Climate predictors of crop yields in the Polissia and Forest-Steppe regions of Ukraine

Yurii Nykytiuk, Oksana Kravchenko
Received: 05.06.2025 Revised: 09.10.2025 Accepted: 29.10.2025
Retrieved from Vol. 28, No. 11, 2025 Pages: 20-27
Download article Read article

Abstract

The purpose of the study was to identify the key climatic predictors that shaped the variability of winter wheat and maize yields under the agroclimatic conditions of the Polissia and Forest-Steppe regions. The methodology was based on the use of long-term meteorological data combined with statistical and machine-learning modelling algorithms, among which multiple linear regression and the Random Forest method were applied for a comparative assessment of predictive performance. A variable importance mechanism was also implemented in order to determine the most informative climatic indicators. The study analysed the influence of temperature extremes, total atmospheric precipitation patterns, and hydrothermal indices during the key phenological stages of crop development. It was established that April-June conditions played a dominant role for winter wheat, whereas July-August thermal and moisture-related parameters were most influential for maize. It was identified that integral indicators, particularly the hydrothermal coefficient, provided considerably higher predictive power compared to individual temperature- or precipitation-based metrics. The presence of threshold crop responses to extreme climatic factors was confirmed, which resulted in regional differences in sensitivity to heatwaves and droughts. The analysis demonstrated that the Random Forest algorithm delivered the highest predictive accuracy, explaining up to 81% of maize yield variability in the ForestSteppe region and up to 74% for winter wheat. The practical value of the study lay in the potential use of the obtained results by analytical institutions, agrometeorological services, and agricultural producers for planning sowing areas, assessing seasonal yield risks, and shaping adaptation strategies under climate-change conditions

Keywords

agroclimatic indices; temperature extremes; hydrothermal regime; productivity variability; machine modelling; Random Forest; climatic risks; phenological stressors

  1. Abbass, K., Qasim, M.Z., Song, H., Murshed, M., Mahmood, H., & Younis, I. (2022). A review of the global climate change impacts, adaptation, and sustainable mitigation measures. Environmental Science and Pollution Research, 29, 42539-42559. doi: 10.1007/s11356-022-18847-3.
  2. Baranovskyi, M.O., & Baranovska, O.V. (2023). Features of assessing the impact of climatic factors on agricultural crop yields: Case of Chernihiv region. Ukrainian Journal of Natural Sciences, 6, 34-43. doi: 10.32782/ naturaljournal.6.2023.4.
  3. Bihun, V.S. (2024). The impact of climate change on agriculture: Adaptive strategies for increasing crop resilience. Dumka Molodoho Vchenoho, 35, 179-188. doi: 10.37128/2707-5826-2024-4-15.
  4. Brannigan, N., Mullan, D., Vandaele, K., Graham, C., McKinley, J., & Meneely, J. (2022). Modelling soil erosion by water under future climate change: Addressing methodological gaps. Catena, 216(B), article number 106403. doi: 10.1016/j.catena.2022.106403.
  5. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. doi: 10.1023/A:1010933404324.
  6. Climate Change and Land. (n.d.). Retrieved from https://www.ipcc.ch/srccl/.
  7. Evans, L.T. (1993). Crop evolution, adaptation and yield. Cambridge University Press.
  8. Guntukula, R. (2020). Assessing the impact of climate change on Indian agriculture: Evidence from major crop yields. Journal of Public Affairs, 20(1), article number e2040. doi: 10.1002/pa.2040.
  9. Gurkan, H., Ozgen, Y., Bayraktar, N., Bulut, H., & Yildiz, M. (2020). Possible impacts of climate change on sunflower yield in Turkey. IntechOpen. doi: 10.5772/intechopen.91062.
  10. Hansen, J.E., et al. (2023). Global warming in the pipeline. Oxford Open Climate Change, 3(1), article number kgad008. doi: 10.1093/oxfclm/kgad008.
  11. Heil, K., Lehner, A., & Schmidhalter, U. (2020). Influence of climate conditions on the temporal development of wheat yields in a long-term experiment in an area with pleistocene loess. Climate, 8(9), article number 100. doi: 10.3390/cli8090100.
  12. Hersbach, H., et al. (2020). The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146(730), 1999-2049. doi: 10.1002/qj.3803.
  13. Hnatiienko, V.H., Hnatiienko, H.M., Zozulia, O.L., & Snytyuk, V.Y. (2024). Method of forecasting yield of agricultural crops using multifactor analysis and neural networks. Scientific Bulletin of Uzhhorod University. Series of Mathematics and Informatics, 44(1), 93-105. doi: 10.24144/2616-7700.2024.44(1).93-105.
  14. Konduri, V.S., Vandal, T.J., Ganguly, S., & Ganguly, A.R. (2020). Data science for weather impacts on crop yield. Frontiers in Sustainable Food Systems, 4, article number 52. doi: 10.3389/fsufs.2020.00052.
  15. Kryvokhyzha, Ye.M., Matviishyn, A.I., & Bryn, V.T. (2024). The impact of climate change on the yield of the main agricultural crops in Ukraine. Podilian Bulletin: Agriculture, Engineering, Economics, 44, 3-5. doi: 10.37406/27069052-2024-3.5.
  16. Kussul, N., Shelestov, A., Yailymov, B., Yailymova, H., Lavreniuk, M., & Shumilo, L. (2020). Crop monitoring technology based on time series of satellite imagery. In Proceedings of the 2020 IEEE 11th International conference on dependable systems, services and technologies (DESSERT) (pp. 346-350). IEEE. doi: 10.1109/ DESSERT50317.2020.9125008.
  17. Moldavan, L., Pimenowa, O., Wasilewski, M., & Wasilewska, N. (2023). Sustainable development of agriculture of Ukraine in the context of climate change. Sustainability, 15(13), article number 10517. doi: 10.3390/ su151310517.
  18. Muñoz-Sabater, J., et al. (2021). ERA5-Land: A state-of-the-art global reanalysis dataset for land applications. Earth System Science Data, 13(9), 4349-4383. doi: 10.5194/essd-13-4349-2021.
  19. Pepeliaev, V.A., Golodnikov, O.M., & Golodnikova, N.O. (2023). Modeling the impact of climate change on the productivity of agricultural crops. Cybernetics & Systems Analysis, 59(6), 96-104.
  20. Romashchenko, M., Husyev, Y., Shatkovskyi, A., Saidak, R., Yatsyuk, M., Shevchenko, A., & Matiash, T. (2020). Impact of climate change on water resources and agricultural production. Land Reclamation and Water Management, 1, 5-22. doi: 10.31073/mivg202001-235.
  21. Shevchenko, O. (2023). The impact of climate change on agricultural land use in Ukraine. Agricultural Sciences, 4, 108-114. doi: 10.33730/2310-4678.4.2023.292725.
  22. State Statistics Service of Ukraine. (2024). Methodological provisions of the state statistical observation “Areas, gross output and yield of agricultural crops”. Kyiv: State Statistics Service of Ukraine.
  23. Telo da Gama, J. (2023). The role of soils in sustainability, climate change, and ecosystem services: Challenges and opportunities. Ecologies, 4(3), 552-567. doi: 10.3390/ecologies4030036.
  24. van Klompenburg, T., Kassahun, A., & Catal, C. (2020). Crop yield prediction using machine learning: A systematic literature review. Computers and Electronics in Agriculture, 177, article number 105709. doi: 10.1016/j. compag.2020.105709.
  25. Yang, B., Wu, S., & Yan, Z. (2022). Effects of climate change on corn yields: Spatiotemporal evidence from geographically and temporally weighted regression model. ISPRS International Journal of Geo-Information, 11(8), article number 433. doi: 10.3390/ijgi11080433.
  26. Yemelyanov, M.O., Shelestov, A.Yu., Yailymova, H.O., & Shumilo, L.L. (2022). Impact of climate change on the area of major crops. Space Science & Technology, 28(2), 30-38. doi: 10.15407/knit2022.02.030.
  27. Zhygailo, О.L., Volvach, O.V., Tolmachova, А.V., & Kostiukievych, T.K. (2021). The influence of climate change on sunflower yield in the Northern Steppe of Ukraine: Analysis and forecast. Scientific Progress & Innovations, 1, 180-186. doi: 10.31210/visnyk2021.01.22.
Nykytiuk, Yu., & Kravchenko, O. (2025). Climate predictors of crop yields in the Polissia and Forest-Steppe regions of Ukraine. Scientific Horizons, 28(11), 20-27. https://doi.org/10.48077/scihor11.2025.20