The influence of agro- and meteorological factors on sunflower yield

Anatolii Kulyk, Valentyna Lisovska, Olha Melnyk, Nadiia Shchekan
Received: 07.11.2025 Revised: 02.03.2026 Accepted: 25.03.2026 Published: 06.04.2026
Retrieved from Vol. 29, No. 1, 2026 Pages: 66-78
Download article Read article

Abstract

Sunflower is one of the leading oilseed crops in Ukraine, and the stability of its yield is of important economic and food importance. In conditions of increasing climate variability, the need for quantitative analysis of the influence of agrotechnical and meteorological factors on the development of the yield is becoming more urgent. The purpose of the study was to quantitatively assess the role of agrotechnical and climatic factors in the development of sunflower yield using statistical analysis methods. The empirical basis of the study was data for 2007-2024, including sunflower yield indicators, levels of mineral and organic fertilisers, and meteorological characteristics (soil temperature in May, precipitation, air moisture saturation deficit, Selyaninov hydrothermal coefficient, wind speed, number of clear days during the growing season). The study used descriptive statistics, the Shapiro-Wilk test, Pearson and Spearman correlation analysis, and multivariate linear regression. The results of the study showed that the average yield level for the period was 25.65 q/ha with a standard deviation of 5.91 q/ha. The most stable and statistically significant effect on sunflower yield was the level of mineral fertiliser application, for which a moderately strong positive relationship was recorded (r=0.656). Among meteorological factors, the most noticeable positive relationship was found for wind speed (r=0.512). The multicollinearity test using the variance inflation coefficient confirmed the correctness of the model, since the values for most variables did not exceed 4, and the maximum indicator was 5.17 for mineral fertilisers. The analysis emphasised the key role of agrotechnical management, since the influence of factors such as Selyaninov hydrothermal coefficient (r=0.083) and moisture deficit (r=0.092) turned out to be weak within the paired analysis. The practical value of the results lies in the possibility of using the developed regression models to predict sunflower productivity and optimise mineral nutrition systems in order to minimise risks caused by adverse meteorological factors

Keywords

agrometeorological indicators; Selyaninov hydrothermal coefficient; multicollinearity; correlation analysis; linear regression; variance inflation factor

  1. Acir, N. (2025). Predicting soil fertility in semi-arid agroecosystems using interpretable machine learning models: A sustainable approach for data-sparse regions. Sustainability, 17(16), article number 7547. doi: 10.3390/su17167547.
  2. Amankulova, K., Farmonov, N., Mukhtorov, U., & Mucsi, L. (2023). Sunflower crop yield prediction by advanced statistical modeling using satellite-derived vegetation indices and crop phenology. Geocarto International, 38(1), article number 2197509. doi: 10.1080/10106049.2023.2197509.
  3. Anton, F.G., Joița-Păcureanu, M., Contescu, L., Cergan, M., Partal, E., & Pintilia, S. (2025). Sunflower production of some genotypes in years 2022, 2023 and 2024, in Romania. Scientific Papers. Series A. Agronomy, 68(1), 246-253.
  4. Baranskyi, D. (2024). Managing sunflower growth in the changing climate and fluctuating moisture levels of the Western forest-steppe. Bulletin of Lviv National Environmental University. Series Agronomy, 28, 57-66. doi: 10.31734/agronomy2024.28.057.
  5. Beteri, J., Lyimo, J.G., & Msinde, J.V. (2024). The influence of climatic and environmental variables on sunflower planting season suitability in Tanzania. Scientific Reports, 14, article number 3906. doi: 10.1038/s41598-023-49581-5.
  6. Chekhova, I.V. (2022). Peculiarities of oilseeds market functioning in Ukraine. Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS, 32, 154-161. doi: 10.36710/IOC-2022-32-15.
  7. Cvejić, S., Hrnjaković, O., Jocković, M., Kupusinac, A., Doroslovački, K., Gvozdenac, S., Jocić, S., & Miladinović, D. (2023). Oil yield prediction for sunflower hybrid selection using different machine learning algorithms. Scientific Reports, 13, article number 17611. doi: 10.1038/s41598-023-44999-3.
  8. Debaeke, P., Attia, F., Champolivier, L., Dejoux, J.F., Micheneau, A., Al Bitar, A., & Trépos, R. (2023). Forecasting sunflower grain yield using remote sensing data and statistical models. European Journal of Agronomy, 142, article number 126677. doi: 10.1016/j.eja.2022.126677.
  9. Furmanets, M., & Furmanets, Y. (2025). Productivity of sunflower under different tillage and fertilization systems in the Western Forest-Steppe of Ukraine. Agro-Business Today. Retrieved from https://agro-business.com.ua/agro/ahronomiia-sohodni/item/31616-produktyvnist-soniashnyku-za-riznykh-system-obrobitku-gruntu-i-udobrennia-v-zakhidnomu-lisostepu-ukrainy.html.
  10. Georgieva, V., Kazandjiev, V., Georgiev, S., Rashev, S., Valkova, D., Mihova, G., Valchev, D., & Dobreva, V. (2024). Agro-climatic conditions for growing of sunflower in different climatic area in Bulgaria. Scientific Papers. Series A. Agronomy, 67(2), 224-231.
  11. Gürkan, H. (2023). Evaluation of the impacts of climate change on sunflower with aquacrop model. Journal of Tekirdag Agricultural Faculty, 20(4), 933-947. doi: 10.33462/jotaf.1240401.
  12. Hnatiienko, V., & Hnatiienko, H. (2024). Integration of machine learning and deep learning methods for sunflower yield prediction. Management of Development of Complex Systems, 59, 225-234. doi: 10.32347/2412-9933.2024.59.225-234.
  13. Hu, Y., & Yu, J.‑y. (2016). Quantile‑quantile plot compared with stabilized probability plot in figure on the distribution of the test research. American Journal of Applied Mathematics, 4(2), 110-113. doi: 10.11648/j.ajam.20160402.17.
  14. Jabed, M.A., & Murad, M.A.A. (2024). Crop yield prediction in agriculture: A comprehensive review of machine learning and deep learning approaches, with insights for future research and sustainability. Heliyon, 10(24), article number e40836. doi: 10.1016/j.heliyon.2024.e40836.
  15. Joseph, C.O., Kambwily, K., & Emmanuel, S.M. (2025). Effects of planting window on grain yield and oil yield under rainfed sunflower (Helianthus annuus L.) in Kilwa District, Lindi, Tanzania. Discover Agriculture, 3, article number 8. doi: 10.1007/s44279-025-00155-1.
  16. Junk, J., Torres, A., El Jaroudi, M., & Eickermann, M. (2024). Impact of climate change on the phenology of winter oilseed rape (Brassica napus L.). Agriculture, 14(7), article number 1049. doi: 10.3390/agriculture14071049.
  17. Karan, R., Ramkumar, M.O., & Yokesh, M. (2024). Revolutionizing tamilnadu agriculture: AI-powered crop yield forecasting and disease prediction for oil seed crops. In 2024 Ist international conference on cognitive, green and ubiquitous computing (pp. 1-10). Piscataway: IEEE. doi: 10.1109/IC-CGU58078.2024.10530710.
  18. Majumder, S., & Mason, C.M. (2025). Sunflower yield modeling with explainable artificial intelligence: Historical weather impacts across half a century of American production. Agronomy Journal, 117(6), article number e70204. doi: 10.1002/agj2.70204.
  19. Mokgolo, M.J., Zerizghy, M.G., & Mzezewa, J. (2024). Sunflower growth and grain yield under different tillage systems and sources of organic manure on contrasting soil types in Limpopo Province of South Africa. Agronomy, 14(4), article number 857. doi: 10.3390/agronomy14040857.
  20. Nazir, A.A., Rubaiat, E., Saiful, I., & Al Sohan, M.F.A. (2025). Evaluating machine learning models for crop yield prediction. In 2025 international conference on quantum photonics, artificial intelligence, and networking (pp. 1-6). Piscataway: IEEE. doi: 10.1109/QPAIN66474.2025.11171630.
  21. O’Brien, R.M. (2007). A caution regarding rules of thumb for variance inflation factors. Quality & Quantity, 41, 673-690. doi: 10.1007/s11135-006-9018-6.
  22. Partal, E. (2022). Sunflower yield and quality under the influence of sowing date, plant population and the hybrid. Romanian Agricultural Research, 39, 463-470. doi: 10.59665/rar3944.
  23. Qiu, Z. (2022). An elastic net based algorithm for China agriculture GDP prediction. In 2022 international conference on economics, smart finance and contemporary trade (pp. 843-849). Paris: Atlantis Press. doi: 10.2991/978-94-6463-052-7_96.
  24. Seck, N.K.G., Ngom, A., Ngom, P., & Noba, K. (2025). Crop yield forecasting in Senegal: Application of machine learning methods. Discover Agriculture, 3(1), article number 192. doi: 10.1007/s44279-025-00381-7.
  25. Sectoral State Archive of Hydrometeorological Observation Materials of the State Emergency Service of Ukraine. (n.d.). Retrieved from https://cgo-sreznevskyi.kyiv.ua/uk/struktura-fondiv/21-hda-mhs.
  26. Shakalii, S.M., & Kulyk, Ye.I. (2025). Impact of weather and climatic factors on sunflower seed quality. In Current directions and challenges in crop production technologies: Proceedings of the 5th international scientific and practical internet conference (pp. 27-29). Poltava: Poltava State Agrarian University.
  27. Shapiro, S.S., & Wilk, M.B. (1965). An analysis of variance test for normality (complete samples). Biometrika, 52(3-4), 591-611. doi: 10.1093/biomet/52.3-4.591.
  28. Song, Z., Wang, P., Zhang, Z., Yang, S., & Ning, J. (2023). Recognition of sunflower growth period based on deep learning from UAV remote sensing images. Precision Agriculture, 24, 1417-1438. doi: 10.1007/s11119-023-09996-6.
  29. State Statistics Service of Ukraine. (n.d.). Main Department of Statistics in Vinnytsia Region. Retrieved from https://vn.ukrstat.gov.ua/index.php/statistical-information/.
  30. Sydiakina, O.V., & Hamajunova, V.V. (2023). Current state and prospects of sunflower seed production. Taurida Scientific Herald, 131, 196-204. doi: 10.32782/2226-0099.2023.131.25.
  31. Thavareesan, S., Sriranganesan, J., & Nishatharan, T. (2025). Exploring machine learning techniques for accurate crop yield prediction. Annals of Agricultural Science and Technology, 8(1), 1-7.
  32. Vasylkovska, K., Andriienko, O., Malakhovska, V., & Moroz, O. (2022). Analysis of changes in comfortable sunflower growing areas using the example of Ukraine. Helia, 45(77), 175-189. doi: 10.1515/helia-2022-0010.
  33. Zabel, F., Knüttel, M., & Poschlod, B. (2025). CropSuite v1.0 – a comprehensive open-source crop suitability model considering climate variability for climate impact assessment. Geoscientific Model Development, 18(4), 1067-1087. doi: 10.5194/gmd-18-1067-2025.
  34. Zalai, M., Bojtor, C., Nagy, J., Széles, A., Monoki, S., & Illés, Á. (2025). Challenges in precision sunflower cultivation: The impact of the agronomic environment on the quality of precision sowing techniques and yield parameters. AgriEngineering, 7(5), article number 145. doi: 10.3390/agriengineering7050145.
Kulyk, A., Lisovska, V., Melnyk, O., & Shchekan, N. (2026). The influence of agro- and meteorological factors on sunflower yield. Scientific Horizons, 29(1), 66-78. https://doi.org/10.48077/scihor1.2026.66