EUVIMEDEUVIMED entdecken
Crossref

Deep Learning–Driven Rice Leaf Blast Detection and Severity Classification Using Attention-Enhanced Convolutional Networks

International Research Journal of Modernization in Engineering Technology & Science · 18.05.2026

DOI: 10.56726/irjmets98188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Research Journal of Modernization in Engineering Technology & Science, online erschienen am 18.05.2026.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rice leaf blast disease, caused by the fungal pathogen Magnaporthe oryzae, remains one of the most destructive threats to global rice production, significantly affecting crop yield, food security, and agricultural sustainability.Traditional disease diagnosis methods largely depend on manual field inspection, which is labor-intensive, subjective, and often incapable of providing timely and accurate severity assessment under diverse environmental conditions.To address these limitations, this study proposes a deep learning-driven framework for automated rice leaf blast detection and severity classification using attention-enhanced convolutional neural networks (CNNs).The proposed model integrates advanced spatial and channel attention mechanisms within a deep convolutional architecture to enhance feature extraction from complex leaf textures, lesion patterns, and color variations.By emphasizing disease-relevant regions while suppressing background noise, the attention-guided network significantly improves classification robustness and interpretability.The framework employs extensive image preprocessing, data augmentation, and transfer learning strategies to optimize model generalization across heterogeneous field datasets.Multiple severity stages of rice leaf blast are categorized to facilitate precise disease progression monitoring and early intervention.Experimental evaluation demonstrates that the proposed attention-enhanced CNN outperforms conventional CNN architectures and machine learning classifiers in terms of accuracy, precision, recall, F1-score, and computational efficiency.Furthermore, Grad-CAM-based visualization techniques are incorporated to provide explainable insights into the decision-making process of the network, thereby increasing transparency and trustworthiness in agricultural applications.The results indicate that the proposed system can serve as an intelligent and scalable solution for precision agriculture by enabling rapid disease identification and severity estimation in real-time farming environments.The integration of attention-driven deep learning models with smart agricultural monitoring systems has the potential to minimize crop losses, reduce excessive pesticide usage, and support sustainable rice cultivation practices.This research contributes to the advancement of AIenabled plant pathology by establishing a reliable framework for automated disease diagnosis and severity assessment in modern agricultural ecosystems.

Zitieren

APA

(2026). Deep Learning–Driven Rice Leaf Blast Detection and Severity Classification Using Attention-Enhanced Convolutional Networks. International Research Journal of Modernization in Engineering Technology & Science. https://doi.org/10.56726/irjmets98188

Vancouver

Deep Learning–Driven Rice Leaf Blast Detection and Severity Classification Using Attention-Enhanced Convolutional Networks. International Research Journal of Modernization in Engineering Technology & Science. 2026. doi:10.56726/irjmets98188

BibTeX
@article{euvimed2026,
  title = {Deep Learning–Driven Rice Leaf Blast Detection and Severity Classification Using Attention-Enhanced Convolutional Networks},
  journal = {International Research Journal of Modernization in Engineering Technology & Science},
  year = {2026},
  doi = {10.56726/irjmets98188}
}
Kostenlos starten →