article · IEEE Access
This review addresses critical gaps in the understanding of AI integration across modern agricultural systems through a systematic analysis of hybrid architectures, adaptation strategies, learning approaches, and knowledge integration methods. Following the PRISMA guidelines, we reviewed 200 papers published over the period 2019-2024, identifying key trends in AI implementation, including the dominance of hybrid approaches and evolution towards data-efficient methodologies. Our meta-analytical synthesis of 51 high-quality studies revealed that hybrid adaptation approaches achieve superior performance (91-94% accuracy) in disease detection and crop monitoring tasks, whereas environmental adaptation strategies offer an optimal balance between performance and resource requirements. Data-efficient learning approaches have shown significant growth, with transfer learning adoption increasing from 30% to 45% of studies, addressing the critical challenge of limited training data in agricultural contexts. We examined implementation challenges, including economic feasibility, ethical considerations, system robustness, and adoption barriers for smallholder farmers. This review provides a comprehensive framework for understanding the current AI applications in agriculture and establishes priorities for sustainable and inclusive agricultural technology development.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2025.3597844
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
