This article is devoted to assessing and substantiating the threats for countries/exporters of agricultural products to the EU under conditions of the European Green Deal. The revealed comparative advantages index (RCA), comparison method, correlation and regression analysis, and taxonomic method have been applied. According to the RCA index the main causes for the relatively significant volume of agri-food exports by some countries to the EU have been identified; using the comparison method it was found that among the leading countries by agricultural products export to the EU, many states do not meet the European Green Deal target criteria for agriculture. Correlation and regression analysis has revealed that among the chosen factors only the volume of fertilisers use per cropland has direct and strong influence on CO2eq emissions; by a taxonomic method the threats value for the leading agri-food exporters to the EU has been calculated. The major agri-food exporters to the EU under conditions of the European Green Deal targets till 2030 have a high threat regarding reduction of their supply to the Member States in the case of a possible Carbon Border Adjustment Mechanism or the introduction of other import restriction mechanisms in future. The results of the study can be used by the government and other executive bodies of the analysed countries to make adequate and rapid decisions to avoid the threats of possible agri-food exports reduction to the EU under the further European Green Deal implementation.

The article proposes to use machine learning as one of the areas of artificial intelligence to forecast the volume of biogas production from household organic waste. The use of five regression algorithms (Linear Regression, Ridge Regression, Lasso Regression, Random Forest Regression, and Gradient Boosting Regression) to create an effective model for forecasting the volume of biogas production from household organic waste is considered. Based on the comparison of these algorithms by MSE and MAE indicators, the quality of training and their accuracy during forecasting are evaluated. The proposed algorithm for creating a model for forecasting biogas production volumes from household organic waste involves the implementation of 10 main and 3 auxiliary steps. Their advantage is that they aid in the performance of component data analysis, which is carried out based on the method of reducing the dimensionality of the data set, increasing interpretability, and minimizing the risk of data loss. An analysis of 2433 data is was carried out, which characterizes the formation of biogas from food (FW) and yard waste (YW) according to four features. Data preparation is performed using the Jupyter Notebook environment in Python. We select five machine learning algorithms to substantiate an effective model for forecasting volumes of biogas production from household organic waste. On the basis of the conducted research, the main advantages and disadvantages of the used algorithms for building forecasting models of biogas production volumes from household organic waste are determined. It is found that two models, “Random Forest Regressor” and “Gradient Boosting Regressor”, show the best accuracy indicators. The other three models (Linear Regression, Ridge Regression, Lasso Regression) are inferior in accuracy and were not considered further. To determine the accuracy of the “Random Forest Regressor” and “Gradient Boosting Regressor” models, we choose the MSE and MAE indicators. The Random Forest Regressor model is found to be a more accurate model compared to the Gradient Boosting Regressor. This is confirmed by the fact that the MSE of the “Random Forest Regressor” model on the training data set is 7.14 times smaller than that of the “Gradient Boosting Regressor” model. At the same time, MAE is 2.67 times smaller in the “Random Forest Regressor” model than in the “Gradient Boosting Regressor” model. The MSE and MAE of both models are worse on the test data set, which indicates overtraining tendencies. The Gradient Boosting Regressor model has worse MSE and MAE than the Random Forest Regressor model on both the training and test data sets. It is established that the model based on the “Random Forest Regressor” algorithm is the most effective for forecasting the volume of biogas production from household organic waste. It provides MAE = 0.088 on test data and the smallest absolute errors in predictions. Further systematic improvement of the “Random Forest Regressor” model for forecasting biogas production volumes from household organic waste based on new data will ensure its accuracy and maintain competitive advantages.

On the basis of the developed simulation model and the Boltzmann-Volterra integral relations with kernels of relaxation and aftereffect, an equation was worked out, which made it possible to take into account the rubber viscoelastic properties in full volume; in this equation, stiffness operator of elastic suspension in the machine is written by using fractional exponential function of the Yu. Rabotnov’s type; on the basis of the mathematical model, the basic parameters of the machine under the study were calculated; in particular, for the vortex mixer, the time dependences of amplitude of the mixer housing vibrations and coefficient of vibration isolation efficiency were calculated with taking into account aging of elastic link material in the machines; the calculation results were compared with the results of industrial tests of the vortex mixer operation lasting for 16 years. The theory and method for calculating vibration isolation systems with rubber elastic links for heavy mining machines were developed with taking into account material structure changes due to the effects of aging.

An analysis of the condition of implementation of projects in agricultural production is carried out. The disadvantages of existing methods and models of planning of the content and time of execution of works in the projects, which mostly do not take into account the changing components of their project environment, are substantiated. The proposed methodology for justifying the models of a changing project environment for harvesting grain, oilseed and legume crops is based on the analysis of official statistics of agrometeorological stations and involves the implementation of production experiments, which makes it possible to increase the accuracy of the results. It has been established that the dewy periods of time in the projects for the collection of early oilseeds, cereals and legumes are characterized by a probabilistic distribution of the time of occurrence of dew and its duration. The indicated regularity and the established correlation relationship between the occurrence of dew and its duration are the main components of the model. The substantiated model of the pink period of time allows to take into account the changing events of the project environment and to improve the quality of the content management process and the time of performance of the harvesting work. It is established that the deficit of humidity in the air, in which the performance of harvesting is effective, changes over the course of the day by parabolic dependence. Its maximum value depends on the agrometeorologically acceptable duration of the works in the projects of harvesting early oilseeds, grain and legume crops, which is the basis for substantiating the model of the air humidity deficit and taking into account its impact on the implementation of works in these projects. The obtained results of the research are the basis of development of simulation models of projects for the collection of early oilseeds, grain and legume crops to improve the accuracy of determining the use indicators and resource requirements for the implementation of these projects. The obtained models increase the quality of management decision making in the projects of harvesting early oilseeds, grain and legume crops.