نوع مقاله : مقاله پژوهشی
نویسندگان
گروه ترویج و آموزش کشاورزی، دانشکده کشاورزی، دانشگاه بوعلی سینا، همدان، ایران
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
Objective: This study analyzes the recent progress in artificial intelligence (AI) and machine learning (ML) in precision agriculture to demonstrate how these technologies contribute to optimizing agricultural processes, increasing productivity, and addressing environmental challenges and the food demands of a growing population. Given the rising demand for precision agriculture and reliance on innovative technologies, the research seeks to identify trends, challenges, and opportunities in this field.
Research Methodology: The study adopts an analytic, scientometrics (literature-based) approach. The statistical population comprises studies related to AI and ML in precision agriculture indexed in Scopus from 2000 to 2025. For article retrieval, keywords "artificial intelligence," "machine learning," "precision agriculture," and "emerging agricultural technologies" were used. Ultimately, 750 articles were selected as the study sample for analysis. To map the semantic networks of the studies, VOSviewer was employed. Additionally, Pearson correlation analysis was used to examine relationships among data to assess the validity and direction of associations between variables.
Findings: According to the analysis, the keyword "precision agriculture" emerged as the central axis of research with a frequency of 231, indicating researchers' increasing focus on optimizing processes and improving efficiency through novel technologies. The keywords "artificial intelligence" (AI) and "machine learning" (ML) occurred 195 and 176 times, respectively, reflecting researchers’ efforts to address agricultural challenges through big data analytics and weather-pattern forecasting. Temporal trend analysis shows that from 2000–2005 only 27 articles were published, rising to 387 articles in 2020–2025. This upward trajectory, especially since 2015, accelerates, evidencing broader adoption of these technologies for productivity optimization and cost reduction. Lexical clustering reveals a cluster around "precision agriculture" with terms such as "farms," "food security," and "agricultural technology," pointing to process optimization and productivity gains driven by data-based decisions. The cluster "machine learning" includes terms like "deep learning" and "support vector machines," underscoring ML techniques and their applications in agricultural data analysis. The cluster "Internet of Things" (IoT) includes terms like "sensors" and "remote sensing," highlighting data collection from devices and their use in field environments. The cluster "systems learning" centers on terms such as "decision making" and "automation," emphasizing the use of learning algorithms and systems to automate agricultural processes and optimize product performance. Pearson correlation results indicate a positive and significant relationship (P < 0.01) between the number of published articles and publication year, confirming increasing attention to AI and ML in precision agriculture in recent years and the impact of emerging technologies and data access on research trends.
Conclusion: The results indicate a growing trajectory and thematic diversity in future research on precision agriculture, which is promising. These findings provide a robust foundation for future studies and for developing effective policies in precision agriculture, contributing to improved performance, productivity, and resource management in the face of environmental changes and population growth. Recognizing the importance of aligning scientific research with practical farm needs, establishing cohesive research frameworks, upgrading data infrastructure, and encouraging active participation from farmers and related industries are identified as key priorities for the future. Consequently, the future of precision agriculture could, through enhanced efficiency, reduced costs, improved environmental sustainability, and mitigated risks from climate variability and limited resources, play a pivotal role in ensuring food security.
کلیدواژهها [English]
)