Identification of buckwheat varieties Fagopyrum esculentum Moench by morphological characters by applying the nearest neighbors algorithm




variety, feature distinctness, model, buckwheat, statistical methods


Purpose. Evaluate buckwheat Fagopyrum esculentum Moench varieties by morphological characteristics by using the nearest neighbors algorithm and identify groups of similar varieties by plant varieties clustering procedure.

Methods. Analytical, mathematical, statistical. As input information for statistical processing, the results of the exa­mination for distinctness, uniformity and stability (DUS) from the database of the automated information system of the Ukrainian Institute for the Examination of Plant Varieties were used. The simulation was performed using Nearest Neighbors algorithm, which belong to Machine Learning method. Data processing was carried out by using trial version of the statistical package IBM SPSS Statistics “Statistical Package for the Social Sciences”. The follo­wing types of variables were used as model parameters: target (optional) variable is “Plant: growth type”, focal case identifier is “Plant: ploidy”, case name is Varieties Name, feature variables are “Cotyledon: anthocyanin coloration”, “Stem: anthocyanin coloration”, “Inflorescence: anthocyanin coloration of bud”, “Time of beginning flowering”, “Plant: height”, “Leaf blade: shape of base”, “Leaf blade: intensity of green color”, “Flower: size”, “Flower: color of petals”, “Flower: length of pedicel”, “Plant: total number of flower clusters”, “Stem: length”, “Stem: number of nodes”, “Stem: diameter”, “Time of maturity”, “Seed: length”, “Seed: shape”, “Seed: skin color”, “Seed: 1000 seed weight”. This model contains 25 buckwheat varieties, included in the State Register of plant varieties suitable for distribution in Ukraine in 2020. These varieties are of foreign and domestic origin.

Results. The model of similar buckwheat varieties was a result of computer modeling. This model was based on seventeen morphological features, selected using frequency analysis of buckwheat morphological features. The generated model contained 17 training objects (varieties) and nine control objects (varieties). 22 groups of similar varieties of common buckwheat were identified.

Conclusion. The most similar groups of varieties are the following: first – ‘Krupnozelena’, ‘Dykul’, ‘Deviatka’ that ‘Yuvileina 100’; second – ‘Ruta’, ‘Malwa ’,‘Nadiina’ and ‘Volodar’; third – ‘Kseniia’, ‘Simka’, ‘Selianochka’ and ‘Malva’.

Author Biographies

Н. С. Орленко, Ukrainian Institute for Plant Variety Examination

Orlenko, N. S.

С. М. Гринів, Ukrainian Institute for Plant Variety Examination

Hryniv, S. М.

С. П. Лікар, Ukrainian Institute for Plant Variety Examination

Likar, S. P.

М. С. Юшкевич, Ukrainian Institute for Plant Variety Examination

Yushkevich, M. S.


Dragavtsev, V. A. (Ed). (2006). Genofond i selektsiya krupyanykh kul’tur. Grechikha [The Gene bank and breeding of groat crops. Buckwheat]. St. Petersburg: VIR. [in Russian]

Kalinova, J., & Vrchotova, N.(2009). Level of Catechin, Myricetin, Quercetin and Isoquercitrin in Buckwheat (Fagopyrum esculentum Moench), Changes of Their Levels during Vegetation and Their Effect on The Growth of Selected Weeds. J. Agr. Food Chem., 57(7), 2719–2725. doi: 10.1021/jf803633f

Minami, M., Ujihara, A., & Campbell, C. (1999). Morphology and inheritance of dwarfism in common buckwheat line, G410, and its stability under different growth conditions. Breed. Sci., 49(1), 27–32. doi: 10.1270/jsbbs.49.27

Tkachyk, S. O., Prysiazhniuk, O. I., & Leshchuk, N. V. (2016). Metodyka provedennia kvalifikatsiinoi ekspertyzy sortiv roslyn na prydatnist do poshyrennia v Ukraini. Zahalna chastyna [Methodology of conducting qualification examination of plant varieties for suitability for distribution in Ukraine. General part]. (2nd ed., rev. and enl.). Vinnytsia: FOP Korzun D. Yu. [in Ukrainian]

Soroka, V. I., Leshchuk, N. V., & Andriushchenko, A. V. (2011). Atlas morfolohichnykh oznak sortiv roslyn hrupy zernovykh (naochne dopovnennia do Metodyky provedennia inspektuvannia nasinnytskykh posiviv zernovykh vydiv) [Atlas of morphological characteristics of plant varieties of cereals (visual addition to the Methodology of inspection of seed crops of cereals)]. Kyiv: Feniks. [in Ukrainian]

Tkachyk, S. O. (2016). Methods of examination of varieties of edible buckwheat (Fagopyrum esculentum Moench) for distinctness, uniformity and stability. In Metodyka provedennia ekspertyzy sortiv roslyn hrupy zernobobovykh ta krupianykh na vidminnist, odnoridnist i stabilnist [Methods of examination of plant varieties of legumes and cereals for distinctness, uniformity and stability]. (2nd ed., rev. and enl.). Vinnytsia: Korzun D. Yu. Retrieved from [in Ukrainian]

UPOV. (2012). Test Guidelines for the conduct of tests for distinctness, uniformity and stability of Buckwheat (Fagopyrum esculentum Moench) (TG /278/1). Geneva: N.p.

Orlenko, N. S., Leshchuk, N. V., Symonenko. N. V., Tahantsova, M. M., & Stadnichenko, O. A. (2019). Peculiarities of using machine learning tools during identification of similar plant varieties (Lactuca sativa L. var. capitata as example). Vìsnik PDAA [Bulletin of Poltava State Agrarian Academy], 4, 233–240. doi: 10.31210/visnyk2019.04.30 [in Ukrainian]

Orlenko, N. S., Mazhuha, K. M., Dushar, M. B., & Maslechkin, V. V. (2019). Comparative analysis of clustering methods sui­table for plant varieties morphological characteristics data processing. Vìsnik PDAA [Bulletin of Poltava State Agrarian Academy], 2, 261–269. doi: 10.31210/visnyk2019.02.35 [in Ukrainian]

Lantz, B. (2013). Machine Learning with R. Learn how to use R to apply powerful machine learning methods and gain an insight into real-world applications. Birmingham: Packt Publishing Ltd.

Byuyul, A., & Tsefel, P. (2002). SPSS: iskusstvo obrabotki. Analiz sta tisticheskikh dannykh i vosstanovlenie skrytykh zakonomernostey [SPSS: Arts of processing. Analysis of statistical data and restoration of hidden patterns]. St. Petersburg: DiaSoftYuP. [in Russian]

Leskovets, Yu., Radzharaman, Yu., & Ulman, D. (2016). Analiz bol’shikh naborov dannykh [Analysis of large data sets]. Moscow: DMK. [in Russian]

Nasledov, A. D. (2013). IMB SPSS Statistics 20 i AMOS: professional’nyy statisticheskiy analiz dannykh [IMB SPSS Statistics 20 and AMOS: professional statistical data analysis]. St. Petersburg: Piter. [in Russian]

Derzhavnyi reiestr sortiv roslyn, prydatnykh dlia poshyrennia v Ukraini na 2020 rik [State register of plant varieties suitable for dissemination in Ukraine in 2020]. (2020). Kyiv: N.p. [in Ukrainian]

Potapov, К. О., Kadyrova, L. R., & Mukhametshina, R. R. (2017). Embryological features and seed productivity of tartary buckwheat. J. Fundam. Appl. Sci., 9(15), 1462–1471. doi: 10.4314/jfas.v9i1s.796

Tyshchenko, V. N. (2004). Efficiency of using a new selection index in winter wheat breeding. Fakt. Eksp. Evol. Org. [Factors in Experimental Evolution of Organisms], 2, 266–270. [in Russian]

Compton, M. E. (1994). Statistical methods suitable for the analysis of plant tissue culture data. Plant Cell Tiss. Organ Cult., 37(3), 217–242. doi: 10.1007/BF00042336

Marmanis, Kh., & Babenko, D. (2011). Algoritmy intellektual’nogo Interneta. Peredovye metodiki sbora, analiza i obrabotki dannykh [Algorithms of the intellectual Internet. Advanced techniques for data collecting, analyzing and processing]. Moscow: Simvol. [in Russian]

Tyshchenko, V. M. (2005). Cluster analysis as a method of individual selection of high-yield winter wheat plants in F2. Selekciâ i nasìnnictvo [Plant Breeding and Seed Production], 89, 125–137. [in Ukrainian]

Tishchenko, V. N., Chekalin, N. M., & Zyukov, M. E. (2004). Using cluster analysis to identify and select highly productive winter wheat genotypes in the early stages of selection. Fakt. Eksp. Evol. Org. [Factors in Experimental Evolution of Organisms], 2, 270–278. [in Russian]

How to Cite

Орленко, Н. С., Гринів, С. М., Лікар, С. П., & Юшкевич, М. С. (2020). Identification of buckwheat varieties Fagopyrum esculentum Moench by morphological characters by applying the nearest neighbors algorithm. Plant Varieties Studying and Protection, 16(2), 137–143.




Most read articles by the same author(s)

1 2 > >>