Akademik Veri Yönetim Sistemi
Smart Agricultural Technology, cilt.11, 2025 (Scopus)
This review systematically examines recent advancements in AI-driven irrigation systems and their role in achieving sustainable water management under climate-resilient agricultural practices. By integrating machine learning algorithms, computer vision, and IoT-based sensors, these autonomous systems enable real-time soil–plant monitoring, adaptive water scheduling, and resource optimization across diverse agro-climatic contexts. Drawing upon a broad range of peer-reviewed experimental and modeling studies published between 2018 and 2025, the review highlights measurable improvements in water-use efficiency, energy savings, and crop productivity. Meta-analytical synthesis using random-effects models was employed to quantify water savings (30–50 %) and yield improvements (20–30 %), while subgroup analyses compared algorithmic performance (e.g., Random Forest, SVM, CNN) and irrigation methods. Moreover, the study discusses economic feasibility, system interoperability, sensor calibration protocols, and ethical considerations related to data governance. Findings reveal that AI-enabled irrigation offers scalable and cost-effective solutions for climate adaptation, especially in drought-prone and infrastructure-limited regions. Future research opportunities include standardization frameworks, cross-platform compatibility, and expanding validation across diverse crop types and regional settings.