However, the digital revolution in agriculture is not merely a matter of adopting new tools, but it represents a fundamental change in understanding, monitoring, and interacting with agricultural systems to enable real-time and data-driven decisionmaking.In other words, and as shown in Figure 1 below, the beforementioned integrated approach involves data flow from collection via remote and IoT sensors to artificial intelligence processing and data analysis, and then in practical applications of monitoring, detection, precision spraying, and automation. As it can be also seen, the bidirectional arrows mean continuous feedback that enables system optimization and learning. Hence, the continuous improvement of algorithms, particularly through deep learning techniques, allows not only greater accuracy in detection, but also greater robustness in variable conditions of illumination, occlusion and environmental complexity, which are intrinsic characteristics in real agricultural scenarios.Secondly, the optimization of spraying technologies is another important highlight in this paper, specifically about the increase in efficiency and environmental impact reduction when applying pesticides in orchards. For instance, an in-depth study on gas-liquid flow dynamics in multi-duct sprayers, based on computational fluid dynamics (CFD), offers new perspectives for the design of more effective equipment (Li et al.). Complementarily, the research on tips hydraulic air-assisted spraying demonstrates significant improvement in droplet deposition and drift reduction (Ou et al.). Furthermore, the integration of Global Navigation Satellite Systems (GNSS) with leaf area density sensors for variable rate spraying represents a significant advance towards localized and intelligent application of inputs (Zhao et al.). These innovations are particularly relevant considering the increasing environmental regulations that limit the use of pesticides and require greater efficiency in their application, turning precision spraying into an economic and environmental necessity.Finally, robotics and remote sensing consolidate as indispensable tools for automation and large-scale data collection. For example, the development of an autonomous navigation method for mobile robots, based on the optimization of 3D point clouds, paves the way for the execution of complex tasks without continuous human intervention (Li et al.). Also, the use of unmanned aerial vehicles (UAVs) equipped with remote sensors and AI models, such as YOLOv8, detect the maturation status of lychees, which illustrates the potential of technology fusion to optimize harvest timing and maximize production value (Liang et al.). The ability to collect spatial and temporal high-resolution data, combined with intelligent processing, allows producers to monitor plant health and development, along with several details that were impossible before, turning orchard management from an experience-based activity into a data-driven approach.All the articles selected in this paper not only highlight the state of the art in technological management of orchards, but they also signal a promising future in which precision agriculture and intelligent automation become the standard. The remaining challenges, such as the integration of data from multiple sources, cost reduction and scalability of solutions, will continue to provide valuable opportunities for further research. Particularly important is the development of integration models that allow communication between different systems and platforms, as well as the creation of viable economic models that make these technologies accessible to producers of different scales. It is hoped this paper inspires new studies that deepen the mentioned critical issues and others that may accelerate the transition to truly smart and sustainable orchards.To sum up, outstanding contributions were made by the authors and reviewers to this important area of research.
Vitoria et al. (Tue,) studied this question.