Scholarlink

Sugarcane diseases like red rot, yellow leaf disease, and white leaf disease pose significant threats to crop yield and economic stability in the agricultural sector. This review evaluates advancements in machine learning (ML) and deep learning (DL) techniques for detecting and managing these diseases. Total 20 peer-reviewed articles have been analyzed using the PREFERRED REPORTING ITEMS FOR SYSTEMATIC REVIEWS AND META-ANALYSES (PRISMA) framework, focusing on methodologies, performance metrics, and research gaps. Techniques such as Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and hybrid models have demonstrated high accuracy rates, with models like AlexNet and VGGNet achieving over 95% accuracy. Feature extraction methods, including Inception v3 and VGG-16, significantly enhanced model performance. Practical applications, such as mobile apps, highlight the real-world utility of these technologies. However, challenges remain in scalability, economic feasibility, and long-term sustainability. There is a need for comprehensive disease management frameworks and real-time monitoring systems. Future research should aim at integrating advanced technologies into scalable, cost-effective solutions and developing holistic strategies for disease management. Real-time systems using AI, sensors, and drones can provide timely interventions, reducing crop losses and improving sugarcane health and yield.

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

Review of Machine Learning and Deep Learning Methods for Effective Sugarcane Disease Detection

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Abhishek Singh,
  • Usha Mittal,
  • Priyanka Chawla

摘要

Sugarcane diseases like red rot, yellow leaf disease, and white leaf disease pose significant threats to crop yield and economic stability in the agricultural sector. This review evaluates advancements in machine learning (ML) and deep learning (DL) techniques for detecting and managing these diseases. Total 20 peer-reviewed articles have been analyzed using the PREFERRED REPORTING ITEMS FOR SYSTEMATIC REVIEWS AND META-ANALYSES (PRISMA) framework, focusing on methodologies, performance metrics, and research gaps. Techniques such as Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and hybrid models have demonstrated high accuracy rates, with models like AlexNet and VGGNet achieving over 95% accuracy. Feature extraction methods, including Inception v3 and VGG-16, significantly enhanced model performance. Practical applications, such as mobile apps, highlight the real-world utility of these technologies. However, challenges remain in scalability, economic feasibility, and long-term sustainability. There is a need for comprehensive disease management frameworks and real-time monitoring systems. Future research should aim at integrating advanced technologies into scalable, cost-effective solutions and developing holistic strategies for disease management. Real-time systems using AI, sensors, and drones can provide timely interventions, reducing crop losses and improving sugarcane health and yield.