This paper is devoted to the study of the construction and application of an artificial neural network for calculating the doses of fertilizer application at the planned yield level in the conditions of grey forest soils of the Republic of Tatarstan. When using mineral fertilizers for crops, it is crucial to comply with the norms and doses of the introduced substances. An overabundance of fertilizer leads to residual accumulation in the soil. Lack of quantity of applied doses affects the quality of the crop, as well as the fertility and ecological situation of agricultural lands. High modern technology and information tools allow solving this problem.

The article describes the two-year experimental study of the effect of the seeding depth on the development of spring wheat plants, the nature of development of the root system and the stalk, which has an important effect on the yield and grain quality. It was found that on gray forest medium loamy soils of the region, the most effective seeding depth is 4–5 cm.

The productivity of spring wheat crops is the result of a complex interaction of many different factors. Construction of mathematical models, using modern methods and approaches, make it possible to explore and optimize the conditions of the environment in relation to the genetic program of a particular culture and thus increase crop productivity. We used the monitoring results of wheat yield for 32 years and eight major independent factors, affecting it: humidity, the effective temperature during the growing season, rainfall, vegetation period, gluten content, the weight of a thousand grains, grain weight from one ear, straw length. The factor analysis was used previously to improve the efficiency of the model. The use of this analysis led to reveal a latent correlation between factors, and group the data, thereby reducing the dimension of the problem. We obtain four main components (MC), corresponding a linear combination of factor loadings and factors, that describe the 83% of output factor dispersion. A part of dispersion, explained by MC1, is approximately 37%; MC2 - 21%, MC - 13% MC4 - 12%. Further investigation is to build and compare two mathematical models. The first classical model is deal with the construction of the regression equation and the second is a neural network research model, based on neural networks of multilayer perceptron type with one input, one output, and one hidden layer. The four major components are used as input parameters of the model. The models were tested on the input set and checked for adequacy of using Fisher’s exact test. As a result, both models showed good results, but more similar to the original data were the results of the neural network model.

The article presents the results of 2-year studies on the main agrotechnical methods for cultivating spring wheat polba in specific conditions. It is shown that the main agrotechnological method, that determines the productivity of a variety, is the introduction of calculated doses of mineral fertilizers, the depth of seeding. To a large extent, the productivity is associated with a combination of nutritional levels, optimal stalk density and depth of seeding. The most effective variants of cultivation technology are established. Changes in the formation of the density of stemstock are revealed with a change in the seeding rates, the depth of seeding at both feeding levels.