This study investigated the relationships between the electrical and selected mechanical properties of soil. The analyses focused on comparing various modeling relationships under study methods that included machine learning methods. The input parameters of the models were apparent soil electrical conductivity and magnetic susceptibility measured at depths of 0.5 m and 1 m. Based on the models, shear stress and soil compaction were predicted. Neural network models outperformed support vector machines and multiple linear regression techniques. Exceptional models were developed using a multilayer perceptron neural network for shear stress (R = 0.680) and a function neural network for soil compaction measured at a depth of 0–0.5 m and 0.4–0.5 m (R = 0.812 and R = 0.846, respectively). Models of very low accuracy (R < 0.5) were produced by the multiple linear regression.

This study focused on the reaction of bivalve molluscs to biogas digestate, which is a waste product of an increasingly developing biogas production in rural areas worldwide. The effects of biogas digestate on aquatic organisms are not fully known, and neither this substance nor any types of manure were tested in the monitoring based on valvometry, which is a biomonitoring method based on bivalve behavior. The change in bivalves functioning in biogas digestate inflow was studied using three different diluted digestate concentrations. Exposure to the highest concentration of digestate induced a decline of mean shell opening and activity time of Unio tumidus species. A significant difference in behavioral patterns was recorded during the first 10 min after exposure to the digestate. A Gradual decreasing tendency of shell opening levels was apparent under the highest concentration reaching 55% compared to the pretreatment value. Also, a decreasing tendency was observed under the medium concentration (82.4% of initial level) after 2 h, while an increase in shell opening levels was recorded in the most diluted digestate. This research work proved that the inflow of biogas digestate has significant impact on bivalves’ behavior. Unio tumidus is a sensitive indicator of biogas digestate inflow in the aquatic environment. Moreover, it proved that the opening and closing activities over time depend on the concentration of the digestate. Therefore, the mollusk bivalves might be utilized in early warning systems to detect organic pollutants in water.

The agricultural sector is one of the most significant sectors of the global economy, yet it is concurrently a highly energy-intensive industry. The issue of optimizing field operations in terms of energy consumption is therefore a key consideration for sustainable agriculture, and the solution to this issue leads to both environmental and financial benefits. The aim of this study was to estimate energy consumption during soil cultivation using geophysical scanning data and machine learning (ML) algorithms. This included determining the optimal set of independent variables and the most suitable ML method. Soil parameters such as electrical conductivity, magnetic susceptibility, and soil reflectance in infrared spectra were mapped using data from Geonics EM-38 and Veris 3100 scanners. These data, along with soil texture, served as inputs for predicting fuel consumption and field productivity. Three machine learning algorithms were tested: support vector machines (SVMs), multilayer perceptron (MLP), and radial basis function (RBF) neural networks. Among these, SVM achieved the best performance, showing a MAPE of 4% and a strong correlation (R = 0.97) between predicted and actual productivity values. For fuel consumption, the optimal method was MLP (MAPE = 4% and R = 0.63). The findings demonstrate the viability of geophysical scanning and machine learning for accurately predicting energy use in tillage operations. This approach supports more sustainable agriculture by enabling optimized fuel use and reducing environmental impact through data-driven field management. Further research is needed to obtain training data for different soil parameters and agrotechnical treatments in order to develop more universal models.

Plant infestations cause significant economic losses in agriculture, necessitating rapid and accurate detection for optimized agrotechnical operations and reduced environmental pollution. This study addresses this challenge by proposing a customized convolutional neural network (CNN) architecture for detecting corn leaf worm infestations in maize. The research focuses on developing unique CNN models through extensive experimentation, systematically adjusting hyperparameters like optimizers, filter numbers, and kernel sizes. The study’s main contributions include the design of an accurate CNN classifier, and its implementation in a user-friendly smartphone application. The research highlights the importance of hyperparameter tuning in CNN performance, demonstrating that optimal configurations lead to high accuracy (up to 95% for accuracy, precision, recall, specificity, and F1-score). While the current model focuses on a single pest, the findings underscore the potential of custom CNN classifiers in vision systems for automated crop inspection, offering a promising solution for minimizing crop losses and the environmental impact of chemical plant protection products.

Soil compaction is a crucial agricultural issue impacting plant growth, water infiltration, and soil health. Because of its sensitivity to soil variables such as texture, moisture content, and salinity, soil electrical conductivity (ECa) has emerged as a promising indirect predictor of soil compaction. This review summarizes selected studies on the relationship between soil compaction and apparent electrical conductivity and examines various prediction approaches. It also considers the potential applications and limitations of using ECa to estimate soil compaction, including methods based on machine learning. Future advancements in technology, modeling, and data integration will be key to fully realizing the potential of ECa in soil compaction management.

Effective spraying is essential for modern agricultural production, to ensure a high-quality and abundant harvest. Simultaneously, it is crucial to minimise the negative impact of crop protection products on the environment. To achieve this, it is necessary to implement the appropriate technical and technological parameters for the treatment and to consider the conditions under which the treatment is carried out. The aim of this study was to determine the relationship between the speed of the sprayer, the pressure of the liquid, and the type of nozzles, as well as air temperature and wind speed, in terms of the degree of coverage of the sprayed surfaces. The degree of coverage was analysed by spraying water-sensitive papers placed on the artificial plant, positioned to obtain horizontal and vertical surfaces. The study found that standard single flat fan nozzles provided greater coverage on upper horizontal surfaces, while standard nozzles were more effective for vertical transverse approach surfaces at lower fluid pressures and travel speeds. Neural networks were used to develop models of the relationships studied. Models with high accuracy for the validation data set were obtained in the case of the coverage of the vertical transverse leaving surface and the upper level surface (R = 0.93 and R = 0.86). These models were used to determine the optimum values of the technical parameters of the spraying process under the selected weather conditions. The maximum spray coverage (41.49%) was predicted for the XR nozzle under the following conditions: pressure = 200 kPa, driving speed = 1.4 m·s⁻¹, temperature = 21.73 °C and wind speed = 0.32 m·s⁻¹. Based on the sensitivity analysis of the neural models it was found that the greatest effect on the coverage of the vertical transverse leaving surface was observed for temperature and the coverage of the upper level surface was mostly influenced by driving speed.