Aug 2026· International journal of computer information systems and industrial management applications· Vol 18, pp. 355-365· 0 citations
TL;DR
RICE-MuSTA is introduced, a framework designed to jointly address multimodality, severity estimation, and uncertainty in rice leaf disease monitoring, and compressing the model into a lightweight architecture suitable for mobile and edge deployment.
Abstract
Background: Rice is a staple food crop for more than half of the world’s population and plays a central role in food security, particularly in Asian and African countries. However, rice productivity is severely affected by foliar diseases such as rice blast, bacterial blight, sheath blight, and brown spot. Delayed or inaccurate diagnosis of these diseases can lead to yield losses ranging from 10–40%, directly impacting farmers’ livelihoods. While recent advances in deep learning have enabled automated leaf disease detection, most existing approaches remain limited to image-only classification, lack severity assessment, ignore environmental uncertainty, and are unsuitable for real-time field deployment Methods: In this work, we introduce RICE-MuSTA, a framework designed to jointly address multimodality, severity estimation, and uncertainty in rice leaf disease monitoring. The framework integrates leaf image features extracted using convolutional neural networks (CNNs), global contextual representations learned via Vision Transformers (ViTs), and microclimate information encoded through a multilayer perceptron (MLP). Findings: The proposed model simultaneously performs disease classification and severity estimation while quantifying predictive uncertainty and providing lesion-level explainability using CAM-based heatmaps. To enable practical adoption, a teacher–student distillation and quantization strategy is employed, compressing the model into a lightweight architecture suitable for mobile and edge deployment.Novelty and applications: Across multiple datasets and evaluation settings, we observed consistent improvements in robustness, interpretability, and deployment efficiency.
A scalable image-based framework for automatic rice leaf disease detection and monitoring using deep learning and cloud-enabled analytics and enables deployment on smartphones, drones, and edge devices for smart agriculture applications.
B Venkata Ramulu, Dr. Geeta Tripathi· International Journal of Eng...· 0 citations
Accurate detection of plant leaf diseases is essential for enhancing crop productivity and supporting global food security. In addition to disease classification, understanding how environmental and soil conditions affect model performance is important for developing robust real-world agricultural monitoring systems. Although deep learning (DL) models achieve high accuracy on benchmark datasets, their performance in real-world settings is often limited by variations in illumination, background complexity, and environmental conditions. This study proposes a smart DL framework for detecting and classifying multiple leaf diseases in tomato, potato, and pepper plants. The framework combines U2-Net-based leaf segmentation with a Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN–Bi-GRU) architecture. MobileNetV2 is employed as the feature extraction backbone to capture spatial characteristics, while Bi-GRU layers model sequential feature dependencies, forming a spatio-temporal network whose architectural design prioritizes parameter efficiency through depthwise separable convolutions and reduced gating complexity. The model was trained and validated using the PlantVillage benchmark dataset and achieved a classification accuracy of 99.8% with a macro-averaged F1-score of 94%, outperforming several state-of-the-art architectures. To assess robustness under real-world conditions, the trained model was further tested on leaf images collected from open-field environments near Eluru, South India. The field evaluation revealed a reduction in classification accuracy to 61.97%, indicating the impact of domain shift and environmental variability. To investigate potential contributing factors, soil parameters, including pH, temperature, moisture, and NPK levels, were monitored using an IoT-based Arduino sensing system over ten consecutive days. Rather than serving as direct inputs to the disease classification model, these environmental measurements were analyzed to assess their potential influence on disease symptom expression and the observed reduction in model performance under field conditions. The results suggest that environmental conditions may influence disease symptom expression and model transferability. This study highlights the importance of integrating DL-based disease recognition with environmental monitoring for reliable field-level agricultural applications. Nevertheless, computational complexity metrics, including inference latency and memory footprint, were not evaluated in the present work and are identified as a priority for future edge deployment studies.
J. Thirupathi, N. Malarvizhi, P. S. Brahmanandam· Sustainability· 0 citations
Performance evaluation using accuracy, model size, time per image, and number of parameters showed that the proposed model achieved high accuracy and provided better discrimination between visually similar disease classes.
Agriculture is a key component in ensuring food security in the world and one of the most common staple foods in the world is rice. But there are a number of leaf diseases affecting rice, like bacterial leaf blight, brown spot, and rice blast, which cause lower production yield. In order to limit economic losses, it is necessary to be able to diagnose these diseases on time. This paper presents an intelligent prediction and classification of rice leaf disease prediction and classification using deep learning and transfer learning approaches. For that purpose, the proposed model uses two pre-trained transfer learning models, DenseNet201 and EfficientNetB3, and a conventional CNN, to classify healthy and diseased rice leaves from a set of image data. The performances of the three models are measured using the following performance measures: accuracy, precision, recall, and F1-score. From the experiments conducted, it can be noted that the best performing model among all three models is the EfficientNetB3, which shows an excellent classification accuracy of 95%. It performs better than both DenseNet201, whose accuracy is 92% and CNN model, whose accuracy is 83.5%. The reason behind the excellent performance of the EfficientNetB3 is that the architecture of the model is optimized in such a way that it is able to extract the most discriminative features with less computational complexity. The proposed framework can offer an efficient, reliable, and automated solution for the early detection of the diseases in the leaves of rice crops.
Vandana Samanthula, N. Valli, Sultanov Sirojiddin et al.· 2026 6th International Confe...· 0 citations
This study introduces a hybrid deep learning architecture that integrates squeeze-and-excitation residual blocks, capsule networks, bidirectional long short-term memory, and attention mechanisms, enabling farmers to obtain rapid, reliable, and cost-effective field diagnoses, thereby improving agricultural productivity and sustainability.
Aekkarat Suksukont, Ekachai Naowanich· Journal of Advances in Infor...· 0 citations
Rice is the main staple food of Pakistan. The rising demand for rice, driven by population growth, is under threat by the bacterial diseases such as leaf blight, leaf blast, and brown spot. These diseases adversely affect rice production, reducing yield and threatening food security. Technological advancements, particularly in deep learning, offer opportunities to strengthen agricultural practices in countries like Pakistan. Early and accurate detection of these diseases is critical to ensuring food security and preventing potential shortages. In this research, we propose a novel pipeline for rice disease detection using a hybrid approach that integrates Generative Adversarial Networks (GANs) for data augmentation, Otsu thresholding for image preprocessing, and a deep learning model for classification. While existing models like Inception V3 and MobileNet V2 have shown promising results on training datasets, their performance diminishes on larger, more diverse datasets, due to overfitting and poor generalizations. Our proposed hybrid pipeline aims to address rice disease detection challenges by integrating (i) synthetic data generation using a Pix2Pix GAN to augment the dataset, (ii) a pre-processing stage employing Otsu thresholding on the augmented images to enhance features, and (iii) a final classification stage using an InceptionDenseNet model trained on the processed data. Our suggested approach achieved an accuracy of 86.98%, a significant improvement from the baseline accuracy of 74% obtained by the Inception DenseNet model on the original dataset. This enhancement demonstrates the effectiveness of the combined GAN-based augmentation and Otsu thresholding pre-processing.
Arshad Ali, Asad Ullah, M. Gulzar et al.· Discover Computing· 0 citations
