Loading...

Research on Crops

Cluster analysis for assessing climatic factors in the cultivation of two crops of early potato varieties in the Russian Federation


DOI: 10.31830/2348-7542.2026.ROC-1244    | Article Id: ROC-1244 | Page : 117-128
Citation :- Cluster analysis for assessing climatic factors in the cultivation of two crops of early potato varieties in the Russian Federation. Res. Crop. 27: 117-128
GASPARYAN SH, LEVSHIN A AND IVASHOVA gas_shag@rgau-msha.ru
Address : Russian State Agrarian University - Moscow, Timiryazev Agricultural Academy, Moscow, Russia
Submitted Date : 29-09-2025
Accepted Date : 13-02-2026
Online Published:

Abstract

A feature of agricultural production in the Russian Federation is that over 70% of its territory lies within the risky farming zone. Climatic uncertainties, particularly temperature and precipitation variability, threaten stable crop yields. Existing statistical methods remain insufficient, necessitating advanced approaches like cluster analysis for reliable climate–yield assessments. Based on this the present investigation was conducted during 2017 to 2023  at the _ the Russian State Agrarian University, All-Russian Institute and of Agrochemistry named after D. Pryanishnikov_ to  application of cluster analysis  for the selection of varieties when cultivating varieties of 2 crops of Potato in the changing climate The methodology for applying Data Mining technologies using the Loginom 7.2 platform was developed and tested on six years of potato field data. Climatic factors (decadal temperature and precipitation) were clustered using the k-means algorithm after preprocessing. Results, visualised through tables and diagrams, enabled detailed interpretation of climatic–yield relationships. Results revealed that three clusters provided the most balanced distribution in the k-means analysis. In the first planting, clusters accounted for 24%, 39% and 37% of observations, while in the second planting, the distribution was 31%, 25% and 44%. Climatic factors such as decadal temperature and rainfall, along with yield data of 11 early potato varieties over six years, were analysed. Yields were higher in the first planting (510 g/bush) compared to the second (468 g/bush). The clusters represented favourable, unfavourable and intermediate climatic conditions influencing crop productivity. It can be concluded that clustering climate data into three groups helps assess weather, predict yields, plan necessary farming interventions, and guide the choice of crop varieties.

Keywords

Climate characteristics cluster probabilities early potato k-means clustering Loginom analytical platform

References

Amini, A. and Wah, T. Y. (2012). On density-based clustering algorithms over evolving data streams: a summarization paradigm. JCST 29: 116-41.
Elansky, S., Smirnov, A., Dyakov, Y., Dolgova, A., Filippov, A., Kozlovsky, B., Kozlovskaya, I., Russo, P., Smart, C. and Fry, W. (2001). Genotypic analysis of Russian isolates of Phytophthora infestans from the Moscow region, Siberia and Far East. J. Phytopathol. 149: 605–11. doi:10.1046/j.1439-0434.2001.00642.x.
Evers, D., Bonnechere, S., Hoffmann, L. and Hausman, J. F. (2007). Physiological aspects of abiotic stress response in potato. Belg. J. Bot. 140: 124–38.
Gasparyan, I. N., Levshin, A. G., Ivashova, O. N., Deniskina, N. F. and Gasparyan, S. V. (2024). Features of the choice of potato (Solanum tuberosum) varieties when growing two harvests in the temperate zone of Russia. Braz. J. Biol. 84: 1–10. doi:10.1590/1519-6984. 278272.
Gasparyan, I., Levshin, A., Ivashova, O., Dyikanova, M. and Deniskina, N. (2014). Agrotechnical requirements for the cultivation of potatoes in a two-crop culture. Res. Crop. 22: 1–4.
Gentle, J. E., Kaufman, L. and Rousseeuw, P. J. (1991). Finding groups in data: an introduction to cluster analysis. Biometrics 47: 778–88. doi:10.2307/2532178.
George, T. S., Taylor, M. A., Dodd, I. C. and White, P. J. (2017). Climate change and consequences for potato production: a review of tolerance to emerging abiotic stress. Potato Res. 60: 239–68.
Güngör, H., Türkoğlu, A., Çakır, M. F., Dumlupınar, Z., Piekutowska, M., Wojciechowski, T. and Niedbała, G. (2024). GT biplot and cluster analysis of barley (Hordeum vulgare L.) germplasm from various geographical regions based on agro-morphological traits. Agronomy 14: doi:10.3390/agronomy14102188.
He, Z. and Yu, C. (2018). Clustering stability-based evolutionary k-means. Soft Comput. 23: 305–21.
Kaufman, L. (1987). Clustering by means of medoids. Rep. Fac. Math. Inform., Katholieke Univ., Leuven, Belgium.
Malik, R., Sharma, H., Verma, A., Kundu, S., Sharma, I. and Chatrath, R. (2024). Hierarchical clustering of Indian wheat varieties using morphological diversity assessment. Indian J. Agric. Res. 47: 116–23.
Ondar, A. and Levshin, A. (2020). Transport provision for increasing mobility of rural doctor in typical districts of the Republic of Tuva. Eng. Rural Dev. 19: 1890–96.
Peeters, J. P. and Martinelli, J. A. (1989). Hierarchical cluster analysis as a tool to manage variation in germplasm collections. Theor. Appl. Genet. 78: 42–48.
Wan, L., Ng, W. K., Dang, X. H., Yu, P. S. and Zhang, K. (2009). Density-based clustering of data streams at multiple resolutions. ACM Trans. Knowl. Discov. Data 3: 1–28.
 
 
 
 

Global Footprints