Artificial intelligence

Abstract: Grain production is the backbone of Ukraine's agricultural sector, playing a key role in ensuring food security, building export potential and developing agricultural land. Thanks to favourable natural and climatic conditions and fertile soils, Ukraine has traditionally been one of the world's leading grain producers and exporters. However, this sector of the economy remains highly risky due to significant fluctuations in crop yields and purchase prices. This study aims to explore different approaches to assessing the risk of grain production associated with interannual yield fluctuations. Wheat was chosen as the crop under study. Given the significant increase in wheat yields in recent years, the deviation of yields from a linear trend was used for statistical analysis rather than yield values. Two approaches to risk assessment have been developed: a comparative approach, which allows comparing the degree of risk of grain production in two regions, and a quantitative approach, which allows estimating the probability of fixed grain losses in a given region. These approaches can be used as an analytical tool for planning agricultural production, especially in the face of growing climate risks. The results of the study are of practical importance for agricultural managers, economists and government agencies interested in increasing the stability and predictability of grain production. The proposed approaches to quantitative risk assessment allow not only to determine the degree of possible losses, but also to formulate effective strategies to reduce the negative impact of adverse factors.

Keywords: grain production, wheat yield, agricultural risk, quantile approach, risk assessment

References:

1. Derzhavna sluzhba statystyky Ukrayiny. [Online]. Available: https://www.ukrstat.gov.ua/.
2. D. Muller, A. Jungandreas, F. Koch, F. Shirhorn. (2016) The impact of climate change on wheat production in Ukraine. Report on agricultural policy (APD).
3. Halyas A, Havrylyuk V. ta in. (2008) Metody minimizaciyi ahrarnyx ryzykiv ta pidvyshhennya efektyvnosti zernovyrobnyctva. Kanadsko-ukrayinskyj zernovyj proekt.
4. Hrycyuk P.M. (2009) Dynamika vrozhajnosti zernovyx: prohnozy i ryzyky. Ekonomika Ukrayiny, с. 42-52.
5. Yevtushenko H.V., Tymkiv N.Ya., Sheshenya A.A. (2016) Osoblyvosti upravlinnya ryzykamy v ahrarnomu sektori ekonomiky. Naukovyj visnyk Mizhnarodnoho humanitarnoho universytetu: Ekonomika i menedzhment, 17, с. 49-52.
6. Hrycyuk P.M., Havrylyuk M.S. (2024) Identyfikaciya zakonu rozpodilu zalyshkiv vrozhajnosti silskohospodarskyx kultur. Komp’yuterne modelyuvannya ta prohramne zabezpechennya informacijnyx system i texnolohij (KMPZ_2024). IV mizhnarodna naukovo-praktychna konferenciya, Lviv-Chernivci, с. 76-80.
7. P. Feng, B. Wang, D.L. Liu, C. Waters, D. Xiao, L. Shi, and Q. Yu. (2020) Dynamic wheat yield forecasts are improved by a hybrid approach using a biophysical model and machine learning technique. Agricultural and Forest Meteorology, pp. 285-286. https://doi.org/10.1016/j.agrformet.2020.107922.
8. D. Elavarasan, D.R. Vincent, V. Sharma, A.Y. Zomaya, and K. Srinivasan. (2018) Forecasting yield by integrating agrarian factors and machine learning models: a survey, Computers and Electronics in Agriculture, Vol. 155, pp. 257-282. https://doi.org/10.1016/j.compag.2018.10.024.
9. S. Veenadhari, B. Misra, and C. Singh. (2014) Machine learning approach for forecasting crop yield based on climatic parameters, 2014 International Conference on Computer Communication and Informatics. IEEE, pp. 1-5. https://doi.org/10.1109/ICCCI.2014.6921718.
10. M. Kuradusenge, E. Hitimana, D. Hanyurwimfura, P. Rukundo, K. Mtonga, A. Mukasine, C. Uwitonze, J. Ngabonziza, and A. Uwamahoro. (2023) Crop Yield Prediction Using Machine Learning Models: Case of Irish Potato and Maize. Agriculture, 13(1). https://doi.org/10.3390/agriculture13010225.
11. P.B. Gibson, W.E. Chapman, A. Altinok, L.D. Monache, M.J. DeFlorio, and D.E. Waliser. (2021) Training machine learning models on climate model output yields skillful interpretable seasonal precipitation forecasts. Commun Earth Environ 2, 159. https://doi.org/10.1038/s43247-021-00225-4.
12. V.S. Konduri, T.J. Vandal, S. Ganguly, and A.R. Ganguly. (2020) Data science for weather impacts on crop yield. Frontiers in Sustainable Food Systems, Vol. 4, pp. 1-11. [Online]. Available: https://doi.org/10.3389/fsufs.2020.00052.
13. Petro Hrytsiuk, Maksym Havryliuk. (2025) Modeling of the nonlinear impact of climatic factors on wheat yield using machine learning techniques. In book: Information and Communication Technologies in Education, Research, and Industrial Applications. pp 20-35. [Online]. Available: https://doi.org/10.15407/jai2025.01.121.
14. Petro Hrytsiuk, Tetiana Babych, Olena Hladka, Maryna Nehrey (2024) Modeling of wheat yield in the steppe region of Ukraine using machine learning techniques. CEUR Workshop Proceedings. Proceedings of the 12-th International Conference "Information Control Systems & Technologies" (ICST 2024), Odesa, Ukraine, September 23-25, Vol. 3790, pp. 409-421. [Online]. Available: https://ceur-ws.org/Vol-3790/paper36.pdf.
15. Vitlinskyj V.V., Velykoivanenko H.I. (2004) Ryzykolohiya v ekonomici ta pidpryyemnyctvi: monohrafiya. K.: KNEU, 480 с.
16. Greenwood, P.E.; Nikulin, M.S. (1996). A guide to chi-squared testing. New York: Wiley.
17. Hall, Robert E.; Lilien, David M.; et al. (1995). EViews User Guide, p. 141.
18. Kozubowski, Tomasz J.; Podgorski, Krzysztof (2000). A Multivariate and Asymmetric Generalization of Laplace Distribution. Computational Statistics, Vol. 15(4), pp. 531-540. https://doi.org/10.1007/PL00022717.
19. Petro Hrytsiuk, Tetiana Babych. (2020) The cryptocurrencies risk measure based on the Laplace distribution. Machine Learning for Prediction of Emergent Economy Dynamics 2020. International Conference on Monitoring, Modeling & Management of Emergent Economy, Odesa, Ukraine, January 2022, pp. 261-276.
20. McKinney, W. (2018) Python for Data Analysis. O’Reilly Media.
21. Dowd, Kevin (2005). Measuring Market Risk. John Wiley & Sons.
22. Uryasev, S., (2000). Conditional Value-at-Risk: Optimization Algorithms and Applications. Financial Engineering News, Vol. 14, pp. 1-5.