Non-Linear Methods Could More Accurately Measure Chlorophyll Content in Grape Foliar Non-Destructively with Visible/Red-Infrared Hyperspectral

Abstract:

Efficient methods of non-destructively measuring chlorophyll content (Chl) across a wide range of greenness in grape leaves are necessary for a producer to effectively monitor the status of the crop. Wet chemical methods and handheld leaf Chl meters such as the Minolta SPAD-502 Chl meter(Markwell,1995) have traditionally been used for this purpose. Recently, the availability of small and affordable radiometers , which uses Near infra-red and Red edge(CI_{red edge})( Mark R. Steel, 2008b), for Chl estimation in grapevine leaves, has provided means to estimate Chl from reflectance measurements. The two methods were equally accurate measuring pigments at low to moderate Chl levels. But, when Chl exceeded 300 mg/m², SPAD sensitivity to Chl declined noticeably and the accuracy of Chl estimation by the CI_{red edge} was much higher than that of the SPAD meter, the chlorophyll index was found to be capable of accurately estimating pigment contents across a much greater Chl range than the SPAD meter. However, in this paper an artificial-intelligence technique, the Support Vector Machine (SVM^LightV6.01) model was introduced to establish the relationship between the Chlorophylls content and reflectance of 400-750 nm spectrum, variation of species and growth stages, which can much more perfectly compensated the reflectance that was absorpted by anthocyanin and carotenoids and scatterd because of different leaf thickness, density, or surface properties. As a result that we have solved the problems such as saturation and/or asymptote in high/or lower content of chlorophyll, and SVM model was found to be capable of more accurately estimating pigment contents across a greater range than the SPAD and CI_{red edge,} thus it can be used for quantitative assessment of early stages of pant stress.

• Periodical: Advanced Materials Research (Volumes 239-242)
• Pages: 2376-2388
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.239-242.2376
• Online since: May 2011
• Authors: Jiang Lin Qin
• Keywords: Chlorophyll, Grape, Hyper-Spectral, Support Vector Machine (SVM)

References

[1] Blackburn, G. A.,1998a. Quantifying Chlorophylls and Carotenoids at Leaf and Canopy Scales; An Evaluation of Some Hyperspectral Approaches. Remote Sensing of Environment, 66(3), 273– 285.

DOI: 10.1016/s0034-4257(98)00059-5

[2] Blackburn, G. A. ,1998b. Spectral Indices for Estimating Photosynthetic Pigment Concentrations: Test Using Senescent Tree Leaves. International Journal of Remote Sensing, 19(4), 657– 675.

DOI: 10.1080/014311698215919

[3] Buschmann, C.,and E.Nagel,1993. In vivo spectroscopy and internal optics of leaves as basis for remote sensing of vegetation, Int.J.Remote Sens.,14,711-722.

DOI: 10.1080/01431169308904370

[4] Broge, N.H., and J.V. Mortensen(2002), Deriving green corp area index and canopy chlorophyll density of winter wheat from spectal reflectance data, Remote Sens. Environ.,81,45-57.

DOI: 10.1016/s0034-4257(01)00332-7

[5] Campbell, James B., 1987. Introduction to Remote Sensing. The Guilford Press, New York

[6] Curran P.J.,1989. Remote Sensing of Foliar Chemistry. REMOTE SENS. ENVIRON. 30:271-278.

[7] Curran P.J.,J.L. Dunfan, and H.L. Gholz.1990. Exlporing the relationship between reflectance red edge and Chl content in slash pine. Tree Physiol.7:33-48.

DOI: 10.1093/treephys/7.1-2-3-4.33

[8] Danks S.M., E. H. Evans, and P.A. Whittaker,1984.Photosynthetic Systems: Structure, Function and Assembly, John Wiley, Hoboken, N.J.

[9] Dash,J., and P.J. Curran,2004. The MERIS terrestrial chlorophyll index, Int.J.Remote Sens.,25,5403-5413.

DOI: 10.1080/0143116042000274015

[10] Datt, B. ,1999. Visible/Near Infrared Reflectance and Chlorophyll Content in Eucalyptus Leaves. International Journal of Remote Sensing, 20(14), 2741– 2759.

DOI: 10.1080/014311699211778

[11] Daugtry, C.S.T.,C.L. Walthall, M.S. Kim, E. Brown de Colstoun, and J.E. McMurtrey III, 2000. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance, Remote Sens. Eviron.,74,229-239.

DOI: 10.1016/s0034-4257(00)00113-9

[12] Filela,I.,I.Serrano,J.Serra,and J Penuelas,1995.Evaluating wheat nitrogen status with canopy reflectance indices and discriminant analysis.Crop Sci.35:1400-1405.

DOI: 10.2135/cropsci1995.0011183x003500050023x

[13] Gitelson A.A., Mark N. Merzlyak and Olga B. Chivkunova. Optical Properties and Nondestrstructive Estimeation of Anthocyanin Content in Plant Leaves.Photochemistry and Photobiology,2001,74(1):38-45.

DOI: 10.1562/0031-8655(2001)0740038opaneo2.0.co2

[14] Gitelson A.A., Galina P. Keydan, and Mark N.Merzlyyak. Three-band model for nonvasive estimation of chlorophyll, carotenoids, and anthocyyanin content in higher plant leaves. GEOPHSICAL RESEARCH LETTERS, VOL.33,L11402, doi:10.1029/2006 GL026457,2006.

DOI: 10.1029/2006gl026457

[15] Gitelson A.A., Andrés Viña, Veróna Ciganda, Donald C.Rundquist, and Timothy J.Arkebauer. Remote estimation of canopy chlorophyll content in crops. Geophsical Research Letters, VOL.32,L10843, doi:10.1029/2005 GL022688,2005.

DOI: 10.1029/2005gl022688

[16] Giorgio Dall'Olmo ,A.G. Anatoly, C.R. Donald,2003. Towards a unified approach for remote estimation of chlorophyll-a in both terrestrial vegetation and turbid productive waters. Geophsical Research Letters, 30(18),1938.

DOI: 10.1029/2003GL018065

[17] Gitelson, A.A., Y.Kaufman, and M. Merzlyak,1996b. Use of a Green Channel in Remote Sensing of Global Vegetation from EOS-MODIS. Remote Sensing of Environment, 58, 289-298.

DOI: 10.1016/s0034-4257(96)00072-7

[18] Gitelson, A.A., M. Merzlyak, and H. Lichtenthaler,1996b. Detection of red edge position and Chlorophyll content by reflectance measurements near 700nm. J.Plant Physiol., 148,501-508.

DOI: 10.1016/s0176-1617(96)80285-9

[19] Gitelson, A. A.,2004. Wide Dynamic Range Vegetation Index for Remote Quantification of Crop Biophysical Characteristics. Journal of Plant Physiology. 161, 165-173.

DOI: 10.1078/0176-1617-01176

[20] Gitelson, A.A., U. Gritz and M. Merzlyak.,2003. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. Journal of Plant Physiology, 160(3), 271-282.

DOI: 10.1078/0176-1617-00887

[21] Gitelson, A. A., and M. Merzlyak,1994. Spectral Reflectance Changes Associate with Autumn Senescence of Aesculus hippocastanum L. and Acer platanoides L. Leaves. Spectral Features and Relation to Chlorophyll Estimation. Journal of Plant Physiology, 143, 286–292.

DOI: 10.1016/s0176-1617(11)81633-0

[22] Gitelson, A.A., and M. N. Merzlyak,2004. Non-Destructive Assessment of Chlorophyll, Carotenoid and Anthocyanin Content in Higher Plant Leaves: Principles and Algorithms. Remote Sensing for Agriculture and the Environment. Greece, Ella, 2004, 78-94.

DOI: 10.1109/igarss.1996.516985

[23] Grant,L.,1987. Review article. Diffuse and Specular Characteristics of Leaf Reflectance .Remote Sensing of Environment.22:309-322.

DOI: 10.1016/0034-4257(87)90064-2

[24] Huete, A. R.,1988. A Soil Adjusted Vegetation Index (SAVI). Remote Sensing of Environment 25, 295-309.

DOI: 10.1016/0034-4257(88)90106-x

[25] Jensen, J.,2000. Remote Sensing of the Environment: An Earth Resource Perspective. 1st Edition. Prentice Hall, Upper Saddle River.

[26] Jensen, J.,2005. Introductory Digital Image Processing: A Remote Sensing Perspective. 3rd Edition. Prentice Hall, Upper Saddle River.

[27] Joachims, T.,1999a. Estimating the generalization performance of a SVM efficiently (LS VIIIReport 25). Universität Dortmund, Germany.\

[28] Joachims, T.,1999b. Making large-scale SVM learning practical. In B. Schölkopf, C. Burges, &A. Smola (Eds.), Advances in kernel methods - Support vector learning. Cambridge, MA: MIT Press.

DOI: 10.7551/mitpress/1130.003.0015

[29] Joachims,T.,2002.Optimizing Search Engines Using Clickthrough Data, Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD), ACM.

DOI: 10.1145/775047.775067

[30] Joachims,T.,2002. Learning to Classify Text using Support Vector Machines Methods, Theory, and Algorithms. Dissertation, Kluwer, 2002.

DOI: 10.1007/978-1-4615-0907-3_3

[31] Kanemasu, E.T.,1974. Seasonal canopy reflectance patterns of wheat, sorghum, and soybean, Remote Sens. Environ.,3,43-47.

DOI: 10.1016/0034-4257(74)90037-6

[32] Kearns, M., And D. Ron,1997. Algorithmic stability and sanity-check bounds for leave-one-out crossvalidation. Proceedings of the Tenth Conference on Computational Learning Theory (p.152{162). New York: ACM Press

DOI: 10.1145/267460.267491

[33] Klinkenberg,R. and T. Joachims, 2000.Detecting Concept Drift with Support Vector Machines. Proceedings of the Seventeenth International Conference on Machine Learning (ICML), Morgan Kaufmann.

[34] Lanjeri, S., J. Melia, and D. Segarra, 2001. A Multi-Temporal Masking Classification for Vineyard Monitoring in Central Spain. International Journal of Remote Sensing, 22(16): 3167-3186.

DOI: 10.1080/01431160152558305

[35] Mark R.Steel, Anatoly A.Gitelson,Donal C.Rundquist,2008.A Comparison of Two Techniques for Non-Destructive Measurement of Chlorophyll Content in Grapevine Leaves.Agronomy Journal,100(3):779-782.

DOI: 10.2134/agronj2007.0254n

[36] Mark R.Steel, Anatoly A.Gitelson,Donal C.Rundquist,2008.Research Note Nodestructive Estimation of Leaf Cholorophyll Content in Grapes.American Journal of Enology and Viticulture,59(3):299-305.

DOI: 10.5344/ajev.2008.59.3.299

[37] Markwell, J., J. Osterman and J. Mitchell. 1995. Calibration of the Minolta SPAD-502 Leaf Chlorophyll Meter. Photosynthesis Research, 46, 467 – 472.

DOI: 10.1007/bf00032301

[38] Montero, F., J. Melia, A. Brasa, D. Segarra, A. Cuesta, and S. Lanjeri, 1999. Assessment of Vine Development According to Available Water Resources by Using Remote Sensing in LaMancha, Spain. Agricultural Water Management, 40, 363-375.

DOI: 10.1016/s0378-3774(99)00010-4

[39] Poni, S.,C. Intrieri, and O.Silvestroni. 1994. Interactions of leaf age, fruiting, and exogenous cytokinins in Sangiovese grapevines under non-irrigated conditions Ⅱ. Cholorophyll and nitrogen content, American Journal of Enology and Viticulture,45:278-284.

DOI: 10.5344/ajev.1994.45.3.278

[40] Porra, R. J., W. Thomson and P. Kriedmann,1989. Determination of Accurate Extinction Coefficients and Simultaneous Equations for Assaying Chlorophylls a and b Extracted with Four Different Solvents: Verification of the Concentration of Chlorophyll Standards by Atomic Absorption Spectroscopy. Biochimica et Biophysica Acta, 975, 384– 394.

DOI: 10.1016/s0005-2728(89)80347-0

[41] Pirie, A. and M.G. Mullins,1976. Changes in Anthocyanin Phenolics Content of Grapevine Leaf and Fruit Treated with Sucrose, Nitrate, and Abscisc Acid. Plant Physiol. 58:468-472.

DOI: 10.1104/pp.58.4.468

[42] Richardson, A. D., S. Duigan, and G. Berlyn,2002. An Evaluation of Noninvasive Methods to Estimate Foliar Chlorophyll Content. New Phytologist, 153(1), 185– 194.

DOI: 10.1046/j.0028-646x.2001.00289.x

[43] Rouse, J. W., R. Haas, J. Schell, and D. Deering, 1973. Monitoring Vegetation Systems in the Great Plains with ERTS. In N. SP-351, Ed. Third ERTS symposium, 1, 309 – 317. Washington: NASA.

[44] Thomas J.R., and H.W. Gaussman,1977. Leaf reflectance vs. leaf Chlorophyll and carotenoid concentration for eitht crops, Agron.J.69,799-802.

DOI: 10.2134/agronj1977.00021962006900050017x

[45] Qin J.L.. Preliminary Inquiry On Technical Support System for the Precision-Farming with Chinese Characteristics. TRANSACTION OF THE CHINESE SOCIETY OF AGRICULTRAL ENGINEERING, Vol.17, 2001, No:3, 1-6.

[46] Vapnik, V.,1998. Statistical learning theory. Chichester, UK: Wiley.

[47] Viña,A.,A.A. Gitelson,2005. New developments in the remote estimation of the fraction of absorbed photosythetically active radiation in crops.Geophysical research letters, 32,L17403,doi:10.1029/ 2005GL023647,2005.

DOI: 10.1029/2005gl023647

[48] Wahba, G.,1999. Support vector machines, reproducing kernel hilbert spaces, and randomized gacv.In B.Schölkopf, C. Burges, & A. Smola (Eds.), Advances in kernel methods - Support vector learning.Cambridge, MA: MIT Press.

DOI: 10.7551/mitpress/1130.003.0009

[49] Taylor S.F., D.W. Lee, and N.M. Holbrook. Why Leaves Turn Red in Autumn. The Role of Anthocyanins in Sensescing Leaves of Red-Osier Dogwood, Plant Physiology,October 2001,Vol.127,pp.566-574.

DOI: 10.1104/pp.010063

[50] Tsochantaridis, I., T.Hofmann, T.Joachims, and Y.Altun,2004. Support vector machine learning for interdependent and structured output spaces. ICML.

DOI: 10.1145/1015330.1015341

[51] Tsochantaridis, I.,T.Joachims, T.Hofmann, and Y.Altun,2005. Large margin methods for structured and interdependent output variables. JMLR, 6, 1453–1484.

[52] Yu, C.N.,T.Joachims, R.Elber, and J.Pillardy, 2007.Support vector training of protein alignment models.RECOMB.

DOI: 10.1007/978-3-540-71681-5_18