Determination of sugar beet nitrogen status by spectral discriminant analysis

Yıl 2019, Cilt: 7 Sayı: 2, 128 - 138, 31.12.2019

Mert Dedeoğlu Levent Başayiğit Murat Erişoğlu

https://doi.org/10.33409/tbbbd.668890

Cited By: 1

Öz

In this study, it is aimed to develop a method by using hyperspectral reflections to determine the leaf N% status of sugar beet which
is strategically important for our country. For this purpose, 72 experimental plants were grown in controlled greenhouse conditions
and perlite environment with Hoagland solutions with deficient and excess N content representing 3 different vegetation stages,
then spectral measurements were taken between 400-1000 nm by spectroradiometer and leaf samples were collected for
determination of N%. Stepwise multiple regression analysis was applied to determine the wavelengths associated with different
periods and N doses in sugar beet leaves and 5 wavelengths (474-517-652-721-961 nm) were selected for the highest contribution
to the total variance from the 48 different wavelength reflection values. The Quadratic Discriminant Analysis (QDA) model, which
was coded using determined wavelengths, assigned 72 plants to their real classes (NDeficient; 92%, NSufficient; 88% and NExcess; 96%)
with 92% accuracy. The 36 test data used for validation of the model were discriminated into 89% N classes (NDeficient; 91%,
NSufficient; 85% and NExcess; 92%) with 89% accuracy, and it was determined that using QDA model with spectral reflections of the
selected wavelengths can be used to detect for sugar beet N demand during different vegetation stages. As a result of the research
has been obtained encouraging findings for the use of discriminant models to the studies on determination of plant nutritional
status by spectral data and we was proposed that the QDA model should be developed using different plant species and nutrients on
the experimental designs.

Anahtar Kelimeler

Hyperspectral reflectance, nitrogen, quadratic discriminant, spectroradiometer

Şeker pancarı yapraklarında azot durumunun spektral diskriminant analizi ile belirlenmesi

Öz

Bu çalışmada ülkemiz için stratejik öneme sahip şekerpancarı bitkisinin yaprak %N sınıflarının belirlenmesine yönelik
hiperspektral yansımalar kullanılarak bir yöntem geliştirilmesi amaçlanmıştır. Bu amaçla 3 farklı vejetasyon evresini temsil eden
noksan, yeter ve fazla N içerikli Hoagland sölüsyonları (Hoagland ve Arnon, 1938) ile 72 deneme bitkisi kontrollü sera şartlarında,
perlit ortamında yetiştirilmiş, spektroradyometre ile 400-1000 nm arası spektral ölçümler ve %N tayini için yaprak örneklemeleri
yapılmıştır. Şekerpancarı yapraklarında farklı dönem ve dozlarla ilişkili dalgaboylarının belirlenmesinde stepwise çoklu regresyon
analizi uygulanmış ve belirlenen 48 farklı dalgaboyu yansıma değerinden temel bileşenler analizi ile toplam varyansa en yüksek
katkıyı sağlayan 5 dalgaboyu (474-517-652-721-961 nm) model için seçilmiştir. Belirlenen dalgaboyları kullanılarak kodlanan
Karesel Diskriminant Analiz (KDA) modeli 72 bitkiyi %92 doğrulukla gerçek sınıflarına (NNoksan ; %92, NYeter; %88 ve NFazla; %96)
atamıştır. Modelin validasyonu için kullanılan 36 test verisinin %89 doğrulukla %N sınıflarına (NNoksan; %91, NYeter; %85 ve NFazla;
%92) ayrımı yapılmış ve seçilen dalgaboylarından olan spektral yansımaların KDA modeli ile farkı vejetasyon dönemleri için
şekerpancarı azotlu gübreleme ihtiyacının tespitinde kullanılabilir olduğu belirlenmiştir. Araştırma sonucu spektral veriler ile bitki
besin durumunun belirlenmesine yönelik çalışmalara diskriminant modellerinin kullanımı için umut verici bulgular elde edilmiş ve
KDA modelinin farklı bitki türü ve besin elementleri için kurgulanacak deneme desenlerinde kullanılarak geliştirilmesi önerilmiştir.
Anahtar Kelimeler: Azot, hiperspektral yansıma, karesel diskriminant, spektroradyometre.

Anahtar Kelimeler

Azot, hiperspektral yansıma, karesel diskriminant, spektroradyometre

Kaynakça

• Alpaslan M, Güneş A, İnal A, 2005. Deneme tekniği. Ankara Üniversitesi Ziraat Fakültesi Yayınları, (1501): 455.
• Anonim, 2018. http://www.tarim.gov.tr/Konular/Bitkisel-Uretim/Bitki-Besleme-ve-Tarimsal-Teknolojiler/Bitki-Besleme-Istatistikleri.
• Ayala-Silva T, Beyl CA, 2005. Changes in spectral reflectance of wheat leaves in response to specific macronutrient deficiency. Adv. in Space Res. 35(2): 305-317.
• Bagheri N, Ahmadi H, Alavipanah S, Omid M 2012. Soil-line vegetation indices for corn nitrogen content prediction. Int. Agrophysics. 26(2): 103-108.
• Basayigit L, Albayrak S, Senol H, 2009. Analysis of VNIR reflectance for prediction of macro and micro nutrient and chlorophyll contents in apple trees (Malus communis). Asian J. of Chem. 21(2): 1302.
• Basayigit L, Dedeoglu M, Akgül H, 2015. The prediction of iron contents in orchards using VNIR spectroscopy. Turk J Agric For. 39(1): 123-134.
• Başayigit L, Dedeoğlu M, Akgül H, Uçgun K, Altındal M, 2017. Investigation of N deficiency in cherry trees using visible and near-infrared spectra part of the spectrum in field condition. Spectroscopy and Spectral Analysis. 37(1): 293-298.
• Curran PJ, Dungan JL, Peterson DL, 2001. Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: Testing the kokaly and clark methodologies. Remote Sensing of Environment. 76(3): 349–359.
• Çalış N, Erol H, 2012. A new per-field classification method using mixture discriminant analysis. Journal Of Applied Statistic. 39(10): 2129-2140.
• Demotes-Mainard S, Boumaza R, Meyer S, Cerovic ZG, 2008. Indicators of nitrogen status for ornamental woody plants based on optical measurements of leaf epidermal polyphenol and chlorophyll contents. Scientia Horticulturae. 115(4): 377-385.
• Deng S, Xu Y, Li X, He Y, 2015. An infinite Gaussian mixture model with its application in hyperspectral unmixing. Expert Systems with Applications. 42(4): 1987-1997.
• Draycott AP, Christenson DR, 2003. Nutrients for sugar beet production: Soil-plant relationships. Cabi.
• Eitel JU, Vierling LA, Litvak ME, Long DS, Schulthess U, Ager AA, Stoscheck L, 2011. Broadband, red-edge information from satellites improves early stress detection in a New Mexico conifer woodland. Remote Sensing of Environment. 115(12): 3640-3646.
• Erisoglu U, Erisoglu M, Erol H, 2012. Mixture model approach to the analysis of heterogeneous survival data. Pak. J. Statist. 28(1): 115-130.
• Eyüpoğlu F, 2002. Türkiye gübre gereksinimi tüketimi ve geleceği. Toprak ve Gübre Araştırma Enst. İşlt. Müd. Ankara.
• Faberio C, Martin de Santa Olalla F, Lopez R, Dominguez A, 2003. Production and quality of the sugar beet cultivated under contrelled deficit irrigation conditions in a semi-arid climate. Agric. Water Manage. 62: 215-227.
• Feng W, Guo BB, Wang ZJ, He L, Song X, Wang YH, 2014. Measuring leaf nitrogen concentration in winter wheat using double-peak spectral reflection remote sensing data. Field Crops Research. 159: 43-52.
• Fernàndez-Martínez J, Joffre R, Zacchini M, Fernández-Marín B, García-Plazaola JI, Fleck I, 2017. Near-infrared reflectance spectroscopy allows rapid and simultaneous evaluation of chloroplast pigments and antioxidants, carbon isotope discrimination and nitrogen content in Populus spp. leaves. Forest Ecology and Management. 399: 227-234.
• Fitzgerald G, Rodriguez D, O’Leary G, 2010. Measuring and predicting canopy nitrogen nutrition in wheat using a spectral index—The canopy chlorophyll content index (CCCI). Field Crops Research. 116(3): 318-324.
• Foster AJ, Kakani VG, Ge J, Gregory M, Mosali J, 2016. Discriminant analysis of nitrogen treatments in switchgrass and high biomass sorghum using leaf and canopy-scale reflectance spectroscopy. IJR. 37(10): 2252-2279.
• Gezgin S, Dursun N, Hamurcu M, Ayaslı Y, 1999. Konya ovasında şeker pancarı bitkisinde beslenme sorunlarının toprak ve bitki analizleri ile belirlenmesi. Konya Pancar Ekicileri Kooperatifi Yayını, Konya.
• Gezgin S, Hamurcu M, Dursun N, 2001. Konya ovasında şeker pancarının azot ve fosfor ihtiyacının belirlenmesi. S. Ü. Ziraat Fakültesi Dergisi. 15(25): 119-131.
• Gillis D, Bowles J, Ientilucci EJ, Messinger DW, 2008 A generalized linear mixing model for hyperspectral imagery. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIV, 2008 (Vol. 6966, pp. 69661B): International Society for Optics and Photonics.
• Haboudane D, Miller JR, Tremblay N, Zarco-Tejada PJ, Dextraze L, 2002. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sensing of Environment. 81(2): 416-426.
• Haboudane D, Tremblay N, Miller JR, Vigneault P, 2008. Remote estimation of crop chlorophyll content using spectral indices derived from hyperspectral data. IEEE Trans. Geosci. Remote Sens. 46: 423–437.
• Hastie T, Tibshirani R, Friedman J, Hastie T, Friedman J, Tibshirani R, 2009. The elements of statistical learning. Springer.
• He L, Zhang HY, Zhang YS, Song X, Feng W, Kang GZ, Guo TC, 2016. Estimating canopy leaf nitrogen concentration in winter wheat based on multi-angular hyperspectral remote sensing. European Journal of Agronomy. 73: 170-185.
• Hoagland DR, Arnon DI, 1938. The water culture method for growing plants without soil. Circ. Calif. Agr. Exp. Sta. 347: 461.
• Huang S, Miao Y, Yuan F, Gnyp M, Yao Y, Cao Q, Bareth G, 2017. Potential of RapidEye and WorldView-2 satellite data for improving rice nitrogen status monitoring at different growth stages. Remote Sensing. 9(3): 227.
• Jackson RD, 1986. Remote sensing of biotic and abiotic plant stress. Annual Review of Phytopathology. 24:265–286.
• Jain N, Ray SS, Singh J, Panigrahy S, 2007. Use of hyperspectral data to assess the effects of different nitrogen applications on a potato crop. Precision Agriculture, 8(4-5): 225-239.
• James G, Witten D, Hastie T, Tibshirani R, 2013. An introduction to statistical learning. Springer, New York. 112:18.
• Jay S, Hadoux X, Gorretta N, Rabatel G, 2014. Potential of hyperspectral imagery for nitrogen content retrieval in sugar beet leaves. Proc. int. conf. ag. eng., AgEng2014, Zurich, The European Society of Agricultural Engineers (EurAgEng), 2014:8.
• Jones JR, Wolf B, Mills HA, 1991. Plant analysis handbook. Micro Macro Publishing Inc.
• Ju J, Kolaczyk ED, Gopal S, 2003. Gaussian mixture discriminant analysis and sub-pixel land cover characterization in remote sensing. Remote Sensing of Environment. 84(4):550-560.
• Kacar B, Katkat AV, Oztürk S, 2002. Bitki fizyolojisi. Uludag Ü. Güclendirme Vakfi Yayini. No: 198 Vipas A.S. Yayin No: 74, ISBN: 975-564-133-5 Bursa.
• Karaçal İ, Tüfenkçi Ş, 2010. Bitki beslemede yeni yaklaşımlar ve gübre-çevre ilişkisi. ZMO. 2010.
• Kostrzewski M, Waller P, Guertin P, Haberland J, Colaizzi P, Barnes E, Thompson T, Clarke T, Riley E, Choi C, 2002. Ground-based remote sensing of water and nitrogen stress. Trans. Am. Soc. Assoc. Exec. 46: 29–38.
• Krishna G, Sahoo RN, Singh P, Bajpai V, Patra H, Kumar S, 2019. Comparison of various modelling approaches for water deficit stress monitoring in rice crop through hyperspectral remote sensing. Agricultural Water Management. 213: 231-244.
• Li F, Gnyp ML, Jia LL, Miao YX, Yu ZH, Koppe W, Bareth G, Chen XP, Zhang FS, 2008. Estimating N status of winter wheat using a handheld spectrometer in the North China Plain. Field Crops Res. 106: 77–85.
• Maimaitiyiming M, Ghulam A, Bozzolo A, Wilkins JL, Kwasniewski MT, 2017. Early detection of plant physiological responses to different levels of water stress using reflectance spectroscopy. Remote Sensing. 9(7): 745.
• Manolakis D, Siracusa C, Shaw G, 2001. Hyperspectral subpixel target detection using the linear mixing model. IEEE Transactions on Geoscience and Remote Sensing. 39(7): 1392-1409.
• MathWorks, I. (2007). Instrument control toolbox 2: user's guide. The MathWorks Inc.
• Mee CY, Siva KB, Ahmad HMH, 2017. Detecting and monitoring plant nutrient stress using remote sensing approaches: A review. Asian J. Plant Sci. 16: 1-8.
• Merzlyak MN, Solovchenko AE, Gitelson AA, 2003. Reflectance spectral features and non-destructive estimation of chlorophyll, carotenoid and anthocyanin content in apple fruit. Postharvest Biology and Technology. 27(2): 197-211.
• Morisette JT, Baret F, Privette JL, Myneni RB, Nickeson JE, Garrigues S, Kalacska M, 2006. Validation of global moderate-resolution LAI products: A framework proposed within the CEOS land product validation subgroup. IEEE Transactions on Geoscience and Remote Sensing. 44(7): 1804-1817.
• Reynolds D, 2015. Gaussian mixture models. Encyclopedia of biometrics. 827-832.
• Rodriguez D, Fitzgerald GJ, Belford R, Christensen LK, 2006. Detection of nitrogen deficiency in wheat from spectral reflectance indices and basic crop eco-physiological concepts. Australian Journal of Agricultural Research. 57(7): 781-789.
• Sinfield JV, Fagerman D, Colic O, 2010. Evaluation of sensing technologies for on-the-go detection of macro-nutrients in cultivated soils. Computers and Electronics in Agriculture. 70(1): 1-18.
• Vigneau N, Ecarnot M, Rabatel G, Roumet P, 2011. Potential of field hyperspectral imaging as a non destructive method to assess leaf nitrogen content in Wheat. Field Crops Research. 122(1): 25-31.
• Wang Z, Skidmore AK, Wang T, Darvishzadeh R, Heiden U, Heurich M, 2017. Canopy foliar nitrogen retrieved from airborne hyperspectral imagery by correcting for canopy structure effects. International Journal of Applied Earth Observation and Geoinformation. 54: 84-94.
• Wójtowicz M, Wójtowicz A, Piekarczyk J, 2016. Application of remote sensing methods in agriculture. Communications in Biometry and Crop Science. 11: 31-50.
• Wright AF, Bailey JS, 2001. Organic carbon, total carbon, and total nitrogen determinations in soils of variable calcium carbonate contents using a Leco CN-2000 dry combustion analyzer. Communications in Soil Science and Plant Analysis. 32(19-20): 3243–3258.
• Wu C, Niu Z, Tang Q, Huang W, 2008. Estimating chlorophyll content from hyperspectral vegetation indices: Modeling and validation. Agricultural and Forest Meteorology. 148(8): 1230-1241.
• Zhang HK, Roy DP, Yan L, Li Z, Huang H, Vermote E, 2018. Characterization of Sentinel-2A and Landsat-8 top of atmosphere, surface, and nadir BRDF adjusted reflectance and NDVI differences. Remote Sensing of Environment. 215: 482-494.
• Zhao G, Maclean LA, 2000. A comparison of canonical discriminant analysis and principal component analysis for spectral transformation. Photogramm. Eng. Remote Sens. 66: 841-847.