Answers are grounded in this paper and cite their sources.
Plant diseases pose a persistent threat to crop quality, food safety, and the sustainability of agriculture worldwide. The diversity of pathogens, the variability of disease symptomatology, and the complexity of environmental conditions make early and accurate disease diagnosis a significant challenge. The automation of agricultural data analysis and the improvement of plant disease diagnosis are achieved through convolutional neural networks (CNNs), vision transformers (ViTs), attention-based networks, YOLO-based detection, EfficientDet, and hybrid deep learning systems, which have progressed within the Agriculture 5.0 framework. This review summarizes the recent advances in the use of deep learning for plant health assessment and Phyto pathological disease diagnosis. It discusses and classifies the deep learning approaches for plant disease analysis, including disease classification, object detection, image segmentation, and hybrid intelligent systems. The model architecture, dataset creation and annotation, diagnostic accuracy, computational efficiency, and real-time implementation are considered under both controlled and field conditions. Factors such as varying illumination, leaf transparency, background complexity, environmental variation, and diseases in the agricultural environment influence model robustness and generalization. It also discusses the limited dataset diversity, underrepresented disease categories, imbalanced evaluation protocols, and heavy reliance on benchmark datasets, which pose challenges for the comparison of studies. Finally, this review addresses how IoT infrastructure, distributed sensor networks, edge intelligence, and continuous field monitoring systems can potentially increase diagnostic reliability and enable large-scale deep learning applications.
No takes yet. Share an insight, caveat, or question.
Abbas et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: