Artificial Intelligence for Irrigation Optimization in Rice Farming: A Systematic Review

The scarcity of global water resources has made irrigation optimization a key challenge for sustainable agriculture. Rice cultivation, one of the most water-intensive cropping systems, offers significant opportunities for improving water-use efficiency through artificial intelligence (AI) technologies. This systematic review evaluates the application of AI techniques for irrigation optimization in rice farming within the context of Agriculture 4.0, with the aim of identifying the principal AI approaches, application domains, research trends, and future directions. The review was conducted following the PRISMA 2020 guidelines using publications retrieved from ScienceDirect, IEEE Xplore, and the ACM Digital Library published over the past five years. Fourteen studies meeting the predefined eligibility criteria were selected for qualitative synthesis and bibliometric analysis. The results indicate that machine learning and deep learning approaches, particularly Long Short-Term Memory (LSTM) networks and Random Forest (RF) models, dominate the current literature. These methods are primarily applied to irrigation scheduling, crop water requirement prediction, soil moisture estimation, and yield forecasting. The analysis also reveals a strong geographical concentration of research in Asia, which accounts for 64.3% of the selected studies. Furthermore, data availability remains limited, with half of the datasets accessible only upon request and only 7.1% publicly available, highlighting an important barrier to reproducibility and broader adoption of AI-based irrigation solutions. Emerging research directions include the integration of remote sensing, Internet of Things (IoT) technologies, and intelligent decision support systems to enable adaptive, data-driven irrigation management. Overall, this review provides a comprehensive overview of the current state of AI-enabled irrigation optimization in rice farming, identifies existing research gaps, and outlines future opportunities for developing sustainable intelligent irrigation systems.