A systematic review of artificial intelligence and internet of things applications in precision agriculture

Abstract

Precision agriculture is increasingly leveraging advancements in artificial intelligence (AI) and machine learning (ML) to address global food demands sustainably. Previous literature on smart agriculture may have considered AI, IoT, and 5G but has not integrated the technology synergies or may overlook the newer trends, including XAI and edge-ready lightweight AI models. This paper addresses those gaps by synthesizing new trends, socio-economic challenges, and relevant policy frameworks that shape the future of AI-enabled agricultural practices. A structured literature review methodology was adopted using Scopus, IEEE Xplore, ScienceDirect, and SpringerLink databases. A total of 78 high-quality studies published between 2018 and 2025 were systematically analyzed.In particular, this review paper synthesizes insights from literature to argue that AI-ML integration improves productivity in agriculture in terms of crop yield prediction, disease prediction and optimization of resources, amongst others. However, there are several adoption barriers such as data privacy issues, costly infrastructural setup, and lack of digital literacy skills among small-scale farmers. We emphasize the importance of using edge computing for faster decision-making and robotics in scaling up precision solutions and also highlight the use of XAI to foster trust via interpretability in AI. Finally, we propose a comprehensive strategy for future work in designing sustainable agrifood systems based on: (1) interoperable systems using standards and protocols, (2) affordable and cyber-resilient systems, and (3) policy initiatives to democratize AI technologies. By addressing technical, ethical, and scalability challenges, this work advocates for a balanced convergence of human expertise and automated systems, ensuring equitable progress toward sustainability goals.