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.

Tillage in agricultural production is one of the most demanding in terms of the tractor's energy requirements, consuming a large amount of fuel and therefore releasing the harmful products of fuel combustion into the atmosphere, where carbon dioxide and nitrogen oxides are released. The experimental test was carried out under real operating conditions on the property, where an analysis was made of all the important parameters that can be correlated with ground resistance and thus the changes in the observed parameters, i.e. the changes in specific fuel consumption and the changes in exhaust emissions. Machine learning techniques were used as highly effective modelling techniques to predict the appropriate tractor operating conditions and soil condition. XGBoost model was selected due to its flexibility and high level of learning. The models were built to predict the CO2 content in the exhaust gases and the specific fuel consumption. Although the statistical parameters were not the highest, the prediction of CO2 content based on the data analysis has an accuracy of over 80%, and the prediction of specific fuel consumption is over 65%, which can be used for a quick or initial analysis, but also represents a challenge for further research on this topic.