SULTAN KIYMAZ, UFUK KARADAVUT, AHMET ERTEK

Yapay Sinir Ağları ve Bazı Doğrusal Olmayan Modellerin Farklı Azot Seviyelerindeki Şeker Pancarı Yaprak Alan Tahmininin Karşılaştırılması

Yaprak alanı, birçok büyüme, fotosentez, terleme ve enerji dengesini içeren agronomik ve fizyolojik çalışmalarla ilgilidir. Çalışma, tarla koşullarında farklı azot seviyelerindeki şeker pancarının (Beta vulgaris L.) yaprak alanı tahmininin belirlenmesini amaçlamıştır. Çalışma, tesadüf bloklarında bölünmüş parseller deneme deseninde 3 tekerrürlü olarak 2012-2013 yıllarında yürütülmüştür. Ölçümler yaprak boyu, yaprak eni, yaprak sapı uzunluğu ve bitki başına toplam yaprak sayısı gibi yaprak parametrelerinden alınmıştır. Yapay sinir ağları ve Lojistik, Richards ve Gompertz gibi doğrusal olmayan yöntemler yaprak alanı ölçümlerini tahmin etmek için karşılaştırıldı. Sonuç olarak, tüm modeller üçüncü gübreleme düzeyinde en yüksek tanımlama başarısını göstermiştir. İlk üç gübre dozunda yapay sinir ağları (YSA) modelinde diğer modellere göre daha yüksek bir başarı düzeyi gösterilirken, dördüncü gübre dozunda Richards modeli daha başarılı olmuştur. Azot seviyesinin artması ile bitkinin büyümesi hızlanmaktadır. YSA modeli hızlı büyüme tanımlamasında yetersiz kalırken, Richards modeli daha hızlı büyümede daha başarılı olarak tanımlanmıştır.

Anahtar Kelimeler:

Karşılaştırma, doğrusal olmayan modeller, sinir ağları modeli, şekerpancarı.

A Comparison of Artificial Neural Networks and Some Nonlinear Models of Leaf Area Estimation of Sugar Beet at Different Nitrogen Levels

Leaf area is related to many physiological and agronomic studies including growth, photosynthesis, transpiration, and energy balance. The study aimed to determine the leaf area estimation of sugar beet (Beta vulgaris L.) at different nitrogen levels under field conditions. The study was conducted out in split plots in randomized complete blocks with three replications in 2012-2013, and measurements were taken from leaf parameters, such as length (L) and width (W), petiole length, and the total number of leaf per a sugar beet. The artificial neural networks and such non-linear methods as the Logistic, Richards, and Gompertz were compared to estimate the leaf area measurements. As a result, all models have shown the highest identification success in the level of third fertilization. While the ANN model in the first three fertilizer doses showed a higher definition of success compared to other models, the Richards model in the fourth fertilizer dose has been more successful. An increase in the nitrogen level has accelerated the plant growth. While the ANN model remained insufficient for very rapid growth identification, the Richards model is defined in more successful rapid growth

Keywords:

Comparison, non-linear models, neural network model, sugar beet.,

PDF

___

Blanco, F.F. and Folegatti, M.V. 2005. Estimation of leaf area for greenhouse cucumber by linear measurements under salinity and grafting. Sci. Agr., 62(4): 305-309.
Achten, W.M.J. Maes, W.H. Reubens, B. Mathijs, E. Singh, V.P. Verchot, L. Muys, B. 2010. Biomass production and allocation in Jatropha curcas L. seedlings under different levels of drought stress. Biomass Bioenerg, 34(5): 667-676.
Albayrak, S. and Yüksel, O. 2009. Leaf area prediction model for sugar beet and fodder beet. Süleyman Demirel Üniversitesi, Fen Bilimleri Enstitüsü Dergisi, 13(1): 20-24.
Asner, G.P. Scurlock, J.M.O. Hicke, J.A. 2003. Global synthesis of leaf area index observations: implications for ecological and remote sensing studies. Glob Ecol Biogeogr, 12(3): 191-205.
Atkinson, P.M. and Tatnall, R.L. 1997. Neural networks in remote sensing. International Journal of Remote Sensing, 18: 699-709. Bakhshandeh, E. Kamkar, B. Tsialtas, J.T. 2011. Application of linear models for estimation of leaf area in soybean (Glycine max (L.) Merr]. Photosynthetica, 49(3): 405-416.
Cemek, B. Unlukara, A. Kurunc, A. 2011. Nondestructive leaf-area estimation and validation for green pepper (Capsicum annuum L.) grown under different stress conditions. Photosynthetica, 49(1): 98-106.
Douglas, M.B. Donald, W.G. 1998. Non-Linear Regression and Its Applications. John Wiley & Sons Inc. Canada.
Draper, N.R. Smith, H. 1998. Applied Regression Analysis. John Wiley and Sons, New York.
Karadavut, U. 2009. Non-Linear Models for growth curves of triticale plants under irrigation conditions. Turkish J. Field Crops, 14(2): 105-110.
Kırsehir Regional Meteorology Station, 2013. Climatic parameters.
Kiymaz, S. and Ertek, A. 2015. Yield and quality of sugar beet (Beta vulgaris L.) at different water and nitrogen levels under the climatic conditions of Kırsehir-Turkey. Agricultural Water Management, 156-165.
Květ, J. Marshall, J.K. 1971. Assessment of Leaf Area and Other Assimilating Plant Surfaces. – In: Šesták, Z., Čatský, J., Jarvis, P.G. (ed.). Plant Photosynthetic Production. Manual of Methods. pp. 517-555. Dr W. Junk Publ., The Hague.
Lemaire, S. Maupas, F. Cournède, P.H. De Reffye, P. 2008. A morphogenetic crop model for sugar-beet (Beta vulgaris L.). In International Symposium on Crop Modeling and Decision Support: ISCMDS 2008, April 19-22, Nanjing, China, 2008.
Moghaddam, P.A. Derafshi, M.H. Shayesteh, M. 2010. A new method in assessing sugar beet leaf nitrogen status through color image processing and artificial neural network. Journal of Food, Agriculture and Environment, 8(2): 485-489.
Peksen, E. 2007. Non-destructive leaf area estimation model for faba bean (Vicia faba L.) Sci. Hort, 113: 322-328.
Serdar, U. and Demirsoy, H. 2006. Non-destructive leaf area estimation in chestnut. – Sci. Hort., 108: 227-230.
Tsialtas, JT. and Maslaris, N. 2005. Leaf area estimation in a sugar beet cultivar by linear models. Photosynthetica, 43(3): 477-479.
Tsialtas, J.T. and Maslaris, N. 2007. Leaf shape and its relationship with Leaf Area Index in a sugar beet (Beta vulgaris L.) cultivar. Photosynthetica, 45(4): 527-532.
Tsialtas, J.T. and Maslaris, N. 2008. Leaf area prediction model for sugar beet (Beta vulgaris L.) cultivars. Photosynthetica, 46(2): 291-293.
Obike, M.O. and Azu, K.E. 2012. Phenotypic correlations among body weight, external and internal egg quality traits of pearl and black strains of guinea fowl in a humid tropical environment. Journal of Animal Science Advances, 10: 857-864.
Rathert, T.C. Uckardes, F. Narinc, D. Aksoy, T. 2011. Comparison of principal component regression with the least square method in prediction of internal egg quality characteristics in Japanese quails. Journal of Faculty of Veterinary Medicine Kafkas University, 17: 687-692.
Reddy, P.M. Reddy, V.R. Reddy, C.V. Rap, S.P. 1979. Egg weight, shape index and hatchability in khaki Campbell duck egg. Indian Journal Poultry Science, 14: 26-31.
Rosa, P.S. Guidoni, A.L. Lima, I.L. Bersch, F.X.R. 2002. Effect of incubation temperature on hatching results of broiler breeders’ eggs classified by weight and hen age. Brazilian Journal of Poultry Science, 31: 1011-1016.
Sarica, M. and Erensayin, C. 2014. Poultry Products. Poultry Science (EDs M. Turkoglu and M. Sarica), Bey Ofset, pp. 89-138. SPSS, 2013. SPSS Release 22.0 Statistical packet program, SPSS for Windows. SPSS Inc., Chicago, IL, USA.
Turkoglu, M. and Sarica, M. 2014. Breeder Management. Poultry Science (EDs M. Turkoglu and M Sarica), Bey Ofset, pp. 344-350. Wilson, H.R. 1991. Interrelationships of egg size, chick size, posthatching growth and hatchability. World's Poultry Science Journal, 47: 5-20.