نوع مقاله : مقاله ترویجی
نویسندگان
1 کارشناس تحقیقات ، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان فارس
2 دانشیار ، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان فارس
3 استادیار ، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان فارس
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
In recent years, the use of artificial intelligence and cognitive technologies in agriculture has led to a significant transformation in production, resource management and farm monitoring. By analyzing abundant data such as weather conditions, soil characteristics, crop growth status and market preferences, artificial intelligence provides farmers with efficient tools for more accurate decision-making. Sensors, drones and robots equipped with machine learning algorithms have enabled targeted operations such as irrigation, fertilization and pesticide spraying, which results in reduced input consumption, maintenance of soil quality and increased productivity. Along with these developments, remote sensing and satellite imagery (especially Sentinel-2) play an important role in identifying and classifying vegetation, mapping agricultural land and monitoring environmental changes. The use of machine learning and deep learning algorithms—including convolutional neural networks (CNNs), support vector machines, decision trees, and random forests—has increased the accuracy of satellite data analysis and the production of high-resolution agricultural maps. Despite the significant benefits, challenges such as the lack of standardized spatial data, limited computational infrastructure, the need for interdisciplinary expertise, and the lack of coherent policies on data and AI have hindered the development of these technologies. Overall, the combination of AI, remote sensing, and machine learning can pave the way for sustainable, smart, and data-driven agriculture.
کلیدواژهها [English]
)