Purpose: to test the hypothesis on possibility of perennial grasses yield forecast model building using machine learning methods. For agricultural production planning, the yield forecasting is one of the important tasks, and when using information technologies, building forecast models requires significantly less labor while maintaining or even increasing the accuracy and adequacy of the models.
Materials and methods. Such methods of scientific knowledge as analysis and synthesis of various levels, methods of data preparation for machine learning, machine learning methods implementing a linear regression model and regression using decision trees were used. The popular Python language and publicly available libraries for data analysis and preparation and building machine learning models were used as the main technology stack for implementing machine learning methods.
Results. The data was prepared for training the model using machine learning methods, and the data was modified without loss in such a way that it represents exclusively numerical values. Linear regression and regression models using decision trees were trained. A metric of model quality confirmed by high values of determination coefficients (0.68 and 0.98, respectively) was calculated, using standard tools from the libraries used.
Conclusions: numerical values of input of such characteristics as food regime (0.176935–0.315269), as well as the ratio of the number of irrigations and irrigation norms (0.056576–0.108139), into the model, confirm their significance for the conditions of research areas and database collection.
doi: 10.31774/2712-9357-2024-14-2-94-107
machine learning, yield forecast, predictive model, perennial grasses
Marchenko S. S., Novikov A. E., Burtseva N. I., Semenenko S. Ya. Machine learning methods application to the perennial grasses yield forecast model building under irrigation. Land Reclamation and Hydraulic Engineering. 2024;14(2):94–107. (In Russ.). https://doi.org/10.31774/2712-9357-2024-14-2-94-107.
1. Edelgeriev R.S.Kh. [et al.], 2021. Global'nyy klimat i pochvennyy pokrov Rossii: proyavleniya zasukhi, mery preduprezhdeniya, bor'by, likvidatsiya posledstviy i adaptatsionnye meropriyatiya (sel'skoe i lesnoe khozyaystvo): nats. dokl. [Global Climate and Soil Cover in Russia: Manifestations of Drought, Prevention Measures, Control, Elimination of Consequences and Adaptation Measures (Agriculture and Forestry). National report]. Vol. 3, Moscow, MBA Publ., 700 p., DOI: 10.52479/978-5-6045103-9-1, EDN: MFABZG. (In Russian).
2. Ovchinnikov A.S., Vlasov M.V., Kupriyanova S.V., 2020. Vliyanie melioratsii zemel' na minimizatsiyu pogodnykh fluktuatsiy i rost ekonomicheskogo effekta sel'skokhozyaystvennogo proizvodstva [Influence of land reclamation on minimizing weather fluctuations and increasing the economic effect of agricultural production]. Izvestiya Nizhnevolzhskogo agrouniversitetskogo kompleksa: nauka i vysshee professional'noe obrazovanie [Proceedings of the Lower Volga Agro-University Complex: Science and Higher Education], no. 1(57), pp. 14-23, DOI: 10.32786/2071-9485-2020-01-01, EDN: FENWMD. (In Russian).
3. Semenenko S.Ya., 2021. Nekotorye aspekty neobkhodimosti razrabotki nauchno obosnovannoy zonal'noy sistemy oroshaemogo zemledeliya [Some aspects of the need to develop a science-based zonal system of irrigated agriculture]. Oroshaemoe zemledelie [Irrigated Agriculture], no. 4, pp. 10-13, EDN: ICKBPJ. (In Russian).
4. Galimov R.G., 2017. Osnovy algoritmov mashinnogo obucheniya – obuchenie s uchitelem [Fundamental algorithms of machine learning – training with a teacher]. Alleya nauki [Alley of Science], vol. 1, no. 14, pp. 810-817, EDN: ZTBUCH. (In Russian).
5. Sokhina S.A., Nemchenko S.A., 2021. Mashinnoe obuchenie. Metody mashinnogo obucheniya [Machine learning. Machine learning methods]. Sovremennaya nauka v usloviyakh modernizatsionnykh protsessov: problemy, realii, perspektivy: sb. nauchnykh statey po materialam V Mezhdunaridnoy nauchno-prakticheskoy konferentsii [Modern Science in the Conditions of Modernization Processes: Problems, Realities, Prospects: Collection of Scientific Articles based on Proc. of the V International Scientific-Practical Conference]. Ufa, Bulletin of Science, pp. 165-168, EDN: BKEJKF. (In Russian).
6. Mahajan J., Banal K., Mahajan S., 2021. Estimation of crop production using machine learning techniques: a case study of J&K. International Journal of Information Technology, vol. 13, no. 4, pp. 1441-1448, https:doi.org/10.1007/s41870-021-00653-7.
7. Dronova T.N., Burtseva N.I., 2019. Rezul'taty issledovaniy po polevomu travoseyaniyu na oroshaemykh zemlyakh Nizhnego Povolzh'ya [Research results on field fodder grass cultivation on the irrigated lands of the Lower Volga region]. Problemy razvitiya APK regiona [Problems of Development of Agro-Industrial Complex of the Region], no. 4(40), pp. 40-46, EDN: NHNBBP. (In Russian).
8. Dronova T.N., Burtseva N.I., Molokantseva E.I., Zemtsova I.P., Golovatyuk O.V., 2022. Produktivnost' mnogoletnikh bobovykh trav na oroshenii [Productivity of perennial leguminous grasses under irrigation]. Izvestiya Nizhnevolzhskogo agrouniversitetskogo kompleksa: nauka i vysshee professional'noe obrazovanie [Proceedings of the Lower Volga Agro-University Complex: Science and Higher Education], no. 2(66), pp. 22-30, DOI: 10.32786/2071-9485-2022-02-02, EDN: QHKYKA. (In Russian).
9. Rogachev A.F., Melikhova E.V., Pleschenko T.V., 2021. Neyrosetevaya sistema upravleniya programmiruemym agrarnym proizvodstvom s ispol'zovaniem retrospektivnykh dannykh i rezul'tatov distantsionnogo zondirovaniya: monografiya [Neural Network Control System for Programmable Agricultural Production Using Retrospective Data and Remote Sensing Results: monograph]. Volgograd State Agrarian University, Volgograd, 172 p., EDN: QBTBVB. (In Russian).
10. Kizimova T.A., Riksen V.S., Shpak V.A., Maksimovich K.Yu., Galimov R.R., 2022. Ispol'zovanie metodov mashinnogo obucheniya dlya prognozirovaniya nitratnogo azota v pochve [Using machine learning techniques to predict nitrate nitrogen in soil]. AgroEcoInfo, no. 5(53), available: https:agroecoinfo.ru/STATYI/2022/5/st_521.pdf [accessed 15.03.2024], DOI: 10.51419/202125521, EDN: CKTGFH. (In Russian).
11. Vozmilov A.G., Lisov A.A., Urmanov V.G., Sineva G.N., 2023. Opredelenie vida zabolevaniy, porazhayushchikh list'ya kartofelya, s ispol'zovaniem algoritmov mashinnogo obucheniya [Determination of the type of potato leaves diseases with using machine learning]. Vestnik NGIEI [Bulletin NGIEI], no. 3(142), pp. 7-16, DOI: 10.24412/2227-9407-2023-3-7-16, EDN: BXWBRC. (In Russian).
12. Anchekov M.I., Bogotova Z.I., 2020. Primenenie metodov iskusstvennogo intellekta v selektsii [Artificial intelligence techniques in breeding]. Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN [News of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences], no. 6(98), pp. 91-96, DOI: 10.35330/1991-6639-2020-6-98-91-96, EDN: EPNWWM. (In Russian).
13. Baryshev D.D., Barysheva N.N., Avdeeva E.V., Pronin S.P., 2022. Primenenie metodov intellektual'nogo analiza dannykh pri diagnostirovanii kachestva semyan pshenitsy [Application of machine learning methods in diagnosing wheat seed quality]. Vysokoproizvoditel'nye vychislitel'nye sistemy i tekhnologii [High-Performance Computing Systems and Technologies], vol. 6, no. 1, pp. 114-118, EDN: OOHCQI. (In Russian).
14. Polenov D.Yu., 2021. Iskusstvennyy intellekt v regulirovanii produktivnosti ob"ektov sel'skogo khozyaystva [Artificial intelligence in regulating the productivity of agricultural objects]. Vestnik Voronezhskogo gosudarstvennogo agrarnogo universiteta [Bull. of Voronezh State Agrarian University], vol. 14, no. 1(68), pp. 46-51, DOI: 10.53914/issn2071-2243_2021_1_46, EDN: XFNNWS. (In Russian).
