Scholarlink

Sugarcane is one of the most economical agri-crops but it is frequently infected by diverse diseases which hugely decrease yield and quality. Due to the very significant cost of Handel disease, timely and more accurate diagnosis of diseases is very important so that effective control measures can be implemented to minimize on economic losses submit Manage disease using Bioresources Technology with translation English you because Disease identity and recognition within time frame are required for successful management therefore thistle are become sooner after disease infection to be documented in detail. We are looking into DL methods like CNNs to address in this research. A CNN model was designed and trained on dataset with several thousand sugarcane leave images either healthy or disease affected plants. With stringent metrics for the evaluation of model performance, 89% accuracy was achieved in classifying sugarcane leaves as healthy or diseased using this model. This is indicative of the fairly high performance achievable by DL, providing a pathway for easily reproducible and accessible disease detection in agricultural practice. To narrow the divide between theoretical research and real-world implementation, a user-friendly, web-based platform was created. This tool allows farmers to upload images of their sugarcane plants for real-time disease diagnosis. By providing timely and accurate information, sugarcane farmers can now utilize this application to inform their decision-making processes for optimal disease control and prevention. Future research directions include the following: model refinement is incorporating user feedback to improve the model’s accuracy and robustness, disease diversity is expanding the model’s capabilities to identify a wider range of sugarcane diseases, integrated management is exploring the integration of disease detection with other agricultural factors, such as soil health, weather conditions, and pest control, to develop comprehensive management strategies, economic analysis is quantifying the economic benefits of using DL for disease diagnosis and management. The primary objective of this research is to foster the evolution of eco-friendly and productive sugarcane cultivation practices by exploring these critical aspects.

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

Accurate Sugarcane Disease Identification and Sustainable Crop Management via Ensemble Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ajay Pal Singh,
  • Harshit Sehgal,
  • Shivangi Gagneja,
  • Simranpreet Kaur,
  • Anish,
  • Aryan Pandey

摘要

Sugarcane is one of the most economical agri-crops but it is frequently infected by diverse diseases which hugely decrease yield and quality. Due to the very significant cost of Handel disease, timely and more accurate diagnosis of diseases is very important so that effective control measures can be implemented to minimize on economic losses submit Manage disease using Bioresources Technology with translation English you because Disease identity and recognition within time frame are required for successful management therefore thistle are become sooner after disease infection to be documented in detail. We are looking into DL methods like CNNs to address in this research. A CNN model was designed and trained on dataset with several thousand sugarcane leave images either healthy or disease affected plants. With stringent metrics for the evaluation of model performance, 89% accuracy was achieved in classifying sugarcane leaves as healthy or diseased using this model. This is indicative of the fairly high performance achievable by DL, providing a pathway for easily reproducible and accessible disease detection in agricultural practice. To narrow the divide between theoretical research and real-world implementation, a user-friendly, web-based platform was created. This tool allows farmers to upload images of their sugarcane plants for real-time disease diagnosis. By providing timely and accurate information, sugarcane farmers can now utilize this application to inform their decision-making processes for optimal disease control and prevention. Future research directions include the following: model refinement is incorporating user feedback to improve the model’s accuracy and robustness, disease diversity is expanding the model’s capabilities to identify a wider range of sugarcane diseases, integrated management is exploring the integration of disease detection with other agricultural factors, such as soil health, weather conditions, and pest control, to develop comprehensive management strategies, economic analysis is quantifying the economic benefits of using DL for disease diagnosis and management. The primary objective of this research is to foster the evolution of eco-friendly and productive sugarcane cultivation practices by exploring these critical aspects.