Precision agriculture in the age of AI: A systematic review of machine learning methods for crop disease detection

Artificial Intelligence (AI) has become a critical tool in modern precision agriculture, particularly in the detection of plant diseases and pests. This study provides a comprehensive review of current AI methodologies applied to crop disease detection, with a focus on machine learning models, dataset availability, and performance metrics. Our findings indicate that Convolutional Neural Networks (CNNs) are the most widely used and cost-effective approach, while Vision Transformers (ViTs) exhibit superior accuracy but require significantly higher computational resources. We identify key research gaps, including the geographic bias in dataset origins, the trade-off between data quality and quantity, and the limited exploration of hybrid AI models. Additionally, challenges related to the scalability and real-time applicability of AI solutions in resource-constrained agricultural environments highlight the need for more efficient computational techniques. Cost-effectiveness remains a concern, as high-performance models often demand expensive infrastructure and expertise, limiting their adoption by smallholder farmers. Furthermore, cybersecurity risks in digital agriculture and disparities in research focus across different crops and disease types underscore the necessity for broader investigations. Unlike prior reviews, this study uniquely integrates methodological performance, dataset characteristics, and cybersecurity perspectives, offering a holistic synthesis that highlights not only technical advances but also practical barriers to large-scale adoption. Future work should prioritize model robustness, efficiency, and accessibility.