Tillage is one of the most energy-intensive operations in crop production, leading to high fuel consumption and the emission of harmful gases such as CO₂ and NO_x. This study was conducted under real field conditions to explore how soil parameters influence variations in fuel use and exhaust emissions. A machine learning approach based on the XGBoost algorithm was applied to develop predictive models for CO₂ concentrations in exhaust gases and specific fuel consumption. The CO₂ prediction model achieved an accuracy exceeding 80%, while the model for fuel consumption reached over 65%. Although not optimized for high precision, these models offer a valuable basis for preliminary assessments and highlight the potential of data-driven approaches for improving energy efficiency and environmental sustainability in agricultural mechanization.

In the realm of agricultural advancement, the relentless quest for agricultural efficiency amidst the vagaries of climate change has positioned greenhouse technology as a linchpin for secure and sustainable food production. The precise management of greenhouse microclimatic conditions i.e., the ability to accurately predict and maintain ideal temperature and relative humidity, is crucial for enhancing plant growth and health, optimizing resource use, and ensuring sustainable agricultural practices. However, maintaining optimal microclimatic conditions is a significant challenge due to the dynamic nature of external environmental influences. This study aims to address the critical need for advanced predictive tools that can enhance the control and management of greenhouse microclimates, thereby supporting sustainable agricultural practices and food security. Our research introduces a novel integration of building transient simulation (TRNSYS) and artificial neural networks (ANNs) to predict temperature and relative humidity inside a greenhouse across the calendar year, based on external atmospheric conditions. The TRNSYS model meticulously simulates the greenhouse’s thermal load, incorporating real-world data to ensure a high level of accuracy in describing the facility’s dynamic behavior. Our ANN model, composed of three layers, underwent optimization to identify the ideal number of neurons, learning rates, and epochs, settling on a model configuration that minimized prediction errors. The evaluation metrics, including root mean square error (RMSE) and mean absolute error (MAE), demonstrated the model’s effectiveness, with an RMSE of 0.3166 °C for temperature and 5.9% for relative humidity, and MAE values of 0.1002° and 3.4%, respectively. These findings underscore the model’s potential as a powerful tool for greenhouse climate control, offering substantial benefits in terms of energy efficiency, resource optimization, and overall sustainability in agriculture. By leveraging detailed dynamic simulations and advanced neural network algorithms, this study contributes significantly to the field of precision agriculture, presenting a novel approach to managing greenhouse environments in the face of changing climatic conditions.

The aim of this study is to develop an African Neutral Network (ANN) model for predicting temperature and relative humidity in the greenhouse during the calendar year. Input data are ambient temperature and relative humidity outside of the greenhouse chosen for a typical meteorological year for the location of the object and the values of temperature and relative humidity of the air in the greenhouse, obtained as a result of a TRNSYS dynamic simulation of the thermal load of the facility. The goal was to show that our ANN model is capable of making predictions over extended time period. The TRNSYS model was created on a real object, taking into account all relevant parameters, in order to describe the dynamic behavior of the object as good as possible. The ANN model is formed of 3 layers, where the number of neurons in the hidden layer is obtained by training different types in order to reach the optimal number of neurons, and the values of the learning rate and epochs are also varied. The activation functions were respectively the hyperbolic tangent in the hidden layer and the linear function in the output layer. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Correlation Coefficient were chosen as the statistical criteria for measuring of the network performance. MAE and RMSE showed that the model with 6 neurons in the hidden layer gave the best results of data prediction in relation to the input data. Statistical analysis of output shows that, the RMSE and Mean Absolute Error (MAE) between the measured and predicted temperature was 0.3166 °C and 0.1002°, and the relative humidity RMSE and MAE was 5.9% and 3.4%, respectively, which can satisfy the demand of greenhouse climate control. The results of the study showed that the model can be used with satisfactory accuracy to predict the parameters of the internal environment, in relation to the complex simulation of the thermal load of the object.

In this work, variable temperature drying regimes, mass of the samples, and the blanching pretreatments were varied to determine the influence of these parameters on the kinetics and specific energy consumption of red beetroot chips during convective drying. Beetroot samples used for the analysis were fresh and blanched slices of 5 mm thickness. Three different temperature regimes were used during drying experiments: first regime (I) was drying at a constant temperature of 70?C, second regime (II) was performed with two-stage drying at temperatures of 80?C and 55?C, and third regime (III) was conducted with three-stage drying at temperatures of 80?C, 60?C, and 55?C, respectively. Results obtained from the experiments were analyzed from the aspects of equilibrium moisture content, drying time, specific energy consumption and drying kinetics including determination of effective moisture coefficient. It was concluded that stage drying strongly affects equilibrium moisture content, while blanching pretreatment increases initial moisture content. The drying time was strongly dependent on the initial mass of the samples, while the energy consumption was depended, besides on the mass, also on drying regime, and it was found to be smallest for two-stage drying. Visually, beetroot had the typical red color for all samples at the beginning, with notable shrinkage effect at the end of the drying process.