A comprehensive review of advances challenges and future directions in plant disease diagnosis using deep learning models

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.

Authors

Institutions

Publication Details

Journal
Discover Sustainability
Published
2026-11-14
DOI
https://doi.org/10.1007/s43621-026-04953-5
Primary Topic
Smart Agriculture and AI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A comprehensive review of advances challenges and future directions in plant disease diagnosis using deep learning models

Mohd Nadhir Ab Wahab, Osamah Mohammed Alyasiri, Mohd Azam Osman, Abdulsalam H. Abbas
Discover Sustainability
Smart Agriculture and AI
article

A comprehensive review of advances challenges and future directions in plant disease diagnosis using deep learning models

Mohd Nadhir Ab Wahab, Osamah Mohammed Alyasiri, Mohd Azam Osman, Abdulsalam H. Abbas
article en

Abstract

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.

Discover Sustainability
Universiti Sains Malaysia (MY), University of Kerbala (IQ), Al-Furat Al-Awsat Technical University (IQ)
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon