摘要
快速准确地定量获取农作物叶绿素含量对于大范围农作物生长健康状况监测、产量估算具有极其重要的意义。由于辐射传输模型通常比较复杂,同时农作物光谱与叶绿素含量是非线性的关系,并且地表环境系统包含众多不确定性因素,传统的辐射传输模型反演技术已不能满足精确估算农作物叶绿素含量的需要。机器学习算法能够表达植物生物化学参数与光谱反射率之间隐含、潜在的非线性函数关系,这有可能使机器学习更加适合于通过辐射传输模型反演获取农作物生物化学参数。如何将机器学习中的算法引入到辐射传输模型,用于构建农作物叶绿素含量高光谱反演模型,提高估算农作物叶绿素含量的精度、解释模型输出的结果,是一个值得深入研究的关键问题。
本文在叶片尺度上,通过PROSPECT模拟农作物光谱,将叶片叶绿素含量与光谱特征联系起来;在冠层尺度,通过机器学习和PROSAIL反演估算了冠层叶绿素含量。论文的主要内容和创新点如下:
(1)分别采用一阶导数、包络线去除、小波变换降噪等对ASD实测光谱和Hyperion影像上的纯净像元光谱增强变换。分析了PROSPECT模型模拟的叶片光谱、PROSAIL模拟的冠层光谱对不同叶绿素含量的光谱响应。利用先验知识解决了遥感反演的病态问题。建立了叶片尺度和冠层尺度农作物光谱数据集。
(2)运用遗传算法和粒子群优化支持向量机参数C和γ选择,提出GA-SVM、PSO-SVM模型,分别应用GA-SVM、PSO-SVM与PROSPECT反演获取农作物叶片叶绿素含量。结果表明,PSO-SVM和PROSPECT反演估算叶绿素含量精度高于GA-SVM反演PROSPECT估算叶绿素含量精度。因此,PSO-SVM对于确定SVM参数、提高支持向量机与PROSPECT反演农作物叶片叶绿素含量精度有重要价值。
(3)将梯度助推机与辐射传输模型结合,提出了基于梯度助推机和PROSPECT的农作物叶片叶绿素含量遥感反演模型,即GBM-PROSPECT。应用GBM-PROSPECT在demy Cλ光谱数据集上估算农作物叶片叶绿素含量,结果表明,估算模型R2为0.9714,MSE为36.9652,与SVM-PROSPECT、RF-PROSPECT相比,GBM-PROSPECT估算农作物叶片叶绿素含量精度最高。因而,在叶片尺度上,GBM-PROSPECT更适合获取叶绿素含量。
(4)运用随机森林进行农作物冠层叶绿素含量遥感反演,构建了RF-PROSAIL模型。使用RF-PROSAIL在db9 Cλ光谱数据集上估算研究区农作物冠层叶绿素含量。结果表明,估算模型R2为0.9000,MSE为1670.4,并且RF-PROSAIL运算时间少于GBM-PROSAIL运算时间,表明估算农作物冠层叶绿素含量RF-PROSAIL优于GBM-PROSAIL。因此,在冠层尺度,RF-PROSAIL最适合估算农作物叶绿素含量。
(5)分析了PROSPECT模型、SAIL模型的局限性,探讨了不同尺度高光谱模型反演估算农作物叶绿素含量误差来源。未来研究应建立融合空间格局分析、改进的辐射传输模型、农作物生物理化参数数据库、随机森林算法的综合尺度提升框架,应用于多源遥感数据协同估算农作物冠层叶绿素含量。
An accurate quantitative estimation of crop chlorophyll content is of great importance for a wide range of monitoring crop grow health condition and estimating biomass,since radiative transfer model are complex caused by the nonlinear relationship between crop specral and chlorophyll content and the uncertainties in the land surface systems, traditional inversion techniques can not satisfied with the demand of accurate estimation of chlorophyll content.Alternatively, machine learning algorithms are able to cope with the strong nonlinearity of the functional dependence between the biophysical parameter and the observed reflected radiance, they may therefore be more suitable candidates for estimating crop biochemistry parameters from inversion of radiative transfer model. It is crucial to apply machine learning algorithms for inversion of radiative transfer model, so as to construct hyperspectral remote sensing estimation model for crop chlorophyll content.
The thesis first linked crop leaf level optical properties and chlorophyll content throuth the inversion of radiative transfer model, PROSPECT. Next, crop chlorophyll content scaled-up to the crop canopy level was estimated using machine learning and PROSAIL. The main conclusions and creative points are as follows:
(1) First derivative, continuum removal, wavelet transform denoising were applied to measured leaf reflectance spectral and crop canopy reflectance spectral from Hyperion images to enhance chlorophyll absorption features. Next, the responses of crop leaf reflectance spectral generated by PROSPECT and canopy reflectance spectral generated by PROSAIL were analyzed with different chlorophyll contents. The ill-posed inverse problem of remote sensing was solved using prior information. Then, leaf-leavel spectral datasets and canopy-level spectral datasets of crops were created.
(2) Genetic algorithm (GA) and particle swarm optimization (PSO) based approaches for determination the penalty parameter C and the kernel function parameter y of support vector machines (SVM), term GA-SVM and PSO-SVM were proposed. GA-SVM and PSO-SVM were applied to invert PROSPECT for retrieval of crop leaf chlorophyll content. The results demonstrate that the estimation accuracy of PSO-SVM approach surpass GA-PSO.Therefore, the PSO-SVM approach is valuable for parameter determination of SVM.
(3) This study is the first couple gradient boosting machines (GBM) with PROSPECT, a hyperspectral remote sensing model, term GBM-PROSPECT, was developed for estimating crop leaf chlorophyll content. The developed model was compared with SVM-PROSPECT and RF-PROSPECT. The results show that GBM-PROSPECT yield an R2 of 0.9714 and a mean square error (MSE) of 36.9652 using the demyCλspectral datasets. Compared with SVM-PROSEPCT and RF-PROSPECT, GBM-PROSPECT got the highest chlorophyll estimation accuracy, therefore, GBM-PROSPECT is more suitable for crop chlorophyll content estimation at leaf level.
(4) This study demonstrated that couple random forests (RF) with PROSAIL, a hyperspectral remote sensing model, term RF-PROSAIL, was developed for estimating crop canopy chlorophyll content. The developed model was compared with GBM-PROSAIL. The results show that GBM-PROSPECT yielded an R2 of 0.9000 and a mean square error (MSE) of 1670.4 using the db9Cλspectral datasets. Compared with GBM-PROSAIL, RF-PROSAIL got the highest chlorophyll estimation accuracy, and the computation time of RF-PROSAIL less than that of GBM-PROSAIL, therefore, RF-PROSAIL is more suitable for crop chlorophyll content estimation at canopy level.
(5) The limation of PROSPECT and SAIL were analyzed, the errors generated in developed hyperspectral remote sensing inversion model for estimating crop chlorophyll content at different scales were discussed. It is recommended that future research should explore a systematic upscaling framework which combines spatial pattern analysis, improved radiative transfer models, crop biophysical/biochemistry parameters database, RF to retrieve crop chlorophyll content from multi-source remote sensing data collaboratively at the canopy level.
引文
Addison P S. Wavelet transforms and the ECG: A review. Physiological Measurement,2005,26:155-199
Agrawal R,Imielinski T. A. Swami: Mining Association Rules Between Sets of Items in LargeDatabases. SIGMOD Conference 1993:207-216
Ahmad S, Kalra A,Stephen H. Estimating soil moisture using remote sensing data: A machinelearning approach. Advances in Water Resources,2010,33(1):69-80
Aleixandre V B, Baret F B, Camachoc F. Optimal modalities for radiative transfer-neuralnetwork estimation of canopy biophysical characteristics: Evaluation over anagricultural area with CHRIS/PROBA observations. Remote Sensing of Environment,2011,115(2):415-426
Allen W A,Gausman H W,Richardson A J,et al. Interaction of isotropic light with a compactplant leaf. Journal of the Optical Society of America,1969,59(10):1376-1379
Allen W A,Gausman H W,Richardson A J. Plant canopy irradiance specified by the Duntleyequations. Journal of the Optical Society of America,1970,60(3):372-376
Allen W A. Transmission of isotropic light across a dielectric surface in two and threedimensions. Journal of the Optical Society of America,1973,63(6):664-666
Alpaydin E. Introduction to Machine Learning. London:The MIT Press,2010
Akhtar M T,Mitsuhashi W,James C J. Employing spatially constrained ICA and wavelet denoising,for automatic removal of artifacts from multichannel EEG data. SignalProcessing,2012,92(2):401-416
Amiri R,Beringer J,Isaac P. Narrowband spectral indices for the estimation of chlorophylalong a precipitation gradient. 3rd Workshop onHyperspectral Image and Signal Processing:Evolution in Remote Sensing (WHISPERS),2011,1-4
Arivazhagan S,Ganesan L. Texture classification using wavelet transform. PatternRecognition Letters,2003,24:1513-1521
Atzberger C. Object-based retrieval of biophysical canopy variables using artificialneuralnets and radiative transfer models. Remote Sensing of Environment,2004,93(1-2):53-67
Ayhan Demiriz,Kristin P Bennett. Linear programming boosting via column generation,2001
Bacour C,Jacquemoud S,Tourbier Y. Design and analysis of numerical experiments to comparefour canopy reflectance models. Remote Sensing of Environment,2002,79(1):72-83
Bacour C,Baret F,Beal D,et al. Neural network estimation of LAI, fAPAR, fCover and LAI×Cab,from top of canopy MERIS reflectance data: Principles and validation. Remote Sensingof Environment,2006,105(4):313-325
Belward A S. Spectral chracteristics of vegetation,soil and water in the visible,near-infraand middle-infra wavelengths. In:Belward A S & Valenzuela C R.(Eds.),1991,Remote Sensingand Geographical Information Systems for Resource Management in developingcountries.Kluwer,Neitherlands
Baret F,Hagolle O,Geiger B,et al. LAI,FAPAR and fCover CYCLOPES global products derived fromVEGETATION.Part1:Principles of the algorithm. Remote Sensing of Environment,2007,110(2):275-286
Baret F,Jacquemoud S,Guyot G,et al. Modeled analysis of the biophysical nature of spectralshifts and comparison with informatio ncontent of broad bands. Remote Sensing ofEnvironment,1992,41(2-3):133-142
Barretta K,Kasischkeb E S, McGuirec A D,et al. Modeling fire severity in black spruce standsin the Alaskan boreal forest using spectral and non-spectral geospatial data. RemoteSensing of Environment,2010,114(7):1494-1503
Beck R. EO-1 User Guide,2003,8-9
Belkin M, Niyogi P, Sindwani V. On manifold regularization. In: Proceedings of the 10thInternational Workshop on Artificial Intelligence and Statistics (AISTATS’05),Savannah Hotel, Barbados,2005,17-24
Blackburn G A,Ferwerda J G. Retrieval of chlorophyll concentration from leaf reflectancespectra using wavelet analysis. Remote Sensing of Environment,2008,112:1614-1632
Blum A, Mitchell T. Combining labeled and unlabeled data with co-training. In: Proceedingsof the 11th Annual Conference on Computational Learning Theory (COLT’98), Wisconsin,MI, 1998, 92-100
Booker L B,Fogel D B,Whitley D,et al. Recombination.In:Back T,Fogel D B,MichalewiczZ,eds.Handbook of evolutionary computation. Bristol and Oxford:IOP Publishing Ltd andOxford University Press,1997
Bousquet L,Lacherade S, Jacquemoud S,et al. Leaf BRDF measurement and model for specularand diffuse component differentiation. Remote Sensing of Environment,2005,98(2-3):201-211
Breiman L. Bagging predictors. Machine Learning,1996,24(2):123-140
Breiman L,Friedman J H,Olshen R A,et al. Classification and Regression Trees. WadsworthInternational,Belmont,Ca,1984
Breiman L. Random forests. Machine learning,2001,45(1):5-32
Broge N H, Mortensen J V. Deriving green crop area index and canopy chlorophyll density ofwinter wheat from spectral reflectance data. Remote sensing of environment,2002,81(1):45-57
Bruce L M, Li J, Huang Y. Automated detection of subpixel hyperspectral targets with adaptivemultichannel discrete wavelet transform. IEEE Transactions on Geoscience and RemoteSensing,2002,40:977-979
Bruce L M,Morgan C,Larsen S. Automated detection of subpixel hyperspectral targets withcontinuous and discrete wavelet transforms. IEEE Transactions on Geoscience and RemoteSensing,2001,39:2217-2226
Bruzzone L,Melgani F. Robust multiple estimator systems for the analysis of biophysicalparameters from remotely sensed data. IEEE Transactions on Geoscience and Remote Sensing,2005,43(1):159-174
Buermann W,Wang Y,Dong,J,Zhou,L,et al. Analysis of multiyear global vegetation index dataset. Journal of Geophysical Research, 2002,107(D22):4646-4662
Burges C J C. A tutorial on support vector machines for pattern recognition. Data Miningand Knowledge Discovery,1998,2:121-167
Burges C J C,Scholkopf B. Improving the accuracy and speed of support vector learningmachine.Advances in neural information processing systems. Cambridge,MA:MITPress,1997,9:375-381
Campbell W M,Campbell J P,Reynolds D A,et al. Support vector machines for speaker and languagerecognition. Computer and Speech Language,2006,20:210-229
Cao L J,Chua K S,Chong W K,et al. A comparison of PCA, KPCA and ICA for dimensionalityreduction in support vector machine. Neurocomputing,2003,55(1-2):321-336
Cao L. Support vector machines experts for time series forecasting.Neurocomputing,2003,51:321-339
Chan J C,Beckers p,Spanhove T,et al. An evaluation of ensemble classifiers for mapping Natura2000 heathland in Belgium using spaceborne angular hyperspectral (CHRIS/Proba) imagery.International Journal of Applied Earth Observation and Geoinformation,2012,18:101-110
Chang C C,Lin C J. LIBSVM: A library for support vector machines,2001
Chan J C W,Paelinckx D. Evaluation of Random Forest and Adaboost tree-based ensembleclassification and spectral band selection for ecotope mapping using airbornehyperspectral imagery. Remote Sensing of Environment, 2008,112,6(16):2999-3011
Chehata N,Guo L,Mallet C. Contribution of airborne full-waveform LiDAR and image data forurban scene classification.In:Proceedings IEEE International Conference on ImageProcessing (ICIP). IEEE,Cairo,Egypt,2009,1669-1672
Chen F R,Qin F,Peng G X,et al. Fusion of Remote Sensing Images Using Improved ICA MergersBased on Wavelet Decomposition. Procedia Engineering,2012,29:2938-2943
Chen J C, Wu C C, Chen C W,et al. Flexible job shop scheduling with parallel machines usingGenetic Algorithm and Grouping Genetic Algorithm. Expert Systems withApplications,2012,39(11):10016-10021
Cho E N,Moon P,Kim C E,et al. Modeling and optimization of ITO/Al/ITO multilayer filmscharacteristics using neural network and genetic algorithm. Expert Systems withApplications,2012,39(10):8885-8889
Ciganda V,Gitelson A,Schepers J. Non-destructive determination of maize leaf and canopychlorophyll content. Journal of Plant Physiology, 2009,166(2):157-167
Clark R N,Roush T L. Reflectance spectroscopy: Quantitative analysis techniques for remotesensing applications. Journal of Geophysical Research,1984,89:6329-6340
Clark R N,Gallagher A J,Swayze G A. Material absorption band depth mapping of imagingspectrometer data using a complete band shape least-squares fit with library referencespectra. In Proceedings of the Second Airborne Visible/Infrared ImagingSpectrometer(AVIRIS) Workshop,1990,90(54):176-186
Clark R N. Spectroscopy of rocks and minerals and principles of spectroscopy. In A. N. Rencz(Ed.), Remote sensing for the earth science(3rd ed.). Manual of RemoteSensing,1999.3:3-58
Clark R N,Swayze G A. Mapping minerals, amorphous materials, environmental materials,vegetation, water, ice and snow,and other materials: The USGS tricorder algorithm. InR. O. Green(Ed.), Summaries of the Fifth Annual JPL Airborne Earth Science Workshop,1995,95(1).39-40
Clark, R. N., King, T. V., Ager, C.,et al. Initial vegetation species and senescence/stressindicator mapping in the San Luis valley, Colorado using imaging spectrometer data. InH. H. Posey,J. A. Pendelton, & D. Van Zyl (Eds.), Proceedings,SummitvilleForum,1995,95(38):64-69
Clevers J G P W. Application of a weighted infrared-red vegetation index for estimating leafarea index by correcting for soil moisture. Remote Sensing of Environment,1989,29 (1):25-37
Clevers J G PW, Kooistra L,Schaepman M E. Estimating canopy water content using hyperspectralremote sensing data. International Journal of Applied Earth Observation andGeoinformation,2010,12(2):119-125
Cocchi M,Seeber1and R,Ulrici A.Multivariate calibration of analytical signals by WILMA(wavelet interface to linear modelling analysis.Journal of Chemometrics,2003,512-527
Combal B,Baret F,Weiss,et al. Retrieval of canopy biophysical variables from bidirectionalreflectance Using prior information to solve the ill-posed inverse problem.RemoteSensing of Environment,2002,84(1):1-15
Comon P. Independent component analysis: A new concept? Signal Processing,1994,36, 287-314
Cover T M, Hart PE. Nearest neighbor pattern classification. IEEE Transactions on InformationTheory,1967,13(1):21-27
Cristescu R,Joutsensalo J,Ristaniemi T. Fading channel estimation bymutual informationminimization for Gaussian stochastic processes.New Orleans:Proceedings ofIEEEInternational Conference on Communications (ICC2000),2000.56-59
Curran P J,Dungan J L, Peterson D L. Estimating the foliar biochemical concentration of leaveswith reflectance spectrometry-testing the Kolaly and Clark methodologies. RemoteSensing of Environment,2001,76,349-359
Darvishzadeh R,Skidmore A,Atzberger C,et al. Estimation of vegetation LAI from hyperspectralreflectance data:Effects of soil type and plant architecture.International Journal ofApplied Earth Observation and Geoinformation,2008,10(3):358-373
Daughtry C S T,Walthall C K,Kim M S,et al. Estimating corn leaf chlorophyll concentrationfrom leaf and canopy reflectance. Remote Sensing of Environment,2000,74(2):229-239
Davis L. Handbook of genetic algorithms.New York:Van Nostrand Reinhold,1991
Dawson T P,Curran P J. A new technique for interpolating the reflectance red edge position.International Journal of Remote sensing,1998,19(11),2133-2139
Dawson T,Curran P,North P,et al. LIBERTY: Modeling the Effects of Leaf BiochemicalConcentration on Reflectance Spectra. Remote Sensing of Environment,1998,65 (1):50-60
Dawson T,Curran P,North P,et al. LIBERTY: The Propagation of Foliar Biochemical AbsorptionFeatures in Forest Canopy Reflectance: A Theoretical Analysis. Remote Sensing ofEnvironment,1999,67(2):147-159
De Lathauwer L, De Moor B, Vandewalle J. An introduction to independent component analysis.Journal of Chemometrics,2000,14,123-149
Delegido J,Alonso L,Gonzalez G,et al. Estimating chlorophyll content of crops fromhyperspectral data using a normalized area over reflectance curve (NAOC). InternationalJournal of Applied Earth Observation and Geoinformation, 2010,12(3):165-174
Demiriz A,Bennett K P. Linear programming boosting via column generation,2001
De Wit,A J W,Boogaard,et al. Spatial resolution of precipitation and radiation:the effecton regional crop yield forecasts. Agricult and Forest Meteorol,2005,135(1-4):156-168
Domingo C,Watanabe O. Madaboost:A modification of adaboost. In:Proceedings of the Workshopon Computational Learning Theory. Morgan Kaufmann Publishers,2000,180-189
Dorigo W A,Richter,Muller A. A lookup table approach for biophysical parameter retrievalby radiative transfer model inversion applied to wide field of view data. In:Proceedigsof the Fourth EARSeL Workshopon Imaging Spectroscopy,Warsaw,Poland.2005
Dorigo W A. Improving the Robustness of Cotton Status Characterisation by Radiative TransferModel Inversion of Multi-Angular CHRIS/PROBA Data. IEEE Journal ofSelected Topics inApplied Earth Observations and Remote Sensing, 2012,5(1):18-29
Drucker H,Burges C J C,Kaufman L,et al. Support vector regression machines.Advances in NeuralInformation Processing Systems,1997,9:155-161
Du P,Kibbe W A,Lin S M. Improved peak detection in mass spectrum by incorporating continuouswavelet transform-based pattern matching. Bioinformatics,2006,22:2059-2065
Durbha S S,King RL,Younan N H. Support vector machines regression for retrieval of leaf areaindex from multiangle imaging spectroradiometer. Remote Sensing of Environment,2007,107(1-2):348-361
Efron B. Boostrap methods:Another look at the Jacknife. The annals ofstatistics,1979,7(1):1-26
Efron B,Tibshirani R. An introduction to the boostrap.Chapman and Hall
El-Mahdy O F M, Ahmed M E H, Metwalli S.Computer aided optimization of natural gas pipenetworks using genetic algorithm.Applied Soft Computing,2010,10(4):1141-1150
Elvidge C D. Visible and near infrared reflectance characteristics of dry plant materials.International Journal of Remote Sensing,1990,11(10),1775-1795
Evgeniou T,Pontil M,Poggio T. A unifed framework for Regularization Networks and SupportVector Machines.A.I.Memo No.1654,Artificial Intelligence aboratory,assachusettsInstitute of Technology,1999
Fang H L,Liang S L. Retrieving leaf area index with a neural network method:Simulation andvalidation. IEEE Transactionson Geoscience and Remote Sensing,2003,41(9):2052-2062
Farge M. Wavelet transforms and their applications to turbulence.Annual Review of FluidMechanics,1992,24:395-458
Felde G W, Anderson G P, Adler-Golden S M, et al. Analysis of Hyperion data with the FLAASHatmospheric correction algorithm.Proceedings of the International Geoscience and RemoteSensing Symposium (IGARSS),Toulouse,21-25 July,2003,90-92
Feret J B,Francois C,Asner G P,et al. PROSPECT-4 and 5: Advances in the leaf opticalproperties model separating photosynthetic pigments. Remote Sensing ofEnvironment,2008,112(6),3030-3043
Fernandez-Martinez J L,Garcia-Gonzalo E. Stochastic Stability Analysis of the LinearContinuous and Discrete PSO Models.IEEE Transactions on EvolutionaryComputation,2011,15(3):405-423
Ferwerda J G,Jones S. Continuous wavelet transformations for hyperspectral featuredetection.Proceedings of the 12th International Symposium on Spatial DataHandling,University of Vienna, Austria,2006
Filippi A M,Jensen J R. Effect of Continuum Removal on Hyperspectral Coastal VegetationClassification Using a Fuzzy Learning Vector Quantizer. IEEE Transactions on Geoscienceand Remote Sensing, 2007, 45(6):1857-1869
Fourty T,Baret F,Jacquemoud S,et al. Leaf optical properties with explicit description ofits biochemical composition: Direct and inverse problems.Remote Sensing ofEnvironment,1996,56(2):104-117
Freund Schapire. A decision-theoretic generalization of on-line learning and an applicationto boosting.JCSS:Journal of Computer and System Sciences,1997
Friedman J H. Multivariate Adaptive Regression Splines.Anals of Statistics,1991,19(1):1-67
Friedman J, Hastie T, Tibshirani R. Additive logistic regression: A statistical view ofboosting (with discussion). The Annals of Statistics, 2000,28(2):337-407
Friedman J H. Greedy function approximation: a gradient boosting machine. Annals ofStatistics, 2001,29(5):1189-1232
Friedman J H. Stochastic gradient boosting. Computational Statistics & Data Analysis,2002,38(4):367-378
Freund Y, Schapire R. Boosting a weak learning algorithm by majority. Information andComputation,1995,121(2):256-285
Freund Y,Schapire R E. A Decision-Theoretic Generalization of on-Line Learning and anApplication to Boosting. Lecture Notes in Computer Science,1997,904,23-37
Garrigues S, Allard D, Baret F, et al. Influence of landscape spatial heterogeneity on thenon-linear estimation of leaf area index from moderate spatial resolution remote sensingdata. Remote Sensing of Environment,2006,105(4):286-298
Galhoun V D,Adali T,stevens M C,et al. Semi-blind ICA of fMRI: A method for utilizinghypothesis-derived time courses in a spatial ICA analysis.NeuroImage,2005,25(2):527-538
Garrigues S,Allard D,Baret F,et al. Influence of landscape spatial heterogeneity on theon-linear estimation of leaf area index from moderate spatial resolution remote sensingdata. Remote Sensing of Environment,2006,105(4):286-298
Gastellu-Etchegorry,J P,Gascon F,Esteve P. An inter polation procedure for generalizing alook-up table inversion method. Remote Sensing of Environment,2003,87(1):55-71
Gislason P O,Benediktsson J A, Sveinsson J R. Random Forests for land coverclassification.Pattern Recognition Letters, 2006,27(4):294-300
Gitelson A A,Vina A,Ciganda V,et al. Remote estimation of canopy chlorophyll content in crops.Geophysical Research Letters, 2005,32,L08403.doi:10.1029/2005GL022688
Goel N S. Inversion of canopy reflectance models for estimation of biophysical parametersfrom reflectance data.InG.Asrar(Ed.), Theory and Applications of Optical RemoteSensing.Wiley Interscience.1989,205-251
Goldberg D E. Genetic algorithms in search,optimization,and machine learning.Massachusetts,USA:Addison Wesley Longman,1989
Gomez C L,Gamps V G,Bruzzone L. Calpe-Maravilla J. Mean map kernel methods for semisupervisedcloud classification. IEEE transactions on Geoscience and Remote Sensing,2010,48(1):1707-1718
Gonzolez-Audícana M,Saleta J L,Catalán R G,et al. Fusion of multispectral and panchromaticimages using improved IHS and PCA mergers based on wavelet decomposition. IEEETransactions on Geoscience and Remote Sensing,2004,42:1291-1299
Goodenough D G, Dyk A, Niemann K O,et al. Processing Hyperion and ALI for forestclassification. IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1321-1331
Govaerts Y M,Jacquemoud S,Verstraete M M,et al. Three-dimensional radiation transfermodeling in a dicotyledon leaf.Applied Optics,1996,35(33):6585-6598
Graps A. An introduction to wavelets. IEEE Computational Science and Engineering, 1995,2,50-61
Green A A,Berman M,Switzer P, et al. A transformation for ordering multispectral data interms of image quality with implications for noise removal. IEEE Transactions onGeoscience and Remote Sensing,1988,26(1):65-74
Guo L,Chehata N, Mallet C, et al. Relevance of airborne lidar and multispectral image datafor urban scene classification using Random Forests. ISPRS Journal of Photogrammetryand Remote Sensing,2011,66(1):56-66
Guelman L. Gradient boosting trees for auto insurance loss cost modeling and predictionExpert Systems with Applications, 2011. In Press, doi:10.1016/j.eswa.2011.09.058
Hapke B. Bidirectional reflectance spectroscopy.1.Theory. Journal of GeophysicalResearch.1981,86(B4):3039-3054
Hapke B,Wells E. Bidirectional reflectance spectroscopy.2. Experiments and observations.Journal of Geophysical Research.1981,86(B4):3055-3060
Heinzel J, Koch B.Investigating multiple data sources for tree species classification intemperate forest and use for single tree delineation. International Journal of AppliedEarth Observation and Geoinformation,2012,18:13-22
Hoffer R M. Biological and physical considerations in applying computer-aided analysistechniques to remote sensor data, In Remote sensing: The Quantitative Approach, SwainP H,& Davis S M, eds, McGraw-Hill,1978,227-289
Ham J,Chen Y,Crawford M,et al. Investigation of the random forest framework forclassification of hyperspectral data. IEEE Transactions on Geoscience and RemoteSensing,2005,43(3):492-501
Holland J. Adaptation in natural and artificial systems. The Michigan University Press,1975
Homolova L,Cudlin P,Zurita-Milla,et al. Physically-based retrievals of Norway spruce canopyvariables from very high spatial resolution hyperspectral data.IEEE InternationalGeoscience and Remote Sensing Symposium(IGARSS ),2007,4057-4060
Hopfield. Neural networks and physical systems with emergent collective computationalabilities. Proceedings of the National Academy of Sciences,1982,79(8):2554-2558
Huang X,Zhang L. Comparison of vector stacking,multi-SVMs fuzzy output,and multi-SVMs votingmethods for multiscale VHR urban mapping. IEEE Geosciences and Remote SensingLetters,2010,7(2):261-265
Hudak A T,Crookston N L, Evans J S, et al. Nearest neighbor imputation of species-level,plot-scale forest structure attributes from LiDAR data.Remote Sensing of Environment,2008,112(5):2232-2245
Huemmrich K F. The GeoSail model:A simple addition to the SAIL model to describe discontinuouscanopy reflectance. Remote Sensing of Environment,2001,75(3):423-431
Hsu C W,Chang C C,Lin C J. A practical guide to support vector classification. Technicalreport,University of National Taiwan,Department of Computer Science and InformationEngineering,2003,1-12
Jacquemoud S,Baret F. PROSPECT:A model of leaf optical properties spectra. Remote Sensingof Environment,1990,34(2):75-91
Jacquemoud S,Baret F,Andrieu B,et al. Extraction of vegetation biophysical parameters byinversion of the PROSPECT + SAIL models on sugar beet canopy reflectance data.Application to TM and AVIRIS sensors. Remote Sensing of Environment,1995,52(3):163-172
Jacquemoud S,Bacour C,Poilve H,et al. Comparison of four radiative transfer models tosimulate plant canopies reflectance-Direct and inverse mode.Remote Sensing ofEnvironment,2000,74(3):471-484
Jacquemoud S,Ustin S L,Verdebout J,et al. Estimating leaf biochemistry using the PROSPECTleaf optical properties model. Remote Sensing of Environment,1996,56(3):194-202
Jensen R, Shen Q. Fuzzy-rough data reduction with ant colonyoptimization. Fuzzy Sets andSystems,2005,495-520
Jacquemoud S, Verdebout J, Schmuck G,et al. Investigation of leaf biochemistry by statistics.Remote Sensing of Environment,1995,54(3),180-188
Jesus Delegido,Luis Alonso,Gonzalo González. Estimating chlorophyll content of crops fromhyperspectral data using a normalized area over reflectance curve (NAOC). InternationalJournal of Applied Earth Observation and Geoinformation,2010,12(3):165-174
Ji J. Robust approach to independent component analysis for SAR image analysis. IET ImageProcessing,2012,6(3):284-291
Kaheil Y H,Rosero E,Gill M K. Downscaling and Forecasting of Evapotranspiration Using aSynthetic Model of Wavelets and Support Vector Machines. IEEE Transactions on Geoscienceand Remote Sensing, 2008,46(9):2692-2707
Kangjoo L,Sungho,Jong C Y. A Data-Driven Sparse GLM for fMRI Analysis Using Sparse DictionaryLearning With MDL Criterion. IEEE Transactions onMedical Imaging,2012,30(5):1076-1089
Kaewpijit S,Moigne J L,El-Ghazawi T. Automatic reduction of hyperspectral imagery usingwavelet spectral analysis. IEEE Transactions on Geoscience and Remote Sensing,2003,41:863-871
Kalacska M,Sanchez-Azofeifa G A,Rivard B,et,al. Ecological fingerprinting of ecosystemsuccession: Estimating secondary tropical dry forest structure and diversity usingimaging spectroscopy. Remote Sensing of Environment,2007,108:82-96
Kearns M,Valiant L G. Learning boolean formulae or factoring. Technical ReportTR-1488,Cambridge,MA:Havard University Aliken Computation Laboratory,1988
Kennedy J,Eberhart R. Particle Swarm Optimization. Proceedings of IEEE InternationalConference on Neural Networks. IV.1995,1942-1948
Kephart J O. A biologically inspired immune system for computers. Proceedings of ArtificialLife IV: The Fourth International Workshop on the Synthesis and Simulation of LivingSystems. MIT Press. 1994,130-139
Khouadjia M R,Sarasola B,Alba E,et al. A comparative study between dynamic adapted PSO andVNS for the vehicle routing problem with dynamic requests. Applied SoftComputing,2012,12(4):1426-1439
Knudby A,Le D E,Brenning. A Predictive mapping of reef fish species richness,diversity andbiomass in Zanzibar using IKONOS imagery and machine learning techniques . Remote Sensingof Environment,2010,114(6):1230-1241
Knyazikhin Y,Martonchik J V,Diner D J,et al. Estimation of vegetation canopy leaf area indexand fraction of absorbed photosynthetically active radiation from atmosphere-correctedMISR data.Journal of Geophysical research,1998a,103(D24):32239-32256
Knyazikhin Y,Martonchik J V,Diner D J,et al. Synergistic algorithm for estimating vegetationcanopy leaf area index and fraction of absorbed photosynthetically active radiation fromMODIS and MISR data.Journal of Geophysical research,1998b,103(D24):32257-32276
Kochubey S M,Kazantsev T A. Changes in the first derivatives of leaf reflectance spectraof various plants induced by variations of chlorophyll content .Journal of PlantPhysiology,2007,164(12):1648-1655
Koger C H,Bruce L M,Shaw D R,et al.Wavelet analysis of hyperspectral reflectance data fordetecting pitted morningglory (Ipomoealacunosa) in soybean (Glycine max).Remote Sensingof Environment,2003,86,108-119.
Kokaly R F,Clark R N. Spectroscopic determination of leaf biochemistry using band-depthanalysis of absorption features and stepwise multiple linear regression. Remote Sensingof Environment,1999,67,267-287
Kokaly R F. Investigating a physical basis for spectroscopic estimates of leaf nitrogenconcentration. Remote Sensing of Environment,2001,75,153-161
Kokaly R F,Despain D G,Clark R N,et al. Mapping vegetation in Yellowstone National Park usingspectral feature analysis of AVIRIS data. Remote Sensing of Environment,84,437-456
Kuusk A. The hot spot effect in plant canopy reflectance. In:Myneni R B,Ross J,eds.Photon-vegetation interactions. Applications in optical remote sensing andplantecology.Berlin:SpringerVerlag,1991,139-159
Laba M,Smith S,Sullivan P,et,al. Influence of wavelet type on the classification of marshvegetation from satellite imagery using a combination of wavelet texture and statisticalcomponent analyses. Canadian Journal of Remote Sensing,2007,33:260-265
Lawrence R,Bunn A,Powell S,et al. Classification of remotely sensed imagery using stochasticgradient boosting as a refinement of classification tree analysis. Remote Sensing ofEnvironment,2004,90(3):331-336
Leung A K,Chau F,Gao J. A review on applications of wavelet transform techniques in chemicalanalysis: 1989-1997. Chemometrics and Intelligent Laboratory Systems,1998,43,165-184
Li Y,Li Z F. Hyperspectral remote sensing of chlorophyll-a in the Xuanwu Lake. InternationalConference on Remote Sensing, Environment and Transportation Engineering(RSETE),2011,2204-2208
Liu M L, Liu X N,Li M. Neural-network model for estimating leaf chlorophyll concentrationin rice under stress from heavy metals using four spectral indices. BiosystemsEngineering,2010,106(3):223-233
Ma X,Zhang H,Zhao X. Semi-Blind Independent Component Analysis of fMRI Based on Real-TimefMRI System. IEEE Transactions on Neural Systems and RehabilitationEngineering,2012,99:1-11
Maas S J, Dunlap. Reflectance, transmittance, and absorption of light by normal, etiolated,and albino corn leaves. Agronomy Journal,1989,81:105-10
MacQueen J B. Some Methods for classification and Analysis of Multivariate Observations.1. Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability.University of California Press.1967,281-297
Mahor A,Rangnekar S. Short term generation scheduling of cascaded hydro electric system usingnovel self adaptive inertia weight PSO. International Journal of Electrical Power &Energy Systems,2012,34(1):1-9
Maier S W,Ludeker W, Gunther K P. SLOP: A Revised Version of the Stochastic Model for LeafOptical Properties. Remote Sensing of Environment,1999,68(3):273-280
Main R, Azong C M, Mathieu R,et al. An investigation into robust spectral indices for leafchlorophyll estimation. ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(6):751-761
Maire L G, Francois C, Dufrene E,et al. Towards universal broad leaf chlorophyll indicesusing PROSPECT simulated database and hyperspectral reflectance measurements. RemoteSensing of Environment,2004,89(1):1-28
Maire L G, Francois C, Soudani K,et al. Calibration and validation of hyperspectral indicesfor the estimation of broadleaved forest leaf chlorophyll content, leaf mass per area,leaf area index and leaf canopy biomass. Remote Sensing ofEnvironment,2008,112(10):3846-3864
Malenovsky Z,Albrechtova J,Lhotákova Z,et,al. Applicability of the PROSPECT model for Norwayspruce needles. International Journal of Remote Sensing,2006,5315-5340
Malenovsky Z, Homolova L,Cudlin P. Physically-based retrievals of Norway spruce canopyvariables from very high spatial resolution hyperspectral data. IEEE InternationalGeoscience and Remote Sensing Symposium(IGARSS),2007,4057-4060
Markwell J,Ostermann J C,Mitchell J L. Calibration of the Minolta SPAD-502 leaf chlorophyllmeter. Photosynthesis Research,1995,46,467-472
Matkan A A,Dashti Ahangar A. Inversion of a Radiative Transfer Model for Estimation of RiceCanopy Chlorophyll Content Using a Lookup-Table Approach. IEEE Journal of SelectedTopics in Applied Earth Observations and Remote Sensing,2011,99,1-9
Mallat S. A wavelet tour of signal processing, 2nd ed. San Diego, USA: Academic Press.1999
Mallat S G. A theory for multiresolution signal decomposition: The waveletrepresentation.IEEE Transactions on Pattern Analysis and MachineIntelligence,1989,11:674-693
Manevski K, Manakos I, Petropoulos G P,et al. Discrimination of common Mediterranean plantspecies using field spectroradiometry. International Journal of Applied EarthObservation and Geoinformation,2011,13(6):922-933
Melendez-Pastor I, Navarro-Pedreno J, Gomez I, et al. Identifying optimal spectral bandsto assess soil properties with VNIR radiometry in semi-arid soils.Geoderma,2008,147(3-4):126-132
Melkemi K E,Batouche M,Foufou S. A multiagent system approach for image segmentation usinggenetic algorithms and extremal optimization heuristics. Pattern RecognitionLetters,2006,27(11):1230-1238
Menhas M I,Wang L,Fei M R,et al. Comparative performance analysis of various binary codedPSO algorithms in multivariable PID controller design. Expert Systems withApplications,2012,39(4):4390-4401
Mercer J. Functions of positive and negative type and their connection with the theory ofintegral equations. Phil.los.Trans. Roy. Soc. London Ser. A, 1909,209:415-446
Miller J,Berger M,Goulas Y,et al. Development of a Vegetation Fluorescence CanopyModel,ESTEC Contract No.16365/02/NL/FF. 2005,138pp.(http://www.ias.csic.es/fluormod/)
Miller D J,Uyar H S.A mixture of experts classifier with learning based on both labelledand unlabelled data. In: M. Mozer, M. I. Jordan, T. Petsche, eds. Advances in NeuralInformation Processing Systems 9, Cambridge, MA: MIT Press, 1997, 571-577
Mitchell T. Machine Learning.McGraw Hill,1997
Mjolsness E,DeCoste D. Machine Learning for Science:State of the Art and FutureProspects.Science,2001,293(5537):2051-2055
Moser G,Serpico S B.Modeling the Error Statistics in Support Vector Regression of SurfaceTemperature From Infrared Data. IEEE Transactions on Geoscience and Remote Sensing,2009,6(3):448-452
Moussaoui S,Hauksdottir H, Schmidt F. On the decomposition of Mars hyperspectral data byICA and Bayesian positive source separation. Neurocomputing,2008,71(10-12):2194-2208
Muller K R,Smola A,Ratsch G,et al. Predicting time series with support vector machines.In:WGerstner,Germond A,Hasler M,Nicoud J D,eds.Lectures Notes in ComputerScience:Artificial Neural Networks ICANN'97.Berlin:Springer,1997,1327:999-1004
Mutanga O,Skidmore A K,Prins H H T. Predicting in situ pasture quality in the Kruger NationalPark, South Africa, using continuum-removed absorption features. Remote Sensing ofEnvironment,2004,89(3):393-408
Myint S W,Lam N S,Tyler J M. Wavelets for urban spatial feature discrimination: Comparisonswith fractal,spatial autocorrelation,and spatial cooccurrence approaches.Photogrammetric Engineering and Remote Sensing, 2004,70:803-812
Nassar A M. Modeling of free jumps downstream symmetric and asymmetric expansions:theoritical analysis and method of stochastic gradient boosting. Journal ofHydrodynamics,2010,22(1):110-120
Nigam K, McCallum A K, Thrun S, et al. Text classification from labeled and unlabeleddocuments using EM. Machine Learning, 2000, 39(2-3):103-134
Nijs I,Behaeghe T, Impens I. Leaf nitrogen content as a predictor of photo-synthetic capacityin ambient and global change conditions. Journal of Biogeography, 1995,22 (2):177-183
Noomen M F, Skidmore A K, van der Meer F D,et al. Continuum removed band depth analysis fordetecting the effects of natural gas, methane and ethane on maize reflectance. RemoteSensing of Environment,2006,105(3):262-270
North P R J. Three-dimensional forest light interaction model using a Monte Carlo method.IEEE Transactions on Geoscience and Remote Sensing.1996,34(4):946-956
Nunez J,Otazu X,Fors O,et,al. Multiresolutionbased image fusion with additive waveletdecomposition. IEEE Transactions on Geoscience and Remote Sensing,1999,37:1204-1211
Osuna E,Freund R,Girosi F. Training support vector machines:An application to face detection.IEEE conference on computer vision and pattern 1997,130-136
Ouma Y O,Tetuko J,Tateishi R. Analysis of co-occurrence and discrete wavelet transformtextures for differentiation of forest and non-forest vegetation invery-high-resolution optical-sensor imagery. International Journal of RemoteSensing,2008,3417-3456
Pal M. Random forest classifier for remote sensing classification. International Journalof Remote Sensing,2005,26(1):217-222
Pearl J. Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoning (UCLATechnical Report CSD-850017). Proceedings of the 7th Conference of the Cognitive ScienceSociety, University of California, Irvine, CA.1985,329-334
Pearlman J S, Barry P S, Segal C C,et al. Hyperion, a space-based imaging spectrometer. IEEETransactions on Geoscience and Remote Sensing.2003,41(6):1160-1173
Pearson, K. On Lines and Planes of Closest Fit to Systems of Points in Space.PhilosophicalMagazine1901,2(6):559-572
Pedros R,Goulas Y, Jacquemoud S,et al. FluorMODleaf:A new leaf fluorescence model based onthe PROSPECT model.Remote Sensing of Environment,2010,114(1):155-167
Pouteau R, Meyer J Y, Stoll B. A SVM-based model for predicting distribution of the invasivetree Miconia calvescens in tropical rainforests. EcologicalModelling,2011,222(15):2631-2641
Poyhonen S,Jover P,Hytyeniemi H. Independent component analysis of vibrations for faultdiagnosis of an induction motor.Mexico:Proceedings of the IASTED InternationalConference on Circuits, Signal and Systems (CSS 2003),2003.203-208
Prasad A M. Iverson L R,Liaw A.Newer classification and regression tree techniques: Baggingand random forests for ecological prediction.Ecosystems,2006,9:181-199
Pu R,Gong P. Wavelet transformapplied to EO-1 hyperspectral data for forest LAI and crownclosure mapping.Remote Sensing of Environment,2004,91:212-224
Qing d E J R, Wang Y P. A new hybrid genetic algorithm for job shop scheduling problem.Computers & Operations Research,2012,39(10):2291-2299
Qiu J,Gao W,Lesht B M,et al. Inverting optical reflectance to estimate surface propertiesof vegetation canopies.International Journal of Remote Sensing,1998,19 (4):641-656
Quinlan J R. Induction of Decision Trees. Machine Learning, 1986,1(1):81-106
Quinlan J R. C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers,1993
Ramoelo A,Skidmore A K,Schlerf M,et al. Water-removed spectra increase the retrievalaccuracy when estimating savanna grass nitrogen and phosphorus concentrations. ISPRSJournal of Photogrammetry and Remote Sensing,2011,66(4):408-417
Rich Caruana, Niculescu-Mizil A. An empirical comparison of supervised learning algorithms.In Proceedings of the 23rd international conference on Machine learning, ICML '06,NewYork, NY, USA,ACM.2006,161-168
Rich Caruana, Karampatziakis N,A Yessenalina. An empirical evaluation of supervised learningin high dimensions. In Proceedings of the 25th international conference on Machinelearning, ICML '08,New York, NY, USA, ACM.2008,96-103
Ren X T,Xu H,Huang Z Y. Fast-ICA Based Blind Estimation of the Spreading Sequences forDown-link Multi-Rate DS/CDMA Signals. Fifth International Conference on IntelligentComputation Technology and Automation (ICICTA), 2012,501-504
Renard N,Bourennane S,Blanc-Talon J. Denoising and Dimensionality Reduction UsingMultilinear Tools for Hyperspectral Images. Geoscience and Remote SensingLetters,2008,5 (2):138-142
Rivard B,Feng J,Gallie A,et al. Continuous wavelets for the improved use of spectrallibraries and hyperspectral data. Remote Sensing of Environment,2008,112:2850-2862
Ridgeway G. The state of boosting. Comp.Sci.Stat.1999,31:172-181
Robert E Schapire. The boosting approach to machine learning:An overview,2002
Robi Polikar. Ensemble based systems in decision making. IEEE Circuits and SystemsMagazine,Third Quarter:2006,21-45
Rosema A,Verhoef W,Schroote J,et al. Simulating fluorescence light-canopy interaction insuppor to flaser-induced fluorescence measurements. Remote Sensing ofEnvironment,1991,37(2):117-130
Rummery G,Niranjan M. On learning Using Connectionist Systems.England Cambridge UniversityEngineering Department Technical Report CUED/F-NFENG/TR166,1994
Ruspini E H. Numerical methods for fuzzy clustering.Information Sciences,1970,2(3):319-350
Schaepman-Strub G, Schaepman M E,Painter T H,et al. Reflectance quantities in optical remotesensing: Definitions and case studies. Remote Sensing of Environment,2006,103(1):27-42
Schapire R,Freund Y,Bartlett P. Boosting the margin:a new explanation for the effectivenessof voting methods.The Annals of Statistics,1998,26(5):1651-1686
Shahshahani B, Landgrebe D. The effect of unlabeled samples in reducing the small samplesize problem and mitigating the hughes phenomenon. IEEE Transactions on Geoscience andRemote Sensing, 1994, 32(5):1087-1095
Schapire R. The strength of weak learnability. Machine Learning,1990,5(2):197-227
Shi jinWang,Avin D Mathew,Yan Chen,et al. Empirical analysis of support vector machineensemble classifiers.2009,6466-6476
Shi W,Zhu C,Zhu C,Yang X. Multi-band wavelet for fusing SPOT panchromatic and multispectralimages.Photogrammetric Engineering and Remote Sensing,2003,69:513-520
Sibson R. SLINK: an optimally efficient algorithm for the single-link cluster method. TheComputer Journal (British Computer Society),1973,16(1):30-34
Sims D A,Gamon J A. Relationships between leaf pigment content and spectral reflectanceacross a wide range of species,leaf structures and developmental stages. Remote Sensingof Environment,2002,81(2-3):337-35
Strang G.Nguyen T. Wavelets and filter banks. Wellesley, MA:Wellesley-Cambridge Press,1996
Stagakis S,Markos N,Skyioti O,et al. Monitoring canopy biophysical and biochemicalparameters in ecosystem scale using satellite hyperspectral imagery:An application ona phlomis fruticosa Mediterranean ecosysem using multiangular CHRIS/PROBA observations.Remote Sensing of Environment, 2010,114(5):977-994
Stumpf A, Kerle N. Combining Random Forests and object-oriented analysis for landslidemapping from very high resolution imagery. Procedia Environmental Sciences,2011,3,123-129
Suits G H. The calculation of the directional reflectance of a vegetative canopy. RemoteSensing of Environment,1972,2:117-125
Sutton R S. Learning to Predict by the Methods of Temporal Differences. Machine Learning,1988,3(1):9-44
Tang E K,Suganthan P N,Yao X. An analysis of diversity measures. MachineLearning,2006,65(1):247-271
Torrence C,Compo G P. A practical guide to wavelet analysis. Bulletin of the AmericanMeteorological Society,1998,79:61-78
Trafalis T B,Ince H. Support vector machine for regression and applications to financialforecasting.Neural Network.IJCNN 2000. Proceedings of the IEEE-INNS-ENNS IntemationalJoint Conference,2000,348-353
Türkan M,Dulek B,Onaran I. Human face detection in video using edge projections. Proceedingsof SPIE-6246.doi:10.1117/12.666704
Unser M,Aldroubi A. A review of wavelets in biomedical applications. Proceedings of theIEEE,1996,84:626-638
Verdebout J, Jacquemoud S,Schmuck G. Optical Properties of Leaves: Modelling andExperimental Studies.In: Hill J,Megier J(Ed.),IMAGING SPECTROMETRY-A TOOL FORENVIRONMENTAL OBSERVATIONS,ECSC,EEC,EAEC,Brussels and Luxembourg,1994,4,169-191
Verhoef W. Light scattering by leaf layers with application to canopy reflectancemodeling:the SAIL model.Remote Sensing of Environment,1984,16(2):125-141
Verhoef W. Earth observation modeling based on layer scattering matrices. Remote Sensingof Environment,1985,17(2):165-178
Verhoef W,Bach H. Simulation of hyperspectral and directional radiance images using coupledbiophysical and atmospheric radiative transfer models. Remote Sensing ofEnvironment,2003,87(1):23-41
Verhoef W,Bach H. Coupled soil-leaf-canopy and atmosphere radiative transfer modeling tosimulate hyperspectral multi-angular surface reflectance and TOA radiance data. RemoteSensing of Environment,2007,109(2):166-182
Valiant L G. A theory of the learnalbe.Communications of the ACM,1984,27 (11):1134-1142
Vapnik V N. An Overview of Statistical Learning Theory. IEEE Transactions on NeuralNetworks,1999,10(5):988-999
Vapnik V. The nature of statistical learning theory.NewYork,NY:Springer-Verlag,1995.138-145
Vasumathi B,Moorthi S. Implementation of hybrid ANN–PSO algorithm on FPGA for harmonicestimation. Engineering Applications of Artificial Intelligence, 2012,25(3):476-483
Walthall C,Dulaney W,Anderson M,et al. A comparison of empirical and neural networkapproaches for estimating corn and soysoybean leaf area index from Landsat ETM+ imagery.Remote Sensing of Environment,2004,92(4):465-474
Wang J,Chang C I. Applications of Independent Component Analysis in Endmember Extractionand Abundance Quantification for Hyperspectral Imagery. IEEE Transactions on Geoscienceand Remote Sensing,2006,44(9):2601-2616
Wang J,Wu X,Zhang C. Support vector machines based on k-means clustering for real-timebusiness intelligence systems. International Journal of Business Intelligence and DataMining,2005,1(1):54-64
Waske B,Benediktsson J. Fusion of support vector machines for classification of multisensordata.IEEE Transactions on Geoscience and Remote Sensing,2007,45(12):3858-3866
Watkins C. Q-Learning. Machine Learning,1992,8(3):279-292
Weiss M,Baret F. Evaluation of canopy biophysical variable retrieval performances from theaccumulation of large swath satellite data. Remote Sensing of Environment,1999,70(3):293-306
Weiss M,Baret F,Myneni R B,et al. Investigation of a model inversion technique to estimatecanopy biophysical variables from spectral and directional reflectance data. Agronomie,2000,20(1):3-22
Weiss M,Troufleau D,Baret F,et al. Coupling canopy functioning and radiative transfer modelsfor remote sensing data assimilation. Agricultural and Forest Meteorology,2001,108(2):113-128
Wenxin Jiang. Boosting with noisy data:Some views from statistical theory. NeuralComputation,2004,16(4):789-810
Xue L H,Yang L Z. Deriving leaf chlorophyll content of green-leafy vegetables fromhyperspectral reflectance. ISPRS Journal of Photogrammetry and Remote Sensing, 2009,64(1):97-106
Yamada N,Fujimara S. Nondestructive measurement of chlorophyll pigment content in plantleaves from three-color reflectance and transmittance. Applied Optics,1991,30(27):3964-3973
Yang F H; White H A.; Michaelis A R. Prediction of Continental-Scale Evapotranspiration byCombining MODIS and AmeriFlux Data Through Support Vector Machine. IEEE Transactionson Geoscience and Remote Sensing, 2006,44(11):3452-3461
Yanjuan Yao,Qinhuo Liu,Qiang Liu,et al. LAI retrieval and uncertainty evaluations fortypical row-planted crops at different growth stages. Remote Sensing of Environment92.2004,139-152
Youngentob K N,Roberts D A,Held A A,etal. Mapping two Eucalyptus subgenera using multipleendmember spectral mixture analysis and continuum-removed imaging spectrometrydata.Remote Sensing of Environment,2011,115(5):1115-1128
Yu X W, Hyypp J, Vastaranta M, et al. Predicting individual tree attributes from airbornelaser point clouds based on the random forests technique. ISPRS Journal of Photogrammetryand Remote Sensing, 2011,66(1):28-37
Zarco-Tejada P J,Berjon A,Lopez-Lozano R,et al. Assessing vineyard condition withhyperspectral indices:Leaf and canopy reflectance simulation in a row-structureddiscontinuous canopy. Remote Sensing of Environment,2005,99(3):271-287
Zhang J,Rivard B,Sánchez-Azofeifa A,et,al. Intra- and inter-class spectral variability oftropical tree species at La Selva,Costa Rica:Implications for species identificationusing HYDICE imagery. Remote Sensing of Environment,2006,105:129-141
Zhang Q,Xiao x,Braswell B,et al. Estimating light absorption by chlorophyll, leaf and canopyin a deciduous broadleaf forest using MODIS data and a radiative transfer model. RemoteSensing of Environment,2005,99(3):357-371
Zhang Y,Hong G. An IHS and wavelet integrated approach to improve pansharpening visualquality of natural colour IKONOS and QuickBird images. InformationFusion,2005,6:225-234
Zhou J,Civco D L,Silander J A. A wavelet transform method to merge Landsat TM and SPOTpanchromatic data. International Journal of Remote Sensing,1998,19:743-757
Zhu M. Kernels and ensembles:perspectives on statistical learning. The AmericanStatistician,2008,62(2):97-109
Zhu X,Ghahramani Z,Lafferty J. Semi-supervised learning using Gaussian fields and harmonicfunctions. In: Proceedings of the 20th International Conference on Machine Learning(ICML’03),Washington,DC,2003,912-919
曹仕,刘湘南,刘清俊.利用独立变量分析与高光谱植被指数模型监测成熟期水稻中砷污染.农业环境科学学报, 2010,29(5):881-886
曹仕,刘湘南,刘美玲,等.融合冠层水分特征的光谱参数NCVI及反演玉米LAI.光谱学与光谱分析,2011,31(2):478-482
宦若虹,张平,潘赟. PCA、ICA和Gabor小波决策融合的SAR目标识别.遥感学报,2012,16(2):262-274
金铭,刘湘南,李铁瑛.基于冠层多维光谱的水稻镉污染胁迫诊断模型研究.中国环境科学, 2011,31(1):137-143
梁顺林.定量遥感.北京:科学出版社,2009,209-210
来海锋,韩斌,厉力华.基于集成类随机森林方法的神经胶质瘤特征基因选择的研究.生物物理学报,2010,26 (9):833-845
李蜜,刘湘南,刘美玲.基于模糊神经网络的水稻农田重金属污染水平高光谱预测模型.环境科学学报,2010,30(10):2108-2115
李波霞,魏玉辉,席莉莉,等.近红外光谱和化学计量学对不同产地不同产期当归的定性研究.光谱实验室,2011,28(4):2128-2134
林婷,刘湘南,金铭.改进ICA算法及其在作物光谱分类中的应用.计算机工程, 2011,37 (11):272-274
刘美玲,刘湘南,曹仕,等.基于高光谱高频组份分形特征的水稻铅胁迫评估.遥感学报,2011,15(4):811-830
刘湘南,佟志军,刘志明,等.遥感数字图像处理与分析.长春,吉林大学出版社,2005,63-64
刘洋,刘荣高,刘斯亮,等.基于物理模型训练神经网络的作物叶面积指数遥感反演研究.地球信息科学学报,2010,12 (3):426-435
阮华,戴连奎.支持向量机分类与回归联合建模方法及其在拉曼光谱分析中的应用.仪器仪表学报,2011,31(11):2440-2446
孙艳辉,吴霖生,翁长晟.应用同步荧光光谱和支持向量机快速鉴别油茶籽油真伪.食品工业科技,2012,4,52-55
汤旭光,宋开山,刘殿伟,等.基于可见/近红外反射光谱的大豆叶绿素含量估算方法比较.光谱学与光谱分析,2011,31(2):371-374
王平,刘湘南,黄方.受污染胁迫玉米叶绿素含量微小变化的高光谱反演模型.光谱学与光谱分析,2010,30(1):197-201
巫兆聪,欧阳群东,胡忠文.应用分水岭变换与支持向量机的极化SAR图像分类.武汉大学学报(信息科学版),2012,37(1):7-10
武佳丽,顾行发,余涛,等.基于SAIL模型的HJ-1卫星LAI反演算法研究.微计算机信息,2010,26(4-1):204-206
肖强,叶文景,朱珠,等.利用数码相机和Photoshop软件非破坏性测定叶面积的简便方法.生态学杂志,2005,24(6):711-714
杨曦光,范文义,于颖.基于PROSPECT+SAIL森林冠层叶绿素含量反演.光谱学与光谱分析,2010a,30(11):3022-3026
杨曦光,范文义,于颖.森林叶绿素含量的高光谱遥感估算模型的建立.森林工程,2010b,26(2):8-11
姚付启,张振华,杨润亚,等.基于主成分分析和BP神经网络的法国梧桐叶绿素含量高光谱反演研究.测绘科学,2010,35(1):109-112
岳征文,王红柳,成格尔.近红外光谱技术结合支持向量机法在保水剂鉴别工作中的应用.干旱区资源与环境,2012,26(4):172-175
张东彦,刘镕源,宋晓宇,等.应用近地成像高光谱估算玉米叶绿素含量.光谱学与光谱分析,2011,31(3):771-775
张雷,刘世荣,孙鹏森,等.气候变化对马尾松潜在分布影响预估的多模型比较.植物生态学报,2011,35 (11):1091-1105
张西雅,徐海卿,李培军.运用EO-1 Hyperion数据和单类支持向量机方法提取岩性信息.北京大学学报(自然科学版), 2012,http://www.cnki.net/kcms/detail/11.2442.N.20120224.1047.011.html