensing monitoring of wheat stripe rust, but there are also the problems of data redundancy and high correlation between bands. Therefore, it is an important link to select spectral features from numerous variables. The feature selection method used in the current research is mainly based on one-time modeling, the data processing is easily affected by the number of samples, and it is difficult to achieve the best results when modeling. To solve this problem, the feature selection method based on model population analysis (MPA) in this study was used to optimize the spectral features sensitive to wheat stripe rust at leaf and canopy scales. This method makes up for the shortcomings of one-time modeling idea, can make full use of sample information, generate a large number of sub-models by random sampling for statistical analysis and extract information from the data. And then, the selected features were used to construct a remote sensing monitoring model for wheat stripe rust, and the effectiveness of the MPA feature selection method was evaluated, in order to provide a reference for the hyperspectral data to select feature variables for remote sensing monitoring of diseases and insect pests. The specific research contents and conclusions are as follows:

(1) At the leaf scale, the spectral response characteristics of wheat stripe rust and the spectral characteristics suitable for disease monitoring were analyzed. The traditional correlation coefficient (CC) method, independent T-test (T-test) method and subwindow permutation analysis (SPA) and random frog (RF) feature selection algorithms based on MPA were used to select the original bands and spectral indices as the sensitive features of stripe rust on wheat leaves, then, the fisher linear discrimination analysis (FLDA) disease severity identification model was constructed and compared. The results show that the accuracy of the SPA-FLDA and RF-FLDA models constructed based on the optimized feature variables of the SPA and RF algorithms is higher than that of the CC and T-test methods, and the number of preferred feature variables is also greatly reduced and the operation efficiency is improved. Among them, the model established by the spectral reflectance band and spectral index optimized by the RF algorithm has the smallest difference in accuracy, and the discrimination accuracy are more than 80%, which realizes the purpose of distinguishing the disease degree of wheat stripe rust. It can be considered that RF algorithm is the best method to optimize the sensitive features of wheat leaf stripe rust.

(2) At the canopy scale, the spectral response of wheat under different disease severity of stripe rust was analyzed. By comparing with the leaf scale, it was found that there were differences in the reflectance curves of the two in the near-infrared band, and the correlation between the spectral index features and the disease index (DI) also showed different effects. CC method and three feature selection algorithms of competitive adaptive reweighted sampling (CARS), variable combination population analysis (VCPA) and bootstrapping soft shrinkage (BOSS) based on MPA were also used to extract the spectral features sensitive to wheat stripe rust. The DI estimation model of wheat stripe rust was constructed by partial least squares regression (PLSR) algorithm. The results showed that the accuracy of the estimation model based on the feature variables selected by MPA algorithm was improved to varying degrees compared with the full-band and CC method, and the number of feature variables was greatly reduced. The prediction results based on the BOSS-PLSR model are the best, and the RPD are all greater than 2, followed by the VCPA-PLSR model. When CC method and MPA algorithm combined to select feature variables, both CC-CARS and CC-VCPA showed better joint effect and improved accuracy, among which CC-VCPA-PLSR model performed best, indicating that the joint method is an effective and feasible feature variable selection method.

(3) Solar-induced chlorophyll fluorescence (SIF) contains very rich photosynthesis information, and photochemical reflectance index (PRI) can sensitively capture the changes of non-photochemical quenching (NPQ) under external stress conditions, but both are disturbed by crop biomass at the canopy scale. In order to weaken its impact, the spectral index SISP was constructed by combining the advantages of reflectance spectroscopy in biochemical parameters of crops and the advantages of canopy SIF and PRI sensitivity to photosynthetic physiology, and its effectiveness in monitoring wheat stripe rust was evaluated. The results showed that compared with the stripe rust monitoring model constructed by the traditional reflectance spectral index, the accuracy of the model constructed by the SISP index is higher. The accuracies of the PLSR, multiple linear regression (MLR) and radial basis function neural network (RBFN) models constructed with SISP and reflectance spectral index as independent variables were all higher than those constructed with reflectance spectral index only. It can be seen that the SISP index can significantly improve the monitoring accuracy of wheat stripe rust, and the RBFN model has the highest accuracy among the three modeling methods.

[1] Davis E C. A review of advanced techniques for detecting plant diseases[J]. Computers and Electronics in Agriculture, 2010, 72(1).

[2] 王静, 景元书, 黄文江, 等. 冬小麦条锈病严重度不同估算方法对比研究[J]. 光谱学与光谱分析, 2015, 35(6): 1649-1653.

[3] 黄文江, 刘林毅, 董莹莹, 等. 基于遥感技术的作物病虫害监测研究进展[J]. 农业工程技术, 2018, 38(9): 39-45.

[4] 童庆禧, 张兵, 郑兰芬. 高光谱遥感——原理、技术与应用[M]. 北京: 高等教育出版社, 2006.

[5] 章钊颖, 王松寒, 邱博, 等. 日光诱导叶绿素荧光遥感反演及碳循环应用进展[J]. 遥感学报, 2019, 23(1): 37-52.

[6] 竞霞, 邹琴, 白宗璠, 等. 基于反射光谱和叶绿素荧光数据的作物病害遥感监测研究进展[J]. 作物学报, 2021, 47(11): 2067-2079.

[7] 张东辉, 赵英俊, 秦凯, 等. 光谱变换方法对黑土养分含量高光谱遥感反演精度的影响[J]. 农业工程学报, 2018, 34(20): 141-147.

[8] 刘燕德, 肖怀春, 孙旭东, 等. 柑桔叶片黄龙病光谱特征选择及检测模型[J]. 农业工程学报, 2018, 34(3): 180-187.

[9] 竞霞, 张腾, 白宗璠, 等. 融合GA与SVR算法的小麦条锈病特征优选与模型构建[J].农业机械学报, 2020, 51(11): 253-263.

[10] 胡根生, 吴问天, 黄文江, 等. 粒子群优化的最小二乘支持向量机在小麦白粉病监测中的应用[J]. 遥感技术与应用, 2017, 32(2): 299-304.

[11] 白宗璠, 竞霞, 张腾, 等. MDBPSO算法优化的全波段光谱数据协同冠层SIF监测小麦条锈病[J]. 作物学报, 2020, 46(8): 1248-1257.

[12] Galvao R K H, Araujo M C U, Martins M D, et al. An application of subagging for the improvement of prediction accuracy of multivariate calibration models[J]. Chemometrics and Intelligent Laboratory Systems, 2006, 81(1): 60-67.

[13] Cheng S X, Xie C Q, Wang Q N, et al. Different wavelengths selection methods for identification of early blight on tomato leaves by using hyperspectral imaging technique[J]. Spectroscopy and Spectral Analysis, 2014, 34(5): 1362-1366.

[14] 刘爽, 谭鑫, 刘成玉, 等. 高光谱数据处理算法的小麦赤霉病籽粒识别[J]. 光谱学与光谱分析, 2019, 39(11): 3540-3546.

[15] 王帅. 小麦赤霉病高光谱特征提取方法研究[D]. 合肥: 安徽农业大学, 2019.

[16] Li X L, Xu K W, Zhang Y Y, et al. Optical determination of lead chrome green in green tea by Fourier transform infrared (FT-IR) transmission spectroscopy[J]. Plos One, 2017, 12(1): e0169430.

[17] 程术希. 基于光谱和成像技术的作物病害不同侵染期快速检测方法研究[D]. 杭州:浙江大学, 2014.

[18] Yu H D, Yun Y H, Zhang W, et al. Three-step hybrid strategy towards efficiently selecting variables in multivariate calibration of near-infrared spectra[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 224: 117376.

[19] Zou X B, Zhao J W, Povey M J W, et al. Variables selection methods in near-infrared spectroscopy[J]. Analytica Chimica Acta, 2010, 667(1-2): 14-32.

[20] Li H D, Liang Y Z, Xu Q S, et al. Model population analysis for variable selection[J]. Journal of Chemometrics, 2010, 24(7-8): 418-423.

[21] Li H D, Zeng M M, Tan B B, et al. Recipe for revealing informative metabolites based on model population analysis[J]. Metabolomics, 2010, 6(3): 353-361.

[22] 李洪东. 广义灰色分析体系建模的基本问题及其模型集群分析研究[D]. 长沙: 中南大学, 2012.

[23] Li H D, Liang Y Z, Cao D S, et al. Model-population analysis and its applications in chemical and biological modeling[J]. Trac Trends in Analytical Chemistry, 2012, 38(1): 154-162.

[24] 黄木易, 黄文江, 刘良云, 等. 冬小麦条锈病单叶光谱特性及严重度反演[J]. 农业工程学报, 2004, 20(1): 176-180.

[25] 黄文江, 黄木易, 刘良云, 等. 利用高光谱指数进行冬小麦条锈病严重度的反演研究[J]. 农业工程学报, 2005, 21(4): 7.

[26] 袁琳. 小麦病虫害多尺度遥感识别和区分方法研究[D]. 杭州: 浙江大学, 2015.

[27] 胡耀华, 平学文, 徐明珠, 等. 高光谱技术诊断马铃薯叶片晚疫病的研究[J]. 光谱学与光谱分析, 2016, 36(2): 5.

[28] Adam E, Deng H, Odindi J, et al. Detecting the early stage of phaeosphaeria leaf spot infestations in maize crop using in situ hyperspectral data and guided regularized random forest algorithm[J]. Journal of Spectroscopy, 2017.

[29] 董锦绘, 杨小冬, 杨贵军, 等. 基于近地高光谱信息的小麦条锈病病情指数反演[J]. 麦类作物学报, 2016, 36(12): 1674-1680.

[30] 郭洁滨, 黄冲, 王海光, 等. 基于高光谱遥感技术的不同小麦品种条锈病病情指数的反演[J]. 光谱学与光谱分析, 2009(12): 3353-3357.

[31] Fernández C I, Leblon B, Haddadi A, et al. Potato late blight detection at the leaf and canopy levels based in the red and red-edge spectral regions[J]. Remote Sensing, 2020, 12(8): 1292.

[32] 鲁军景, 黄文江, 张竞成, 等. 基于小波特征的小麦白粉病与条锈病的定量识别[J]. 光谱学与光谱分析, 2016, 36(6): 1854-1858.

[33] Azadbakht M, Ashourloo D, Aghighi H, et al. Wheat leaf rust detection at canopy scale under different LAI levels using machine learning techniques[J]. Computers and Electronics in Agriculture, 2019, 156: 119-128.

[34] 黄林生, 张庆, 张东彦, 等. Relief-F筛选波段的小麦白粉病早期诊断研究[J]. 红外与激光工程, 2018, 47(5): 219-226.

[35] 曲歌, 陈争光, 张庆华. 基于无信息变量消除法的水稻种子发芽率测定[J]. 江苏农业学报, 2019, 35(5): 1015-1020.

[36] 竞霞, 张腾, 白宗璠, 等. 融合GA与SVR算法的小麦条锈病特征优选与模型构建[J]. 农业机械学报, 2020, 51(11): 253-263.

[37] 曹引, 冶运涛, 赵红莉, 等. 基于离散粒子群和偏最小二乘的水源地浊度高光谱反演[J]. 农业机械学报, 2018, 49(1): 173-182.

[38] 孔庆明, 谷俊涛, 高睿, 等. 基于组合偏最小二乘的特征波段优选方法在氨、碱化处理玉米秸秆粗蛋白检测中的研究[J]. 分析测试学报, 2020, 39(11): 1334-1343.

[39] 姚志凤, 雷雨, 何东健. 基于高光谱成像的小麦白粉病与条锈病识别[J]. 光谱学与光谱分析, 2019, 39(3): 969-976.

[40] 王冉, 刘志刚, 杨沛琦. 植物日光诱导叶绿素荧光的遥感原理及研究进展[J]. 地球科学进展, 2012, 27(11): 1221-1228.

[41] 周丽娜, 于海业, 张蕾, 等. 基于叶绿素荧光光谱分析的稻瘟病害预测模型[J]. 光谱学与光谱分析, 2014, 34: 1003-1006.

[42] 陈兵, 王克如, 李少昆, 等. 病害胁迫对棉叶光谱反射率和叶绿素荧光特性的影响[J]. 农业工程学报, 2011, 27(9): 86-93.

[43] Belasque J, Gasparoto M, Marcassa L G. Detection of mechanical and disease stresses in citrus plants by fluorescence spectroscopy[J]. Appl Opt, 2008, 47(11): 1922-1926.

[44] Cheng Y B, Elizabeth M, Zhang Q, et al. Integrating solar induced fluorescence and the photochemical reflectance index for estimating gross primary production in a cornfield [J]. Remote Sensing, 2013, 5(12): 6857-6879.

[45] 刘良云. 植被定量遥感原理与应用[M]. 北京: 科学出版社, 2014.

[46] 张永江, 黄文江, 王纪华, 等. 基于Fraunhofer线的小麦条锈病荧光遥感探测[J]. 中国农业科学, 2007(1): 78-83.

[47] Raji S N, Subhash N, Ravi V, et al. Detection of mosaic virus disease in cassava plants by sunlight-induced fluorescence imaging: a pilot study for proximal sensing[J]. International Journal of Remote Sensing, 2015, 36(11).

[48] Song L, Guanter L, Guan K, et al. Satellite sun-induced chlorophyll fluorescence detects early response of winter wheat to heat stress in the Indian Indo-Gangetic Plains[J]. Global Change Biology, 2018.

[49] 赵叶, 竞霞, 黄文江, 等. 日光诱导叶绿素荧光与反射率光谱数据监测小麦条锈病严重度的对比分析[J]. 光谱学与光谱分析, 2019, 39(9): 2739-2745.

[50] 竞霞, 吕小艳, 张超, 等. 基于SIF-PLS模型的冬小麦条锈病早期光谱探测[J]. 农业机械学报, 2020, 51(6): 191-197.

[51] 陈思媛, 竞霞, 董莹莹, 等. 基于日光诱导叶绿素荧光与反射率光谱的小麦条锈病探测研究[J]. 遥感技术与应用, 2019, 34(3): 511-520.

[52] 竞霞, 白宗璠, 高媛, 等. 利用随机森林法协同SIF和反射率光谱监测小麦条锈病[J].农业工程学报, 2019, 35(13): 154-161.

[53] 高媛, 竞霞, 刘良云, 等. 基于多核支持向量机的小麦条锈病遥感监测研究[J]. 麦类作物学报, 2020, 40(1): 118-126.

[54] Verrelst J, Rivera J P, Van der Tol C, et al. Global sensitivity analysis of the SCOPE model: what drives simulated canopy-leaving sun-induced fluorescence?[J]. Remote Sensing of Environment, 2015, 166(6): 8-21.

[55] Zhang C, Filella I, Garbulsky M, et al. Affecting factors and recent improvements of the photochemical reflectance index (PRI) for remotely sensing foliar, canopy and ecosystemic radiation-use efficiencies[J]. Remote Sensing, 2016, 8(9): 677.

[56] 张竞成. 多源遥感数据小麦病害信息提取方法研究[D]. 杭州: 浙江大学, 2012.

[57] 中国国家标准化管理委员会. GB/T 15795-2011小麦条锈病测报技术规范[S]. 北京:中国标准出版社, 2011.

[58] Schell J A. Monitoring vegetation systems in the great plains with ERTS[J]. Nasa Special Publication, 1973, 351(1): 309.

[59] Chen J M. Evaluation of vegetation indices and a modified simple ratio for boreal applications[J]. Canadian Journal of Remote Sensing, 1996, 22(3): 229-242.

[60] Huete A, Justice C, Liu H. Development of vegetation and soil indices for MODIS-EOS [J]. Remote Sensing of Environment, 1994, 49(3): 224-234.

[61] Gitelson A A, Kaufman Y J, Merzlyak M N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote Sensing of Environment, 1996, 58(3): 289-298.

[62] Huete A R. A soil-adjusted vegetation index (SAVI)[J]. Remote Sensing of Environment, 1988, 25(3): 295-309.

[63] Rondeaux G, Steven M, Baret F. Optimization of soil-adjusted vegetation indices[J]. Remote Sensing of Environment, 1996, 55(2): 95-107.

[64] (美)普拉萨德, (美)约翰, (美)阿尔弗雷德主编. 高光谱植被遥感[M]. 刘海启,李召良译. 北京: 中国农业科学技术出版社, 2015. 11.

[65] Datt B. A new reflectance index for remote sensing of chlorophyll content in higher plants: tests using eucalyptus leaves[J]. Journal of Plant Physiology, 1999, 154(1): 30-36.

[66] Vogelmann J E, Rock B N, Moss D M. Red edge spectral measurements from sugar maple leaves[J]. Titleremote Sensing, 1993, 14(8): 1563-1575.

[67] Gamon J A, Serrano L, Surfus J S. The photochemical reflectance index: an optical indicator of photosynthetic radiation use efficiency across species, functional types, and nutrient levels[J]. Oecologia, 1997, 112(4): 492-501.

[68] Gong P, Pu R, Heald R C. Analysis of in situ hyperspectral data for nutrient estimation of giant sequoia[J]. International Journal of Remote Sensing, 2002, 23(9): 1827-1850.

[69] 白宗璠. 反射率光谱与SIF数据协同的小麦条锈病遥感监测研究[D]. 西安: 西安科技大学, 2020.

[70] Zarco-Tejada P J, Miller J R, Mohammed G H, et al. Chlorophyll fluorescence effects on vegetation apparent reflectance: I. Leaf-level measurements and model simulation[J]. Remote Sensing of Environment, 2000, 74(3): 582-595.

[71] Zarco-Tejada P J, Miller J R, Mohammed G H, et al. Chlorophyll fluorescence effects on vegetation apparent reflectance: II. Laboratory and airborne canopy-level measurements with hyperspectral data[J]. Remote Sensing of Environment, 2000, 74(3): 596-608.

[72] Dobrowski S Z, Pushnik J C, Zarco-Tejada P J, et al. Simple reflectance indices track heat and water stress-induced changes in steady-state chlorophyll fluorescence at the canopy scale[J]. Remote Sensing of Environment, 2005, 97(3): 403-414.

[73] Zarco-Tejada P J, Pushnik J C, Dobrowski S, et al. Steady-state chlorophyll a fluorescence detection from canopy derivative reflectance and double-peak red-edge effects[J]. Remote Sensing of Environment, 2003, 84(2): 283-294.

[74] Du S S, Liu L Y, Liu X J, et al. Response of canopy solar-induced chloriphy fluorescence to the absorbed photosynthetically active radiation absorbed by chlorophyll[J]. Remote Sensing, 2017, 9(9): 911.

[75] Köhler P, Guanter L, Kobayashi H, et al. Assessing the potential of sun-induced fluorescence and the canopy scattering coefficient to track large-scale vegetation dynamics in Amazon forests[J]. Remote Sensing of Environment, 2018, 204(1): 769-785.

[76] 姜微. 高光谱技术在马铃薯品种鉴别及品质无损检测中的应用研究[D]. 哈尔滨: 东北农业大学, 2017.

[77] Li H D, Xu Q S, Liang Y Z. Random frog: An efficient reversible jump Markov Chain Monte Carlo-like approach for variable selection with applications to gene selection and disease classification[J]. Analytica Chimica Acta, 2012, 740: 20-26.

[78] Wang Y, Jiang F, Gupta B B, et al. Variable selection and optimization in rapid detection of soybean straw biomass on CARS[J]. IEEE Access, 2018, 6: 5290-5299．

[79] 宋雨宸, 宦克为, 韩雪艳, 等. 基于蒙特卡洛变量组合集群分析法的小麦蛋白质近红外光谱变量选择[J]. 长春理工大学学报(自然科学版), 2017, 40(5): 29-35.

[80] Deng B C, Yun Y H, Cao D S, et al. A bootstrapping soft shrinkage approach for variable selection in chemical modeling[J]. Analytica Chimica Acta, 2016, 908.

[81] Garcia-Allende P B , Conde O M , Mirapeix J , et al. Quality control of industrial processes by combining a hyperspectral sensor and fishers linear discriminant analysis[J]. Sensors and Actuators B: Chemical, 2008, 129(2): 977-984.

[82] 罗批, 郭继昌, 李锵, 等. 基于偏最小二乘回归建模的探讨[J]. 天津大学学报(自然科学与工程技术版), 2002(6): 783-786.

[83] 刘占宇, 黄敬峰, 陶荣祥, 等. 基于主成分分析和径向基网络的水稻胡麻斑病严重度估测[J]. 光谱学与光谱分析, 2008, 28(9): 2156-2160.

[84] 赵英时. 遥感应用分析原理与方法[M]. 北京: 科学出版社, 2003.

[85] 秦占飞, 常庆瑞, 谢宝妮, 等. 基于无人机高光谱影像的引黄灌区水稻叶片全氮含量估测[J]. 农业工程学报, 2016, 32(23): 77-85.

[86] 黄木易, 王纪华, 黄文江, 等. 冬小麦条锈病的光谱特征及遥感监测[J]. 农业工程学报, 2003(6): 154-158.

[87] Gausman H W, Allen W A, Myers V I, et al. Reflectance and internal structure of cotton leaves, Gossypium hirsutum L.[J]. Agronomy Journal, 1969, 61(3): 374-376.

[88] 蒋选利. 小麦条锈病相互作用的超微结构、细胞化学和分子细胞学研究[D]. 北京: 中国农业大学, 1999.

[89] Ji H, Wang W Z, Chong D F, et al. CARS algorithm-based detection of wheat moisture content before harvest[J]. Symmetry, 2020, 12(1): 115.

[90] Jiang H, Xu W D, Chen Q S. Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (saccharomyces cerevisiae) cultivations[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 214: 366-371.

[91] Mishra P, Herrmann I, Angileri M. Improved prediction of potassium and nitrogen in dried bell pepper leaves with visible and near-infrared spectroscopy utilising wavelength selection techniques[J]. Talanta, 2021, 225: 121971.

[92] Calderón R, Navas-Cortés J A, Zarco-Tejada P. Early detection and quantification of verticillium wilt in olive using hyperspectral and thermal imagery over large areas[J]. Remote Sensing, 2015, 7(5): 5584–5610.

[93] Zarco-Tejada P J, González-Dugo V, Williams L E, et al. A PRI-based water stress index combining structural and chlorophyll effects: assessment using diurnal narrow-band airborne imagery and the CWSI thermal index[J]. Remote Sensing of Environment, 2013, 138(7): 38-50.

[94] Liu X J, Guanter L, Liu L Y, et al. Downscaling of solar-induced chlorophyll fluorescence from canopy level to photosystem level using a random forest model[J]. Remote Sensing of Environment, 2019, 231(9): 110772.

[95] Liu X J, Liu L Y, Hu J C, et al. Improving the potential of red SIF for estimating GPP by downscaling from the canopy level to the photosystem level[J]. Agricultural and Forest Meteorology, 2020, 281(2): 107846.

[96] 刘新杰. 日光诱导叶绿素荧光的遥感反演研究[D]. 北京: 中国科学院大学, 2016.