There is no specialized equipment designed to spread granular cylindrical organic fertilizer in the soil. There are also no rational recommendations available on how to spread this type of fertilizer. Mineral fertilizer spreaders are most often used for spreading granulated organic fertilizer. However, these fertilizers are significantly different from mineral fertilizers. Due to these differences, organic granular fertilizers often are spread unevenly, and the fertilizer does not reach the required working width. Furthermore, the rate of spreading is not accurate, and the fertilizer is often crushed too much. The objective of this research is to develop a simulation model for granular organic fertilizer applications with a centrifugal spreader in EDEM (extended distinct element method) software. It is possible to develop a numerical model that corresponds to a real spreader, and to determine the key physical–mechanical parameters for the application of granular organic fertilizer. This model can also be used for evaluating the transverse uniformity of the fertilizer in the field (along the trajectory normal to the machine). The results of this research show that the distance traveled by the fertilizer granules partially depends on the particle size, initial speed, type of fertilizer and the parameters of the spinning discs of the spreader.

Soil compaction (SC) is one of the most damaging degradation processes. The effects of compaction are closely related to crop losses and GHG emissions due to additional fuel use. It is therefore important not only to correctly monitor the condition of the soil and the restoration of damaged soil but also to understand the costs of excessive exploitation of soil and individual risks in different countries and continents. A model of equations has been developed to assess the effects of compaction that can be used on a national or even single farm scale. However, for its further application, more data should be collected. Based on the data available in the public domain, the damage caused by compaction was compared between Ukrainian (UA) and Lithuanian (LT) scenarios as these countries have a similar situation but different levels of soil resource management. Soil characteristics, such as soil types and predisposition to compaction, depending on its type, were assessed in both countries. The main parameters used to estimate the damage due to SC were: yield loss; additional fuel consumption; losses of N, P, K fertilizers, water pollution, and flooding; erosion; and GHG emissions. The results reveal potential annual losses due to compaction of around EUR 27 million for Lithuania and around EUR 1.6 billion for Ukraine. Expected potential average losses per hectare of arable land are about EUR 49 ha⁻¹ y⁻¹ for Ukraine (33.9 million ha or 56.76% of the total area) and about EUR 13 ha⁻¹ y⁻¹ for Lithuania (2.11 million ha or 33.77%). Potential crop losses are one of the costliest consequences of compaction. They could cost about EUR 1 billion annually for Ukraine and about EUR 10.7 million for Lithuania. Moreover, the additional use of fuel and the associated GHG emissions can probably take away EUR 180 million (UA) and about EUR 4 million (LT) each year.

The threshing mechanism is the main component of the combine harvester on which the grain separation and cleaning qualitative work indicators depend. It is important to ensure that all threshing mechanism components, including the threshing drum bearings and all other bearings of the combine, are working properly and reliably. There are many places in the combine where it is not possible to measure bearing vibrations directly without dismounting them, since there is no suitable spot to mount a sensor. The paper investigates the threshing drum rolling bearing condition of combines, which are difficult to access, by using a vibration diagnostics technique utilizing a newly manufactured steel bracket. The vibration measurements and analysis were conducted by the Adash A4900 Vibrio M analyzer (Adash spol. s.r.o., Ostrava, Czech Republic). The vibration source measurement was based on the fast Fourier transform (FFT) spectrum analysis. Analysis of the experimental results showed that average squared velocity values (in the frequency interval of 10–1000 Hz), together with other measured vibration parameters, can be used for the combine threshing drum‘s bearing condition evaluation.

This study evaluated the potential of Sentinel-2-derived NDVI (Normalized Difference Vegetation Index) for predicting within-field variability of winter wheat grain yield in central Lithuania during the 2024 growing season. Reliable within-field yield prediction remains challenging in regions with heterogeneous soils and limited region-specific models, particularly in northeastern Europe. Grain yield data were obtained from combine harvesters equipped with GPS yield monitoring across 13 fields with a total area of 283.6 ha. NDVI values were calculated for four half-monthly periods from March to May, corresponding to key phenological stages (from tillering to spike emergence). Spatial and temporal variability in NDVI–yield relationships was observed, with early May consistently showing the strongest correlations (r up to 0.49), particularly in lower-fertility fields, indicating its critical role in yield prediction. Machine learning models (Random Forest, XGBoost, and Deep Neural Networks), along with linear regression, were applied to predict yields based on NDVI from four growth stages. Random Forest achieved the highest predictive accuracy (MAE = 0.951 t/ha), outperforming the other models. The model also showed the highest correlation with observed yields (Pearson r = 0.717), indicating strong agreement between predicted and measured values. Feature importance analysis confirmed NDVI from 1 to 15 May as the most influential predictor across all models. Predicted yield maps closely matched observed patterns, with the largest discrepancies near field edges due to combine harvester effects. These findings highlight the utility of mid-season NDVI for precise estimation of within-field grain yield variability and demonstrate that Random Forest models can effectively capture the NDVI–yield relationship, particularly under heterogeneous field conditions.

Telemetry systems are increasingly finding applications in agriculture for a variety of tasks. These systems assist farmers in optimizing farm processes. By leveraging these technologies, energy resources can be used more efficiently, leading to reduced environmental pollution. The primary objective of this research is to analyze telemetry data and explore ways to enhance the efficiency of combine harvesters (CHs). For this study, data from the Lexion 750 TT CH equipped with a crawler chassis was selected. Harvesting operations were conducted across fields growing popular plant types in Lithuania, including wheat, barley, rapeseed, oats, corn, and beans. The selected CH was also equipped with a remote monitoring system for tracking machine parameters. During the research, the structure of the time distribution of the work and the consumed fuel was analyzed. The highest operational efficiency—defined as the proportion of time spent on productive harvesting tasks—was 78%, observed during the oat harvest, when the unloading while harvesting, unloading while idle, harvesting, and headland turns were 3%, 2%, 64%, and 9%, respectively. The lowest efficiency, 56%, occurred during wheat harvesting. It was found that harvesting 899.32 ha of six different plant species with the tested CH produces 46.11 t of GHG emissions in CO_2eq. The largest part of the emission in CO_2eq was released during direct harvesting, with the engine operating at 1800–1900 min⁻¹. However, as much as 30% of the time and 11.2% of fuel was consumed by the CH for non-harvesting activities. In conclusion, attention should be paid to reducing the inefficient use of CH time. In this way, technological operations would not only be carried out more rationally, but also environmental pollution would be reduced, and in the case of this study, we could potentially reduce CO_2eq emissions by more than 10%.

Numerous automatic technological processes control systems are implemented in modern agriculture equipment. Automation facilitates technological processes. These control systems help customers to save fertilizer and crop protection products as well as fuel. Machinery performance data is collected and stored via the Telemetry system can be sent to a customer’s computer for overview and decision-making for the following years. However, a significant quantity of data is not automatically processed by the Telemetry system. Currently, the final decisions are done on the customer’s feelings. Farmers want to be sure that the equipment they use will not only depend on the technological process but also reduce the negative impact on the environment. The aim of this study is to analyze the combine harvester data collected in the Telemetry system during harvesting at manual and auto-steering modes. The study compares the influence of combine harvester steering modes on GHG emissions and diesel fuel consumption using the Life Cycle Assessment (LCA) modules. The results show that global warming emission, using automatic steering mode, was reduced by 2.45% as compared to the manual driving mode. The diesel fuel consumption at automatic steering mode was reduced by 9.45% compared to manual driving. The working time analysis has shown a more rational and more accurate technological operation during linear steering mode. In summary, the analysis of the structure work process provides detailed information that can increase the overall productivity of the machine and optimize the work process.