DATA PRE-PROCESSING METHOD FOR FORECASTING GRAIN YIELD IN A HARVEST PROGRAMMING SYSTEM
DOI:
https://doi.org/10.17721/AIT.2025.2.06Keywords:
data processing, Bayesian networks, agrometeorological data, data integration, machine learning, yield programming, scenarios.Abstract
The article is presented in the OnlineFirst format, which involves early posting of materials on the journal website before their final printing in paper form.
The article has passed the review procedure and has been accepted for publication.
The article is available for search and citation by its DOI, which remains unchanged. After the issue is printed in the printing house, a new citation can be made using information about the volume number and page number, using the same DOI reference.
Background. A method for processing meteorological indicators and agronomic data, including the results of field experiments, has been developed, intended for use in the crop programming system, in particular, for predictive modeling and development of scenarios of agrochemical measures in conditions of climate change. Its feature is that it allows integrating heterogeneous data obtained from various sources and creating sets of informative indicators that reflect the conditions of crop development, which provides a more complete representation of the state of agroecosystems and improves the quality of the obtained forecasts. The aim of the work is to develop a method for processing data in the crop programming system, which ensures the consideration of both time dependencies and the hierarchy of the data structure, adapted for use in the crop programming system.
Methods. The research used methods of analysis and synthesis, system analysis, expert evaluation, multi-criteria analysis, statistical, time series analysis, Bayesian approach, machine learning.
Results. The developed method provides the possibility of adaptive modeling of grain crop yields, taking into account the characteristics of a certain agroclimatic zone. This allowed us to take into account both time dependencies and to process the data structure “plant → plot → farm → region”. Lag relationships between the yield of the current year and the factors of the previous period were taken into account, which is especially important when using long-term agrometeorological observations, since it allows us to trace the impact of climate change on a certain territory.
Conclusions. The effectiveness of the developed method was tested on field experiment data. The developed mathematical models improved the quality of grain crop yield forecasts by almost 10%. The use of the method of intelligent data analysis made it possible to more accurately determine the impact of meteorological factors on plant development at different stages of the agrocenosis. The constructed crop yield scenarios provide an in-depth analysis of factors that influence plant development at different stages of vegetation, which improves the quality of forecasts for different options for the influence of controlled factors and uncontrolled conditions and, accordingly, increases yield and biologization of grain crop production processes. The developed method, models and scenarios are intended for integration into the yield programming system, but can also be used separately. Their use will create conditions for optimizing agricultural technologies, increasing the efficiency of grain production.
Downloads
References
Ashfaq, M., Khan, I., Afzal, R. F., Shah, D., Ali, S. & Tahir, M. (2025). Enhanced wheat yield prediction through integrated climate and satellite data using advanced AI techniques. Scientific Reports, 15, 18093. https://doi.org/10.1038/s41598-025-02700-w
Bidjuk, P. I., Terent’jev, O. M., Prosjankina-Zharova, T. I., & Efendijev, V. V. (2017). Prognostic modeling of nonlinear non-stationary processes in crop production using SAS Enterprise Miner tools. Scientific News of NTUU KPI, 1, 24–36 [in Ukrainian]. https://doi.org/10.20535/1810-0546.2017.1.87423
Bilyaeva, I.M. (2015) Scientific justification and practical use of agrometeorological methods for predicting the yield of field crops under irrigation conditions. Taurida Scientific Herald, 94, 8-15. . https://www.tnv-agro.ksauniv.ks.ua/archives/94_2015/4.pdf
Cho, W., Lambert, D. M., Brorsen, B. W., Maples, C. H., Fornah, A. & Raun, W. R. (2023). A Bayesian approach for analyzing crop yield response data with limited treatments. Agrosystems, Geosciences & Environment, 6, e20358. https://doi.org/10.1002/agg2.20358
Cooper, M., Voss-Fels, K. P., Messina, C. D., Tang T. & Hammer, G. L. (2021). Tackling G × E × M interactions to close on-farm yield-gaps: creating novel pathways for crop improvement by predicting contributions of genetics and management to crop productivity Theoretical and Applied Genetics, 134, 1625–1644. https://doi.org/10.1007/s00122-021-03812-3
Corbeels, M., Berre, D., Rusinamhodzi, L., & Lopez-Ridaura, S. (2018). Can we use crop modelling for identifying climate change adaptation options? Agricultural and Forest Meteorology, 256, 46–52. https://doi.org/10.1016/j.agrformet.2018.02.026
Jabed, M. A., Azmi Murad, M. 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, e40836. https://doi.org/10.1016/j.heliyon.2024.e40836
Jensen, F. V. (2001). Bayesian networks and decision graphs. Cham: Springer. https://doi.org/10.1007/978-1-4757-3502-4
Kocian, A., Massa, D., Cannazzaro, S., Incrocci, L., Di Lonardo, S., Milazzo, P., & Chessa, S. (2020). Dynamic Bayesian network for crop growth prediction in greenhouses. Computers and Electronics in Agriculture, 169, 105167. https://doi.org/10.1016/j.compag.2019.105167
Kontseba, S., Lishchuk, R., Skurtol, S., Rodashchuk, H., & Vasylchenko, I. (2021). Forecasting of agricultural production volumes using methods of data mining. Systemni doslidzhennia ta informatsiini tekhnolohii, 1, 87–97. [in Ukrainian]. https://doi.org/10.20535/SRIT.2308-8893.2021.1.07
Kussul, N., Drozd, S., & Yailymova, H. (2023). Forecast of yield of major crops in Ukraine in war conditions 2022 based on MODIS and Sentinel-2 satellite data. In 11th International Conference on Advanced Information and Communication Technology (ICAIIT) (pp. 89–95). IEEE. http://dx.doi.org/10.25673/101923
Kussul, N., Shelestov, A., Yailymov, B., Yailymova, H., Lemoine, G., Deininger, K. (2025). Assessment of war-induced agricultural land use changes in Ukraine using machine learning applied to Sentinel satellite data. International Journal of Applied Earth Observation and Geoinformation. 140. 104551, https://doi.org/10.1016/j.jag.2025.104551
Mahmood, T., Ahmed, T., & Trethowan, R. (2022). Genotype x Environment x Management (GEM) reciprocity and crop productivity. Frontiers in Agronomy, 4, 800365. https://doi.org/10.3389/fagro.2022.800365
Rivière, P., Dawson, J. C., Goldringer, I., & David, O. (2015). Hierarchical Bayesian modeling for flexible experiments in decentralized participatory plant breeding. Crop Science, 55, 1053–1067. https://doi.org/10.2135/cropsci2014.07.0497
Salakpi, E. E., Hurley, P. D., Muthoka, J. M., Bowell, A., Oliver, S., & Rowhani, P. (2022). A dynamic hierarchical Bayesian approach for forecasting vegetation condition. Natural Hazards and Earth System Sciences, 22, 2725–2749. https://doi.org/10.5194/nhess-22-2725-2022
Shahhosseini, M., Hu, G., Huber, I., & Archontoulis, S. V. (2021). Coupling machine learning and crop modeling improves crop yield prediction in the US Corn Belt. Scientific Reports, 11, 1606. https://doi.org/10.1038/s41598-020-80820-1
Spirtes, P., Glymour, C., & Scheines, R. (1993). Causation, Prediction and Search. Cham: Springer. https://doi.org/10.1007/978-1-4612-2748-9
Trofymchuk, O., Bidiuk, P., Prosyankina-Zharova, T., Terentiev, O. (2019). Decision support systems for modelling, forecasting and risk estimation. Beau Bassin: LAP Lambert Academic Publishing.
Valleggi, L., Scutari, M., & Stefanini, F. M. (2023). Learning Bayesian networks with heterogeneous agronomic data sets via mixed-effect models and hierarchical clustering. arXiv. https://doi.org/10.48550/arXiv.2308.06399
Wang, A. X., Tran, C., Desai, N., Lobell, D., & Ermon, S. (2018). Deep Transfer Learning for Crop Yield Prediction with Remote Sensing Data. In Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS ’18) (Article 50, pp. 1–5). Association for Computing Machinery. https://doi.org/10.1145/3209811.3212707
Yan, Y., Wang, Y., Li, J., Zhang, J., & Mo, X. (2025). Crop yield time-series data prediction based on multiple hybrid machine learning models. arXiv. https://doi.org/10.48550/arXiv.2502.10405
Zhao, C., Liu, B., Piao, S., Wang, X., Lobell, D. B., Huang, Y., Huang, M., Yao, Y., Bassu, S., Ciais, P., Durand, J.-L., Elliott, J., Ewert, F., Janssens, I. A., Li, T., Lin, E., Liu, Q., Martre, P., Müller, C., Peng, S., Peñuelas, J., Ruane, A. C., Wallach, D., Wang, T., Wu, D., Liu, Z., Zhu, Y., Zhu, Z., & Asseng, S. (2017). Temperature increase reduces global yields of major crops in four independent estimates. Proceedings of the National Academy of Sciences, 114(35), 9326–9331. https://doi.org/10.1073/pnas.1701762114
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Олексій ШОЛОХОВ, канд.фіз.-мат.наук, Денис ПРОСЯНКІН, асп. (Автор)
This work is licensed under a Creative Commons Attribution 4.0 International License.
