MACHINE LEARNING-BASED CROP YIELD PREDICTION USING METEOROLOGICAL DATA

Authors:Pochemin Nikita M., Morkovkin Gennady G.

631.559.004
Theme: Modern problems of land reclamation and water industrial complex and ways to solve them
Views: 248

Annotation

Purpose: to develop a scientifically based methodology for grain crop yields forecasting by integrating high-frequency monitoring data with advanced machine learning methods for subsequent optimization of irrigation regimes.

Materials and methods. The study was conducted on the data array obtained from a network of 38 automatic weather stations located in the Altai Territory and functioning during the 2024 growing season. Hourly data on 29 meteorological indicators were collected and processed. To build predictive models, a set of ensemble algorithms including Random Forest, Gradient Boosting, and XGBoost, in comparison with classical linear models was used. SHAP analysis (SHapley Additive exPlanations) was used to interpret the results and identify the significance of predictors.

Results. It was stated that Random Forest model demonstrated the best predictive ability (R² = 0.012, RMSE = 14.10 c/ha). SHAP analysis revealed a nonlinear influence of meteorological factors. The key yield predictor is the maximum air temperature in July. A threshold effect was determined: when the maximum temperature in July (+34 °C) was exceeded, yield decreased statistically significantly. The second most significant factor was the amount of precipitation in September.

Conclusions. The effectiveness of machine learning and SHAP analysis in identifying critical meteorological thresholds affecting the grain crop productivity under irrigated conditions has been proven. The obtained results allow to recommend the implementation of high-frequency monitoring systems and predictive models for prompt adjustment of irrigation regimes, that helps mitigate the effects of temperature stress and improve the efficiency of water use in agriculture.

Keywords

machine learning, yield forecasting, irrigated agriculture, Random Forest, SHAP analysis, meteorological parameters, temperature stress, land reclamation efficiency

For quoting

Pochemin N. M., Morkovkin G. G. Machine learning-based crop yield prediction using meteorological data. Ways of Increasing the Efficiency of Irrigated Agriculture. 2025;97(3):187–202. (In Russ.).

Authors

N. M. Pochemin – Postgraduate Student of the Department of Soil Science, Land Reclamation and Geoecology, State University of Land Use Planning, Moscow Russian Federation, pochyomin@list.ru, ORCID ID: 0000-0002-5899-5464;

G. G. Morkovkin – Professor of the Department of Soil Science, Land Reclamation and Geoecology, Doctor of Agricultural Sciences, Professor, State University of Land Use Planning, Moscow Russian Federation, ggmork@mail.ru, ORCID ID:0000-0001-8830-7135.

Bibliography

1. Zakharov V.L., Buneev S.S., Shubkin S.Yu., Sotnikov B.A., Kravchenko V.A., 2024. Matematicheskaya model' dlya prognozirovaniya urozhaynosti yabloni na podvoe 62-396 [Mathematical model for predicting the yield of apple trees on rootstock 62-396]. Vestnik rossiyskoy sel'skokhozyaystvennoy nauki [Bullet. of Russian Agricultural Science], no. 4, pp. 69-71, DOI: 10.31857/S2500208224040126, EDN: XKVIHS. (In Russian).

2. Strashnaya A.I., Pavlova A.V., Kulakova T.V., Klang P.S., 2023. Agrometeorologicheskie usloviya i prognozirovanie urozhaynosti zernovykh i zernobobovykh kul'tur v sub"ektakh vostochnoy chasti Sibirskogo federal'nogo okruga [Agrometeorological conditions and prediction of the yield of grain and leguminous crops in the constituent entities of the eastern Siberian Federal District]. Gidrometeorologicheskie issledovaniya i prognozy [Hydrometeorological Research and Forecasting], no. 4(390), pp. 118-137, DOI: 10.37162/2618-9631-2023-4-118-137, EDN: GLOLLU. (In Russian).

3. Padma T., Sinha D., 2023. Crop Yield Prediction Using Improved Random Forest. ITM Web of Conferences. vol. 56, pp. 02007. DOI: 10.1051/itmconf/20235602007. EDN: ZULROF.

4. Verma S.K., Sinha S., Deb Chaudhury P.K., [et al.]. 2023. Crop Yield Forecasting with Precise Machine Learning. International Conference on Innovative Computing and Communications: Proceedings of ICICC, vol. 3. Lecture Notes on Networks and Systems, vol. 537. Singapore, Springer, pp. 445-453. DOI: 10.1007/978-981-99-3010-4_38.

5. Reddy S.M., Naini S., Thatipamula S., 2021. An Optimized Machine Learning Approach for Predicting Various Crop Yields. SSRN Electronic Journal, DOI: 10.2139/ssrn.3808343.

6. Debelee T.G., Kebede S.R., Waldamichael F.G., Tadesse D.M., 2023. Wheat Yield Prediction Using Machine Learning: A Survey. Pan African Conference on Artificial Intelli-gence: Communications in Computer and Information Science, vol. 1800, pp. 114-132, DOI: 10.1007/978-3-031-31327-1_7.

7. Keerthana M., Meghana K. J. M., Pravallika S. [et al.], 2021. An Ensemble Algorithm for Crop Yield Prediction. Proceedings of the 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), pp. 1547-1552, DOI: 10.1109/ICICV50876.2021.9388479.

8. Tan J.A., 2023. Comparative Analysis of the Machine Learning Model for Crop Yield Prediction in Quezon Province, Philippines. Proceedings of the 2023 8th International Conference on Communication Systems and Network Technologies (CSNT), pp. 1-5, DOI: 10.1109/CSNT57126.2023.10134593.

9. Nikhil U.V., Pandiyan A.M., Raja S.P., Stamenkovic Z., 2024. Machine Learning-Based Crop Yield Prediction in South India: Performance Analysis of Various Models. Computers, vol. 13, no. 6, p. 137, DOI: 10.3390/computers13060137, EDN: GFHVUA.

10. Kalichkin V.K., Usenko V.I., Garkusha A.A., Fedorov D.S., Maksimovich K.Yu., 2025. Interpretiruemaya model' mashinnogo obucheniya dlya prognozirovaniya uro-zhaynosti yarovoy pshenitsy [An interpretable machine learning model for spring wheat yield forecasting]. Rossiyskaya sel'skokhozyaystvennaya nauka [Russian Agricultural Science], no. 2, pp. 59-66, DOI: 10.31857/S2500262725020117, EDN: DFJMTX. (In Russian).

11. Fayzullin R.V., Novikova O.A., 2024. Primenenie metodov mashinnogo obucheniya dlya prognozirovaniya v sel'skokhozyaystvennom sektore ekonomiki [Application of machine learning methods for forecasting in the agricultural sector of the economy]. Intellektual'nye sistemy v proizvodstve [Intelligent Systems in Manufacturing], no. 22(2), pp. 69-79, DOI: 10.22213/2410-9304-2024-2-69-79, EDN: SBLSEG. (In Russian).

12. Rananavare L.B., Chitnis S., 2022. Crop Yield Prediction Using Temporal Data. IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). Bangalore, India, pp. 1-5, DOI: 10.1109/CONECCT55679.2022.9865791.

13. Raddekar A., Chikmurge D., Subhedar M., 2023. Prediction of Crop Yield with Feature Dimension Reduction Method Using Regression Models. The 7th International Conference On Computing: Communication, Control and Automation (ICCUBEA) Pune, India, pp. 1-6, DOI: 10.1109/ICCUBEA58933.2023.10392189.

14. Kutsenogii P.K., Kalichkin V.K., Pakul A.L., Kutsenogii S.P., 2021. Mashinnoe obuchenie v kachestve instrumenta prognozirovaniya urozhaynosti sel'skokhozyaystvennykh kul'tur [Machine learning as a tool for crop yields forecast]. Rossiyskaya sel'skokhozyaystvennaya nauka [Russian Agricultural Science], no. 1, pp. 72-75, DOI: 10.31857/S2500262721010178, EDN: GINGAQ. (In Russian).

15. Sundari V., Anusree M., Swetha U., Divya Lakshmi R., 2022. Crop recommendation and yield prediction using machine learning algorithms. World Journal of Advanced Research and Reviews. vol. 14, no. 3, pp. 452-459, DOI: 10.30574/wjarr.2022.14.3.0581, EDN: TVJSDU.

16. Rastog R., Bhardwaj M.K., Sharma A., 2022. Crop and Yield Prediction Through Machine Learning Techniques to Maximize Production: 21st Century Sustainable Approach for Smart Cities 5.0. Proceed. 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N). Greater Noida, India, pp. 1286-1291, DOI: 10.1109/ICAC3N56670.2022.10074244.

17. Gupta M., Santhosh Krishna B.V., Kavyashree B., Narapureddy H.R., Surapaneni N., Varma K., 2022. Crop Yield Prediction Techniques Using Machine Learning Algorithms. International Conference on Smart Structures and Systems (ICSSS) Chennai. India, pp. 1-7, DOI: 10.1109/ICSSS54381.2022.9782246.

18. Aruna Devi M., Suresh D., Jeyakumar D., Swamydoss D., Lilly Florence M., 2022. Agriculture Crop Selection and Yield Prediction using Machine Learning Algorithms. Second International Conference on Artificial Intelligence and Smart Energy (ICAIS) Coimbatore. India, pp. 510-517, DOI: 10.1109/ICAIS53314.2022.9742846.

19. Toomula S., Pelluri S., 2022. Design of Kernel Extreme Learning Machine based Intelligent Crop Yield Prediction Model. International Conference on Automation, Computing and Renewable Systems (ICACRS). Pudukkottai. India, pp. 694-701, DOI: 10.1109/ICACRS55517.2022.10029093.

20. Krishna N.V.S., Neeraj P., Surya B., Prudhvi B.V., Deepthi V.H., 2023. Machine Learning Algorithms for Crop Yield Prediction in Real-Time Scenarios. 4th International Conference on Signal Processing and Communication (ICSPC) Coimbatore. India, pp. 377-381, DOI: 10.1109/ICSPC57692.2023.10126011.

21. Arkhipova M.Yu., 2022. Modelirovanie urozhaynosti zernovykh kul'tur sel'skokho-zyaystvennykh regionov c ispol'zovaniem tekhnologiy komp'yuternogo zreniya [Modelling crop yield in agricultural regions using computer vision technologies]. Ekonomika regiona [Economy of Regions], vol. 18, no. 2, pp. 581-594, DOI: 10.17059/ekon.reg.2022-2-20, EDN: HWJDJG. (In Russian).

22. Morkovkin G.G., Shapovalov D.A., Maksimova N.B., 2025. Razrabotka metodiki otsenki sostoyaniya plodorodiya zemel' na osnove modelirovaniya urozhaynosti sel'sko-khozyaystvennykh kul'tur po prirodnym zonam Altayskogo kraya [Development of a methodology for assessing the state of Altai Territory]. Mezhdunarodnyy sel'skokhozyaystvennyy zhurnal [International Agricultural Journal], vol. 68, no. 4(406), pp. 433-437, DOI: 10.55486/25876740_2025_68_4_433. (In Russian).