|
|
:
|
In recent decades, advancements in digital technologies, particularly the Internet of Things (IoT) and artificial intelligence (AI), have driven considerable transformation within the agricultural sector. The present study seeks to deliver an integrated and comprehensive synthesis of national research initiatives focused on smart agriculture. This report consolidates and harmonizes the findings of multiple research projects in digital agriculture across Iran. The reviewed materials encompass a range of applications, including IoT-based systems for monitoring and managing apple orchards; smart irrigation approaches for wheat and barley production alongside a case study on grain maize; feasibility studies and deployment of intelligent irrigation within the Lake Urmia watershed; an AI-enabled weed-image recognition system; and an assessment of IoT effectiveness in cold-water aquaculture hatcheries. In apple orchards, a four-layer framework comprising perception, transmission, processing, and application was implemented using wireless sensor networks (LoRa/WSN), a network server, and a management dashboard to support soil and air moisture monitoring as well as early detection of diseases and pests (powdery mildew and codling moth). This system contributed to reduced pesticide application frequency and improved irrigation efficiency. Within wheat and barley cultivation (Alborz Province pilot), sensor nodes, a communication gateway, and a local weather station were integrated into an electronic decision-support tool, facilitating environmental alerts and operational scheduling. For grain maize, phenology-based irrigation scheduling was employed using soil moisture depletion relative to field capacity and growing degree-day metrics. The findings underscore the necessity of localized calibration to ensure optimal system performance. In the Lake Urmia basin, field assessments and document analyses reveal substantial opportunities to enhance irrigation water productivity, varying significantly by crop type and province. Capacity building and improved on-farm irrigation management are identified as critical prerequisites for effective implementation. In the aquaculture sector, despite progress in mechanization, the degree of digital integration remains limited. Real-time monitoring of key water-quality parameters—dissolved oxygen, pH, nitrate, and nitrite—along with automated aeration control, offers strong potential for reducing production risks. Regarding weed management, field experiments demonstrate that the lightweight MobileNetV3 model achieves 92% accuracy under controlled conditions and 88% in field environments, supporting its feasibility for low-cost deployment on simple hardware platforms. Overall, the report outlines the theoretical foundations, integrated methodological approach, major outcomes of each project, quantitative and qualitative analyses, policy considerations, infrastructure requirements, an implementation roadmap, and performance evaluation indicators.
|