Scholarlink

To address the growing challenges of plant diseases and their impact on global food security, this study presents an innovative AI-driven workflow for disease detection and management. Leveraging the Plant Village dataset, our approach combines image classification, information retrieval, and response generation to provide actionable insights for farmers. The proposed system employs a hybrid VGG16/VGG19 model, achieving 96.12% accuracy in disease identification, alongside a fine-tuned BLIP model for symptom captioning. Language models, such as Mistral-Small-3.1-24B-Instruct, further enhance response quality, demonstrating a Faithfulness score of 0.6085. While the method shows robustness. This scalable solution aims to reduce crop losses (estimated at 20–40% annually) and minimize reliance on chemical pesticides, supporting sustainable agricultural practices in vulnerable regions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Plant Diseases Detection with Retrieval-Augmented Generation

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Outhmane Bourkoukou,
  • Khadija Ghommat

摘要

To address the growing challenges of plant diseases and their impact on global food security, this study presents an innovative AI-driven workflow for disease detection and management. Leveraging the Plant Village dataset, our approach combines image classification, information retrieval, and response generation to provide actionable insights for farmers. The proposed system employs a hybrid VGG16/VGG19 model, achieving 96.12% accuracy in disease identification, alongside a fine-tuned BLIP model for symptom captioning. Language models, such as Mistral-Small-3.1-24B-Instruct, further enhance response quality, demonstrating a Faithfulness score of 0.6085. While the method shows robustness. This scalable solution aims to reduce crop losses (estimated at 20–40% annually) and minimize reliance on chemical pesticides, supporting sustainable agricultural practices in vulnerable regions.