Scholarlink

<p>Timely identification and categorization of crop diseases are crucial for ensuring food security and promoting sustainable agricultural practices to prevent such illnesses. Crop disease recognition is important in agricultural information extraction because it provides valuable data support for later knowledge services and retrieval. Categorization of crop diseases play a vital role in safeguarding food security and sustainable agricultural practices. This paper presents a new hybrid architecture of LSTM and CNN networks for the automatic detection and classification of crop diseases. We compare the proposed model to the best deep learning models on PlantVillage, Embrapa, Rice and Apple datasets. The proposed approach delivers an extensive evaluation of the advantages and drawbacks of several deep learning methodologies in crop disease diagnosis, furnishing significant insights for forthcoming research in precision agriculture. The comparison analysis indicates that the proposed CNN-LSTM model surpasses existing models in accuracy, F1-score precision and recall particularly in addressing intricate illness patterns and fluctuating environmental variables.</p>

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

Identification and classification of automated crop diseases using a novel CNN and LSTM model

  • 期刊论文

  • 发表日期：

    2025年10月27日

查看全文
  • Avjeet Singh,
  • Ranveer Singh

摘要

Timely identification and categorization of crop diseases are crucial for ensuring food security and promoting sustainable agricultural practices to prevent such illnesses. Crop disease recognition is important in agricultural information extraction because it provides valuable data support for later knowledge services and retrieval. Categorization of crop diseases play a vital role in safeguarding food security and sustainable agricultural practices. This paper presents a new hybrid architecture of LSTM and CNN networks for the automatic detection and classification of crop diseases. We compare the proposed model to the best deep learning models on PlantVillage, Embrapa, Rice and Apple datasets. The proposed approach delivers an extensive evaluation of the advantages and drawbacks of several deep learning methodologies in crop disease diagnosis, furnishing significant insights for forthcoming research in precision agriculture. The comparison analysis indicates that the proposed CNN-LSTM model surpasses existing models in accuracy, F1-score precision and recall particularly in addressing intricate illness patterns and fluctuating environmental variables.