A decade of progress across four interconnected frontiers is synthesizes the evolution of deep learning architectures for plant disease detection, the adaptation of foundation models including CLIP, SAM, and DINOv2 to agricultural contexts, and the development of multimodal fusion frameworks integrating imagery, environmental, genomic, and hyperspectral data are synthesized.
Abstract
Plant diseases destroy 20–40% of global food production annually, posing a critical threat to food security for a projected population of 9.7 billion by 2050. Conventional diagnostic approaches relying on expert visual assessment are slow, costly, and unsuitable for modern agricultural scales. While deep convolutional neural networks demonstrated early promise, single-modality, image-centric systems consistently fail under real-world field conditions characterized by variable lighting, co-occurring infections, and cultivar diversity. This review synthesizes a decade of progress across four interconnected frontiers: the evolution of deep learning architectures for plant disease detection; the adaptation of foundation models including CLIP, SAM, and DINOv2 to agricultural contexts; the development of multimodal fusion frameworks integrating imagery, environmental, genomic, and hyperspectral data; and the transition from static disease diagnosis to descriptive comparison of reported metrics, which suggested that multimodal approaches frequently reported improved diagnostic performance relative to corresponding single-modality baselines, although direct cross-study comparison was limited by methodological heterogeneity. A systematic review following PRISMA guidelines identifies eligible comparative studies. Descriptive comparison of reported performance metrics across these studies indicated that multimodal approaches generally achieved higher accuracy and sensitivity than single-modality models, particularly for pre-symptomatic disease detection. Eight critical research gaps are identified, including the absence of a unified agricultural foundation model and limited climate-aware forecasting under non-stationary climate projections. A structured research agenda is proposed to accelerate translation from laboratory performance to globally equitable, field-deployable crop protection systems.
The multimodal fusion framework is introduced to overcome the limitations of unimodal approaches and integrates the most appropriate data sources, thus allowing the earliest and most accurate detection of plant pathogens.
M. T. Qasim, L. A. Hameed, Zainab I. Mohammed et al.· Current Applied Science and...· 0 citations
It is suggested that in order to be implementable in the field, future intelligent agricultural diagnosis systems must be able to balance predictive accuracy, explainability, computational efficiency and field adaptability.
Usman Haruna· Research Journal of Pure Sci...· 0 citations
Potato leaf disease poses a significant threat to global food security, causing substantial crop losses that jeopardise agricultural productivity and farmers’ livelihoods worldwide. Existing automated detection frameworks suffer from several persistent limitations, including over-reliance on controlled benchmark datasets, narrow disease class coverage, exclusive use of spatial feature representations, absence of feature selection, and dependence on single-architecture end-to-end pipelines. To address these limitations, this paper proposes ComPo-Net, a novel lightweight ensemble framework that integrates three efficient CNN architectures—ResNet18, ShuffleNet, and MobileNetV2—for nine-class potato leaf disease detection and classification. Deep features are extracted from three intermediate layers of each network, with the Discrete Wavelet Transform applied for dimensionality reduction and cross-network fusion of the higher-dimensional layer features, capturing spectral–spatial information that purely spatial approaches cannot provide, while the remaining layer features are directly concatenated across networks. One-way Analysis of Variance (ANOVA) feature selection is subsequently applied to retain the most statistically significant features from the combined multi-scale, multi-network representation, and seven machine learning classifiers are systematically evaluated to identify the optimal classification strategy. The framework is assessed on a merged dataset of three publicly available benchmarks spanning both controlled and uncontrolled imaging environments, constituting a nine-class evaluation setting not previously addressed at this scale in the literature. ComPo-Net achieves an accuracy of 96.32%, an F1-score of 93.87%, an MCC of 0.9350, and AUC values exceeding 0.993 across all nine classes with Cubic SVM as the best-performing classifier. When compared against methods evaluated on the seven-class uncontrolled-environment dataset—the closest available task setting to ComPo-Net’s nine-class merged benchmark—ComPo-Net surpasses the best-performing comparable method by a margin of 6.45 percentage points, demonstrating the effectiveness of multi-scale ensemble feature extraction combined with spectral–spatial representation and principled feature selection for robust potato leaf disease detection under diverse real-world conditions.
A complete assessment framework is presented that goes beyond traditional accuracy-based metrics and includes analysis related to confidence calibration and temporal consistency, as well as out-of-distribution robustness and adversarial stability, as well as out-of-distribution robustness and adversarial stability.
K. Naveen, D. Ajitha· Applied Fruit Science· 0 citations
Citrus crops are economically vital worldwide, yet they remain highly susceptible to a range of infectious diseases that cause considerable yield and quality losses each year. Early and accurate disease identification is fundamental to sustainable orchard management and food security. Over the past decade, deep learning has emerged as the dominant paradigm for automated plant disease detection, surpassing traditional image-processing pipelines in both accuracy and scalability. This paper presents a comprehensive review of deep learning methodologies applied to citrus disease detection, covering convolutional neural networks (CNNs), attention mechanisms, lightweight architectures, object detection frameworks, multimodal fusion, and edge-computing deployment. Recent studies are critically analyzed with respect to model architecture, dataset characteristics, performance metrics, and deployment context. The review identifies prevailing trends including the shift toward lightweight models for edge devices, the integration of attention modules for fine-grained feature capture, and the growing adoption of multimodal and transformer-based approaches. Key open challenges such as limited data diversity, computational constraints in field deployments, and the need for domain-adaptive models are also discussed, along with prospective research directions. The findings serve as a reference for researchers and practitioners seeking to develop robust, real-time citrus disease detection systems.
Aniket K. Shahade, Vishal Jain, G. Manteghi et al.· 2026 International Conferenc...· 0 citations
Two deep learning models, a custom CNN model and a transfer learning model based on the DenseNet-121 architecture are presented, showing that the developed transfer learning model based on DenseNet-121 had superior performance over the CNN model.
H. Jeiad, S. Samaan, Omar Janeh et al.· Automation· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
