Precision viticulture systems are essential for enhancing traditional intensive viticulture, achieving high-quality results, and minimizing costs. This study explores the integration of Unmanned Aerial Vehicles (UAVs) and artificial intelligence in precision viticulture, focusing on vine detection and vineyard zoning. Vine detection employs the YOLO (You Only Look Once) deep learning algorithm, achieving a remarkable 90% accuracy by analysing UAV imagery with various spectral ranges from various phenological stages. Vineyard zoning, achieved through the application of the K-means algorithm, incorporates geospatial data such as the Normalized Difference Vegetation Index (NDVI) and the assessment of nitrogen, phosphorus, and potassium content in leaf blades and petioles. This approach enables efficient resource management tailored to each zone’s specific needs. The research aims to develop a decision-support model for precision viticulture. The proposed model demonstrates a high vine detection accuracy and defines management zones with variable weighting factors assigned to each variable while preserving location information, revealing significant differences in variables. The model’s advantages lie in its rapid results and minimal data requirements, offering profound insights into the benefits of UAV application for precise vineyard management. This approach has the potential to expedite decision making, allowing for adaptive strategies based on the unique conditions of each zone.

The conducted research aims to ascertain the variations in macro and microelement content within the soil-to-leaf relationship in small vineyards. The vineyard block (1.2 ha), located in Sremski Karlovci, Serbia, planted with Grasac (Riesling Italico), was divided into 20 subplots. Each subplot served as an individual location for soil and leaf sampling. Soil samples were collected at three depths, while leaf sampling occurred at two phenophase (end of flowering and at ripening), with separation into petiole and blade parts. Vari?ability of soil physico-chemical characteristics between subplots was determinate, with the greatest variability in the 30-60 cm soil layer. The soil generally displayed low levels of organic matter and available P, K, Zn and B. Erosion processes were indicated by the spatial distribution of physico-chemical parameters. Differences in nutrient contents were noted among leaf parts and phenophases, aligning with existing literature. Comparing leaf nutrient status to optimal values from literature, N and P content was found at lower limits, confirming K and B deficiencies. Identically, fertilization recommendations can be inferred from soil and foliar analyses, primarily for N, K and B. Additionally, based on soil analysis, a slight increase in P and Zn application is advisable. Established correlations among all observed variables revealed connections between soil parameters, across all depths, and nutrients in the leaf blade at the end of flowering. It is notable to say that nutrient content in soil, particularly N, K, Mn and Zn, exhibited statistically significant positive correlations with its content in the leaf blade, respectively. Further research is necessary to lay the foundation for the development of ac?curate and reliable criteria for diagnosing nutrition, not only for the whole species but also among grapevine leading varieties. Given the significant variations in nutrient requirements and accumulation among these genotypes, this research will be instrumental in ensuring op?timal nutrient supply while minimizing deficiencies or excesses.