Machine learning in predicting crop rotation productivity
https://doi.org/10.26897/2687-1149-2025-1-41-52
Abstract
Crop rotation contributes to maintaining sustainable farming systems. The application of machine learning will enable more efficient design and prediction of crop rotation productivity. Traditional data processing methods do not meet the requirements of intelligent farming. To evaluate the application of machine learning, models for predicting crop rotation productivity were built based on six algorithms: decision tree (CART), random forest (RF), bootstrap aggregating (Bagging), Gradient Boosting, extreme gradient boosting (XGBoost), and artificial neural network (ANN). The study used time series data on the productivity of nine types of crop rotations at three levels of technogenic inputs, obtained in the forest-steppe of the Ob region in Novosibirsk Oblast by the Siberian Research Institute of Agriculture and Chemicalization of Agriculture of the SFSCA RAS during 1999-2019. As an additional predictor, the model included an atmospheric moisture indicator in the form of the Standardized Precipitation Index (SPI), calculated as the average atmospheric moisture indicator for May-July over the rotation of each analyzed crop rotation. Models describing crop rotation productivity based on ANN, Gradient Boosting, and XGBoost algorithms were characterized by the highest predictive abilities depending on the prevailing atmospheric moisture conditions and the level of cultivation technology intensification (R2 = 0.90…0.93). Comparative analysis showed that the model based on extreme gradient boosting demonstrates the best performance with a determination coefficient (R2) of 0.93, root mean square error (RMSE) of 2.34, and mean absolute error (MAE) of 1.81. The possibility of applying machine learning methods as an effective tool for predicting crop rotation productivity has been demonstrated.
About the Authors
V. K. Kalichkin
Siberian Federal Scientific Centre of AgroBioTechnologies of the Russian Academy of Sciences
Russian Federation
Russian Federation
Vladimir K. Kalichkin, DSc (Ag), Head of Agriculture and Agrochemistry Research Area, SFSCA RAS
D. S. Fedorov
Siberian Federal Scientific Centre of AgroBioTechnologies of the Russian Academy of Sciences
Russian Federation
Russian Federation
Dmitry S. Fedorov, Junior Researcher, Agro-Climatic Research Laboratory, SFSCA RAS
K. Yu. Maksimovich
Siberian Federal Scientific Centre of AgroBioTechnologies of the Russian Academy of Sciences
Russian Federation
Russian Federation
Kirill Yu. Maksimovich, PhD (Biology), Research Associate, Agro-Climatic Research Laboratory, SFSCA RAS
630501, Tsentralnaya Str., 2b, Krasnoobsk, Novosibirsk Oblast
V. S. Riksen
Siberian Federal Scientific Centre of AgroBioTechnologies of the Russian Academy of Sciences
Russian Federation
Russian Federation
Vera S. Riksen, Head of Agro-Climatic Research Laboratory, SFSCA RAS
References
1. Kiryushin V.I. The management of soil fertility and productivity of agrocenoses in landscape adaptive farming systems. Pochvovedenie. 2019;9:1137-1139. (In Russ.) https://doi.org/10.1134/S0032180X19070062
2. Stepnykh N.V., Nesterova E.V., Zargaryan A.M., Zemledelie. 2022;2:7-13. (In Russ.)
3. Лошаков В.Г. Development of the doctrine about crop rotation in RSAU-MTAA. Zemledelie. 2017;2:3-9. (In Russ.).
4. Zavyalova N.E., Fomin D.S., Teterlev I.S. Effect of crop rotations and monoculture on agrochemical propertiesand nitrogen regime of sod-podzolic soil of the Cis-Ural region. Agrohimiya. 2019;1:5-10. (In Russ.). https://doi.org/10.1134/S0002188119010162
5. Kurdyukova O.N. Weed infestation of crops and short rotating crops productivity in the steppe zone. Bulletin of KSAU. 2022;7;184:69-76. ( In Russ.). https://doi.org/10.36718/1819-4036-2022-7-69-76
6. Akimenko A.S., Sviridov V.I., Dudkina T.A., Vavin V.G., Dolgopolova N.V. Substantiation of the direction of grain pro duction intensification in crop rotations of the forest-steppe of the Central Chernozem region. Zemledelie. 2023;1:3-7. https://doi.org/10.24412/0044-3913-2023-1-3-7
7. Makarova E.I. Economic and mathematical modeling of structural optimization of cropping system of agricultural enterprises. Vestnik of Voronezh State Agrarian University. 2015;4-2:174-178. (In Russ.).
8. Nuretdinov I.G., Nuretdinova Yu.V., Khasyanov O.R. Optimization of sown area structure of crops by economic and mathematical modeling: practical aspect. Vestnik of the Kazan State Agrarian University. 2015;10(4):24-27. (In Russ.).
9. Sviridov V.I. Methodological and methodological aspects of designing the optimal structure of acreage in the transition to adaptive landscape farming. Vestnik Kurskoy Gosudarstvennoy Selskohozyaystvennoy Akademii. 2018;2:4-10. (In Russ.).
10. Nikitina K.R. Crop rotation optimization using the quadratic programming approach. Ekonomics. Management. Innovations.2019;2:92-96. (In Russ.).
11. Apazhev A.K., Shekikhachev Yu.A. Optimization of the functioning of agricultural production systems. Izvestiya Kabardino-Balkarskogo gosudarstvennogo agrarnogo universiteta im. V.M. Kokova = Izvestiya of the Kabardino-Balkarian State Agrarian University named after V.M. Kokov. 2022;1:81-89. https://doi.org/10.55196/2411-3492-2022-1-35-81-89 (In Russ.).
12. Dudko Yu.V., Marinkin E.B., Vladimirova T.M. Use of neural network technologies in predicting soil fertility when growing leguminous crops and predicting their yield. Voprosy Nauki: Innovatika, Tekhnika i Tekhnologii. 2019;1:67-72. (In Russ.).
13. Rogachev A.F. System analysis and forecasting of yield time series based on autocorellation functions and neural network technologies. Proceedings of Lower Volga Agro-University Complex: Science and Higher Education. 2018;3:309-316. (In Russ.).
14. Rogachev A.F. Melikhova, E.V. Justification of algorithms and tools for neural network forecasting of agricultural productivity using retrospective data. Proc. of the Lower Volga AgroUniversity Comp. 2020;1:290-302. (In Russ.). https://doi.org/10.32786/2071-9485-2020-01-29
15. Lebed N.I., Tokarev K.E., Nekhoroshev D.D., Storozhakov S.Yu., Popov A.Yu. Development of methods for managing the production processes of phyto-agrocenoses in precision farming using hybrid automated systems and artificial intelligence algorithms. Mezhdunarodnyi Sel’skohozyaistvennyi Zhurnal. 2024;2:201-204. (In Russ.).
16. Benos L., Tagarakis A.C., Dolias G. et al. Machine learning in agriculture: A comprehensive updated review. Sensors. 2021;21(11):3758. https://doi.org/10.3390/s21113758
17. Attri I., Awasthi L.K., Sharma T.P. Machine learning in agriculture: a review of crop management applications. Multimedia Tools and Applications. 2024;83(5):12875-12915. https://doi.org/10.1007/s11042-023-16105-2
18. Taye M.M. Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions. Computers. 2023;12(5):91. https://doi.org/10.3390/computers12050091
19. Kalichkin V.K., Alsova O.K., Maksimovich K.Y. Application of the decision tree method for predicting the yield of spring wheat. IOP Conference Series: Earth and Environmental Science. IOP Publishing. 2021;839(3):032042. https://doi.org/10.1088/1755-1315/839/3/032042
20. Elavarasan D., Vincent P.M. D.R. A reinforced random forest model for enhanced crop yield prediction by integrating agrarian parameters. Journal of Ambient Intelligence and Humanized Computing. 2021;12:10009-10022. https://doi.org/10.1007/s12652-020-02752-y
21. Kok Z.H., Shariff A.R.M., Alfatni M.S.M., Khairunniza-Bejo S. Support vector machine in precision agriculture: a review. Computers and Electronics in Agriculture. 2021;191:106546. https://doi.org/10.1016/j.compag.2021.106546
22. Hegedus P.B., Maxwell B.D., Mieno T. Assessing performance of empirical models for forecasting crop responses to variable fertilizer rates using on-farm precision experimentation. Precision Agriculture. 2023;24:677-704. https://doi.org/10.1007/s11119-022-09968-2
23. Gopal M.P.S., Bhargavi R. Performance evaluation of best feature subsets for crop yield prediction using machine learning algorithms. Applied Artificial Intelligence. 2019;33(7):621-642. https://doi.org/10.1080/08839514.2019.1592343
24. Han J., Zhang Z., Cao J. et al. Prediction of winter wheat yield based on multi-source data and machine learning in China. Remote Sensing. 2020;12(2):236. https://doi.org/10.3390/rs12020236
25. Tigkas D., Vangelis H., Tsakiris G. DrinC: a software for drought analysis based on drought indices. Earth Science Informatics. 2015;8:697-709. https://doi.org/10.1007/s12145-014-0178-y
26. Breiman L., Friedman J., Olshen R.A., Stone C.J. Classification and Regression Trees (1st ed.). Chapman and Hall/CRC. 1984;368. https://doi.org/10.1201/9781315139470
27. Breiman L. Random forests. Machine learning. 2001;45:5-32. https://doi.org/10.1023/A:1010933404324
28. Breiman L. Bagging predictors. Machine learning. 1996;24:123-140. https://doi.org/10.1007/BF00058655
29. Friedman J.H. Greedy function approximation: a gradient boosting machine. The Annals of Statistics. 2001;29(5):1189-1232. https://doi.org/10.1214/aos/1013203451
30. Haykin S. Neural networks: A comprehensive foundation. Prentice Hall PTR. Upper Saddle River, NJ. United States. 1994;768.
31. Kalichkin V.K., Fedorov D.S., Alsova O.K., Maksimovich K.Yu. Development of software for analyzing and forecasting crop yields. Achievements of Science and Technology in Agro-Industrial Complex. 2022;36(1):51-56. (In Russ.). https://doi.org/10.53859/02352451_2022_36_1_51
32. Crop Yield Analysis & Forecast (CYAF) software. Fedorov D.S., Alsova O.K., Kalichkin V.K., Maksimovich K.Yu. Certificate of state registration of software No. 2021777894, 08.11.2021. (In Russ.).
33. Du Z., Yang L., Zhang D. et al. Corn variable-rate seed ing decision based on gradient boosting decision tree model. Computers and Electronics in Agriculture. 2022;198:107025. https://doi.org/10.1016/j.compag.2022.107025
34. Sarijaloo F.B., Porta M., Taslimi B., Pardalos P.M. Yield performance estimation of corn hybrids using machine learning algorithms. Artificial Intelligence in Agriculture. 2021;5;82-89. https://doi.org/10.1016/j.aiia.2021.05.001
35. Awasthi P., Mishra S., Gupta N. Performance Assessment of Machine Learning Techniques for Corn Yield Prediction. International Conference on Advanced Network Technologies and Intelligent Computing. Cham: Springer Nature Switzerland. 2022;320-335. https://doi.org/10.1007/978-3-031-28183-9_23
36. Wolanin A., Mateo-García G., Camps-Valls G. et al. Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt. Environmental Research Letters. 2020;15(2):024019. https://doi.org/10.1088/1748-9326/ab68ac
37. Hassija V., Chamola V., Mahapatra A. et al. Interpreting black-box models: a review on explainable artificial intelligence. Cognitive Computation. 2023;16:45-74. https://doi.org/10.1007/s12559-023-10179-8
38. Wang X., Huang J., Feng Q., Yin D. Winter wheat yield prediction at county level and uncertainty analysis in main wheat-producing regions of China with deep learning approaches. Remote Sensing. 2020;12(11):1744. https://doi.org/10.3390/rs12111744
39. Reichstein M., Camps-Valls G., Stevens B. et al. Deep learning and process understanding for data-driven Earth system science. Nature. 2019;566:195-204. https://doi.org/10.1038/s41586-019-0912-1
40. Kalichkin V.K., Maksimovich K.Yu. Methodology for forming a digital farming management system. Siberian Herald of Agricultural Science. 2024;54(3):5-20. (In Russ.)
Review
For citations:
Kalichkin V.K., Fedorov D.S., Maksimovich K.Yu., Riksen V.S. Machine learning in predicting crop rotation productivity. Agricultural Engineering (Moscow). 2025;27(1):41-52. (In Russ.) https://doi.org/10.26897/2687-1149-2025-1-41-52
Views:
128
Email this article 