Main Article Content

T.A. Kizimova


This paper presents a multinomial logistic regression model that allows predicting and thereby quickly determining the content of nitrate nitrogen in the 0-40 cm soil layer before sowing. To build and train the model the data of a long-term multifactorial stationary field experiment of the Siberian Research Institute of Husbandry and Chemicalization of Agriculture (SRIHCA) of the Siberian Federal Scientific Centre of AgroBioTechnologies (SFSCA) of the Russian Academy of Sciences (RAS) of the time period of 2009 -2018 were used. During the analysis of the data sample (observations), the main predictors of the model that affect the content of nitrate nitrogen in the soil (target indicator) were identified. The predictors are represented by qualitative and quantitative parameters of the working area: predecessor, tillage, weather conditions, productive moisture content in the soil before sowing, nitrate nitrogen content by appropriate gradations. The quality of the developed multinomial logistic regression model was assessed using the coefficient of determination, which was 78% according to the Nagelkerke measure, and 72% according to the Cox - Snell measure. The predictive capabilities of the trained model were evaluated. The overall proportion of correct predictions for the multinomial logistic regression is 80.6%.


Download data is not yet available.


Metrics Loading ...

Article Details

Crop production


Samoilov L.N. Kompleks faktorov, vlijajushhih na proizvodstvo i kachestvo zerna pshenicy [Complex of factors affecting the production and quality of wheat grain] / L.N. Samoilov, L.S. Chernova, S.V. Trushkin // Plodorodie [Fertility]. – 2018. – №6 (105) – P.12-16. [in Russian]

Kontsevaya S. R. Analiz vlijanija abioticheskih faktorov na urozhajnost' zernovyh kul'tur [Analysis of the influence of abiotic factors on the yield of grain crops] / S. R. Kontsevaya // Buhuchet v sel'skom hozjajstve [Accounting in agriculture]. - 2018. – No. 1. – pp. 81-87. [in Russian]

Malygina N. S. Issledovanie faktorov, vlijajushhih na urozhajnost' i kachestvo zerna pshenicy (na primere Orlovskogo rajona Orlovskoj oblasti) [Investigation of factors affecting the yield and quality of wheat grain (on the example of the Oryol district of the Oryol region)] / N. S. Malygina, I. M. Tikhoikina // Vestnik Orel GIET. – 2015. – No. 3. – pp. 43-47. [in Russian]

Pasinkova E.N. Agrohimicheskie priemy regulirovanija urozhajnosti i kachestva zerna pshenicy [Agrochemical methods of regulating the yield and quality of wheat grain]: Abstract. diss. doct. biol. nauk / E.N. Pasinkova – M.: VNIIA. – 2014. – 49 p. [in Russian]

Gamzikov G.P. Pochvennaja diagnostika azotnogo pitanija rastenij i primenenija azotnyh udobrenij v sevooborotah [Soil diagnostics of nitrogen nutrition of plants and the use of nitrogen fertilizers in crop rotations] / G.P. Gamzikov // Plodorodie [Fertility]. – 2018. – №1 (100) – Pp.8-14. [in Russian]

Kidin V. V. Osnovy pitanija rastenij i primenenija udobrenij [Fundamentals of plant nutrition and application of fertilizers] / V. V. Kidin –Moscow: RGAU-MSHA. – 2008. – 415 p. [in Russian]

Vorobyova L. A. Teorija i praktika himicheskogo analiza pochv [Theory and practice of chemical analysis of soils] / L. A. Vorobyova M.: GEOS. - 2006. – 400 p. [in Russian]

Grell M. Point-of-use sensors and machine learning enable low-cost determination of soil nitrogen / M. Grell, G. Barandun, T. Asfour // Nature Food 2. – 2021. – pp. 981-989.

Anishchenko A. N. Agriculture 4. 0 kak perspektivnaja model' nauchno-tehnologicheskogo razvitija agrarnogo sektora sovremennoj Rossii [Agriculture 4.0 as a promising model of scientific and technological development of the agricultural sector of modern Russia] / A. N. Anishchenko, A. A. Shutkov // Prodovol'stvennaja politika i bezopasnost' [Food policy and security]. – 2019. – №6 (3). – Pp.129-140. [in Russian]

Ganieva I. A. Cifrovaja transformacija sel'skogo hozjajstva Rossii: konsolidacija gosudarstva i agrobiznesa [Digital transformation of agriculture in Russia: consolidation of the state and agribusiness] / I. A. Ganieva // Dostizhenija nauki i tehniki APK [Achievements of science and technology of agriculture]. – 2019. – №4 (33) – Pp. 5-7. [in Russian]

Fedorenko N. P. Cifrovoe sel'skoe hozjajstvo: sostojanie i perspektivy razvitija [Digital agriculture: state and prospects of development] / N.P. Fedorenko, D.S. Mishurov, D.S. Buklagin, etc. – Moscow: Rosinformagrotech, 2019. – 316 p. [in Russian]

Stepnykh N.V. Cifrovizacija upravlenija agrotehnologijami [Digitalization of agrotechnology management] / N.V. Stepnykh, E.V. Nesterova, A.M. Zargaryan – Kurtamysh: LLC "Kurtamysh printing house", 2018. – 43 p. [in Russian]

Yuefen L. Machine learning for the prediction of L. chinensis carbon, nitrogen and phosphorus contents and understanding of mecanisms underlying grassland degradation / Yuefen Li, Shuo Liang, Yiying Zhao et al. // Journal of Environmental Management. – 2017. –Vol. 192. – pp. 116-123.

Kalichkin V.K. Prognozirovanie soderzhanija nitratnogo azota v pochve s ispol'zovaniem mashinnogo obuchenija [Prediction of nitrate nitrogen content in soil using machine learning] / V.K. Kalichkin, T.A. Luzhnykh, V.S. Riksen // Sibirskij vestnik sel'skohozjajstvennoj nauki [Siberian Bulletin of Agricultural Science]. – 2021. – Vol. 51. – No. 5. – pp. 91-100. [in Russian]

Xinbing W. Machine learning-based in-season nitrogen status diagnosis and side-dress nitrogen recommendation for corn / W. Xinbing, M. Yuxin, D. Rui et al. // European Journal of Agronomy. – 2021. – Vol. 123. – pp. 126-193.

Osco L.P. Leaf Nitrogen Con-centration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques / L.P. Osco, J.M. Junior, A.P. Ramos et al. // Remote Sens. – 2020. – Vol .12. – pp. 32-37.

Chlingaryan A. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture / A. Chlingaryan, S. Sukkarieh, B. Whelan // A review, Computers and Electronics in Agriculture. – 2018. – Vol. 151. – P. 61-69.

Skvortsov E.A. Primenenie tehnologij iskusstvennogo intellekta v sel'skom hozjajstve [Application of artificial intelligence technologies in agriculture] / E.A. Skvortsov, V.I. Nabokov, K.V. Nekrasov et al. // AVU. – 2019. – №8 (187). – Pp. 91-98. [in Russian]

Byul A. SPSS: iskusstvo obrabotki informacii [SPSS: the art of information processing] / A. Byul, P. Cefel. – SPb.:Dia-SoftUP LLC, 2005. – 608 p. [in Russian]

Nikolenko S.I. Glubokoe obuchenie [Deep learning] / S.I. Nikolenko, A. Kadurin, E. Arkhangelskaya — St. Petersburg: St. Petersburg, 2018. — 480 p. [in Russian]

Cohen A. Method for Hypothesis Tests in Polychotomous Logistic Regression / A. Cohen, M. A. Rom // Computational Statistics and Data Analysis, 1994. – Vol. 17 – pp. 277-288.

Long J. S. Regression models for categorical and limited dependent variables, Thousand Oaks / J. S. Long Sage – Publ, 1997. – 328p.