The article addresses issues on application of unmanned aerial vehicles (UAV) to monitor nitrogen nutrition through the example of wheat plants. The optical spectral range can be used to monitor exploitation of the UAV. It is recommended to develop specialized spectral indices for such equipment. The article provides calibration curves for nitrogen nutrition monitoring. In the created neural networks, the linear model is represented as a network without intermediate layers, which in the output layer contains only linear elements, the weight corresponds to the elements of the matrix, and the thresholds are the components of the shear vector. During the operation, the neural network actually multiplies the vector of inputs into the matrix of scales, and then adds a vector of displacement to the resulting vector. Results of the research show how to create the specialized RPVI adapted to technological capabilities of UAVs. It has been experimentally proved that input parameters that describe the state of agricultural plantations are regularly distributed. The average statistical characteristics for additive color RGB model is advisable to be the neural network input instead of large sample data volume.

The article deals with the application of remote sensing of agricultural plantations for assessment of their nitrogen fertilizer provision. The basic technologies of remote sensing used today, their advantages and disadvantages are described. A new calibration method for images obtained from sensors placed on the platform of UAV in unstable illumination based on EXIFF data file, such as size Light Value, is proposed. In terms of agrochemical permanent study area, I have received experimental data on the spectral characteristics of wheat and verified the proposed method. The expediency of development of specialized vegetation index during the use of UAVs in the visible range of the spectrum is justified. Based on the results, a neural network has been created that determines the content of nitrogen under the image with regard to the developed method.

The article presents the study results of the intelligent control systems for biotechnological objects using the example of a greenhouse. A measuring system for effectively study of solar radiation and prediction of possible violations of information was developed. Neural networks were used as a mathematical tool for predicting temperature time series. The information channels of solar radiation were filtered using the Hilbert-Huang transformation. A transformational mathematical filter was developed, which made it possible to significantly increase the accuracy of solar radiation intensity prediction. The optimal weights for the neural network of predicting the time series of solar radiation intensity were determined with the application of the genetic algorithm. The developed vegetable production control system allows ensuring the maximum profit from the products sale and minimizes energy costs by introducing an additional unit of the neural network prediction of external disturbances and to determine control actions using fuzzy controllers.

The classification of loadings which are changed according to random laws for electric drives of agricultural and communal purposes is described in this article; the statistical characteristics of electric drives are determined. Such loads can be reduced to stationary random processes and can be approximated by one of four classes of random functions. The models of loads in the form of forming filters are presented, the structure and parameters of which depend on the class of loads. These models can be used for the optimal synthesis by statistical characteristics of electric drives, which work with random loads.

To improve energy and environmental security in urban environments and in accordance with the requirements of the EU, the task of sustainable developing agriculture in urban agglomerations and monitoring it using satellite images becomes relevant. The aim of the work is the development of methods and means for determining stable islands of thermal energy to substantiate the optimal locations for plant growing practices in the metropolis. The research was conducted in Kyiv, the largest metropolis of Ukraine. Data from the Landsat 8 and 9 satellites were used because of the free data and they have better spatial resolution and an available archive of observation results. It was established that the temperature map of the city of Kyiv shows differences in temperature between different parts of the city, probably due to the presence of different sources of heat radiation. It is obvious that the standard deviation of the temperature in the plots depends on many factors, in particular, the season and the type of land use. It is necessary to find alternative solutions for the development of crop production in this area, taking into account the characteristics of thermal emissions. Based on software products from free satellite monitoring providers, EO Browser, a specialized software solution (web application) has been created for monitoring agricultural plantations in an urban environment. A collection of LANDSAT 8 satellite images was used. Areas with stable heat emissions were found, which are due to the operation of a modern shopping and entertainment center, and non-traditional crops for landscaping adapted to its design are proposed. As a result of research, strong heat emissions were recorded for some objects, for them the temperature exceeds the surrounding area by 4 °C, while the minimum standard deviation in January is 0.5 °C, the maximum in July is 2.8 °C, in April and October—1.7 °C and 1.2 °C, respectively.

Wide class of electric drives has the stochastic torques of load which essentially worsens the technical and economic indicators of work of such electric drives. Creation of the closed systems with statistically optimal regulators could raise operation efficiency. Optimization criteria of regulating laws for controlled induction electric drives under the stochastic loads are formed. The technique of synthesis for the statistically optimal systems by a minimum criterion of root mean square error of the stabilized parameters is developed. Optimal structures of regulators of the closed electric drives of such class depending on a kind of random loads are defined. Simulation of work of the electric drive in a grain crusher has shown efficiency of a filtration by statically optimal regulator of the high-frequency components of random torques of load, increase of cyclic indicators of energy efficiency of the electric drive, such as cyclic efficiency and power factor, reduction of dispersions of its outlet parameters including the electromagnetic torque, speed and current.