Digital Technologies for Assessing and Predicting the Impact of Spatiotemporal Distribution of Greenhouse Gases on the Photosynthetic Activity of Crops

Abstract

Purpose of research: formation of a bank of models for the implementation of simulation experiments to assess and predict the values of greenhouse gas concentrations in the surface layer of the territory's atmosphere based on artificial neural networks and GIS technologies. The influence of the increased concentration of carbon dioxide in the surface layer of the atmosphere on the growth and development of agricultural plants, namely on the change in photosynthetic activity, the level of mineralization of the humus layer of the soil, which affects crop yields, is considered. The peculiarities of agricultural production determine the relevance of the creation and implementation of a new intelligent technology that will provide the opportunity to identify optimal parameters of crop production.Methods. The formation of a training sample for a neural network was carried out through numerical experiments and mathematical modeling methods. To select the best neural network topology for predicting the concentration of greenhouse gases in the territory under consideration, experiments were conducted that revealed the standard deviation and relative error. To assess the predictive abilities of the models, field experiments were conducted to measure CO2 concentrations in the surface layer of the atmosphere in the agricultural territories of the Belgorod region.Results. A software toolkit has been developed that makes it possible to visualize the dispersion and accumulation of greenhouse gases in the surface layer of the atmosphere. This makes it possible to conduct simulation experiments necessary to determine the territories that are under the influence of man-made sources. An assessment of the photosynthetic activity of plants in the selected territory was carried out, which allows us to form further recommendations for the effective use of agricultural territory aimed at increasing crop yields.Conclusion. The paradigms of neural networks were considered, experiments were conducted to identify the best topology. A software toolkit has been developed to visualize the dispersion and accumulation of greenhouse gases in the surface layer of the atmosphere for decision makers. The effects of technogenic factors on the photosynthetic apparatus of agricultural plants are analyzed, on the basis of which conclusions and practical recommendations for the cultivation of agricultural crops are formulated.