Abstract Purpose Efficient orchard spraying requires uniform canopy coverage while reducing pesticide drift and application rates. To achieve this, variable rate applications (VRA) are preferred. However, most current studies on VRA focus on directing the spray liquid to the tree canopy. To address these challenges, a real-time variable-rate air-assisted orchard sprayer was developed, integrating laser sensors and a hydraulic-driven turbofan controlled by LabVIEW software. Methods The objective of this study was to develop a real-time variable-rate orchard sprayer capable of controlling the outgoing airflow as well as the spray liquid based on canopy characteristics. Prior to testing, the sprayer was adapted to each orchard, and its performance was evaluated through deposition and drift trials under different canopy geometries and leaf densities. Results With VRA, air velocities were maintained between 3 and 5 m s⁻¹ at the canopy’s outer edge, a range critical for achieving adequate air capacity and droplet transport within tree canopies. VRA left 25% of the conventional application (CA) tracer on leaves, yet this value was considered adequate when the spray index data was analyzed. VRA also achieved drift reductions in ground losses (86.95%) and airborne drift (89.98%). Conclusion The system’s trigger mechanism, guided by real-time canopy data from laser sensors, proved adaptable to diverse orchard conditions. Thanks to the sprayer, more successful spraying with less drift was achieved with less pesticide usage (69.90%) and less fuel consumption (14.78%). These findings highlight the potential of this precision agriculture technology to enhance spraying efficiency, conserve resources, and minimise environmental impact.

Abstract Purpose This study evaluates the impact of nitrogen recommendations provided by a Decision Support Systems (DSS) on soft wheat production and technical efficiency in specialized Italian cereal farms. Methods Employing a Stochastic Frontier Analysis, the research evaluates the relationship between adherence to DSS recommendations and farm performance. The analysis relies on real farm data from the Barilla Farming platform, agrarian year 2022/2023, covering 487 farms and 1,664 fields, including suggested and actual nitrogen applications and observed yields. Results Findings indicate that compliance with DSS recommendations enhances output levels and efficiency, particularly for medium and large farms, whereas deviations, especially over-application, reduce efficiency with potential increase of costs and environmental risks. Notably, small farms maintain efficiency despite lower nitrogen applications, indicating the need for tailored DSS calibration. Results highlight the importance of site-specific nitrogen management strategies to optimize both economic and environmental outcomes. Conclusion While promoting DSS adoption is essential, our findings suggest that ensuring farmers’ compliance with DSS recommendations is equally—if not more—critical to realizing its full benefits. Policymakers and extension services should not only encourage the uptake of DSS but also focus on strategies that enhance farmers’ adherence to recommended practices. Additionally, ensuring the adaptability of DSS to different farm structures is key to maximizing its impact across varying production scales.

Abstract Introduction Soil nutrient management is essential for sustainable agriculture, directly affecting crop productivity and food security. Conventional laboratory-based methods for estimating soil nitrogen (N) and phosphorus (P), although accurate, are time-consuming, labor-intensive, and unsuitable for rapid or large-scale monitoring. Objectives This study aimed to develop an efficient, accurate, and scalable framework for soil nitrogen and phosphorus estimation using hyperspectral imaging integrated with deep learning techniques. Methods A total of 286 soil samples were collected from two agricultural locations in North Dakota during pre-sowing and post-harvest periods, capturing spatio-temporal variability. Laboratory chemical analyses were conducted to quantify soil N and P, and corresponding hyperspectral data were acquired in the visible and near-infrared (VNIR) and short-wave infrared (SWIR) regions. Spectral data were processed and categorized based on laboratory reference values. A convolutional neural network (CNN) model was developed for nutrient prediction, incorporating neural architecture search (NAS) and hyperparameter tuning for model optimization. The framework was evaluated using single-sensor and fused multi-sensor datasets, with spectral augmentation techniques applied to improve model robustness. Results Baseline CNN models achieved prediction accuracies of approximately 0.44, which improved to 0.68 with multi-sensor data fusion and spectral augmentation. Integration of NAS and hyperparameter tuning resulted in an additional 10–15% performance gain, achieving a final prediction accuracy of approximately 0.83 for combined nitrogen and phosphorus classification. NAS-based models showed minimal performance differences between raw and augmented datasets, while computational training time nearly doubled due to increased model search complexity. Applying NAS on raw hyperspectral data provided the most balanced trade-off between computational efficiency and predictive performance. Conclusions The integration of hyperspectral imaging with optimized CNN architectures and NAS enables accurate, scalable, and efficient soil nutrient prediction. This framework addresses spectral variability and environmental noise, offering a robust pathway for real-time soil nutrient monitoring and advancing data-driven precision agriculture.

Abstract Purpose Around a quarter of Sweden’s arable land is located within 20 m of a field boundary, yet little is known about crop growth conditions and optimal fertilization in field margins. Therefore, the present study aimed to investigate this, and assess whether there is reason to adjust fertilization in field edge zones. Methods The yield and grain quality of winter wheat ( Triticum aestivum L.) were determined at three distances from field edges (8 m, 26 m and 45 m) in eight transects bordering forests and eight transects bordering open land. Topsoil properties were determined in the same locations and differences between groups were statistically evaluated. Results The yield and thousand kernel weight were lower, and protein content was higher, close to field edges compared to yields in field interiors. The topsoil content of plant-available phosphorous (P) and potassium (K) was higher near the borders. Edge effects were greater towards forests than towards open land. The observed differences suggest lower rates of N, P and K by 22, 5 and 6 kg ha − 1 by field edges towards open land and 28, 13 and 19 kg ha − 1 by field edges towards forests, although the difference in K-rate by open land was not statistically demonstrated ( p > 0.05). Conclusion Reducing fertilizer rates in field margins can be a simple method of reducing redundant nutrient use without losing yield. More efficient nutrient use in crop production is necessary for the work towards environmental objectives, such as the 50% reduction of nutrient losses of the EU Farm to Fork Strategy.

Abstract Purpose A three-year study was carried out in a steep vineyard to study inter-annual and within-season vigor variability by proximal sensing. Methods Each season, vigor maps were obtained around veraison when a full canopy status was achieved; in 2021 and 2022, within-season vigor variability was assessed at 9 and 8 dates. Every year, main yield components, grape composition and pruning weight were determined. In 2022, dynamic in vegetative growth, canopy density, leaf gas exchange and water status, soil temperature and water status were also performed. Results Mostly due to more rapid soil warming, vines growing in low vigor (LV) plots had fostered leaf area development and shoot growth over the first three dates of measurements before high vigor (HV) fully made up at pre-flowering. From flowering onward, vine growth in LV was totally checked and the gap versus the HV kept widening. Over summer, in LV, leaf water potential assessed pre-dawn and midday reached the quite limiting thresholds of −0.6 and −1.4 MPa, whereas in HV water stress was rather moderate. Gas exchange limitations in LV essentially mirrored the above with stomatal conductance decreased to 0.03 mmol m −2 s −1 at pre-veraison. Final vine size and yield were severely curtailed in LV (−49% and −62% as compared to HV, respectively) which, on the other hand, achieved much better and complete grape maturity. Conclusion This trial confirms that even within a tiny and steep vineyard, spatial variability between vigor zones evaluated at full canopy tends to be maintained over years, thus justifying, for instance, a selective harvesting approach. However, it is quite meaningful that, in both 2021 and 2022, the ultimately defined LV vigor initially developed bigger canopy, balanced with HV at pre-flowering and then re-entered in their standard classification of “low vigor” plots. This behavior is relevant anytime a variable management strategy is planned. Indeed, early season fertilization should be adjusted with a logic opposite to that applicable to a “low vigor” level while, real-time canopy spray is recommended.