Scholarlink

<p>Global agriculture faces growing threats from pests, pathogens, and invasive species, intensified by climate change and biodiversity losses. Conventional approaches are limited in both precision and scale, and artificial intelligence (AI) is now reshaping integrated pest management (IPM). Modern agricultural monitoring leverages high-resolution observations, hyperspectral sensors, and the Internet of Things (IoT) to facilitate early detection for diseases. Hybrid AI systems can integrate multi-source data to enhance the accuracy of real-time monitoring of pest and disease dynamics, including the detection and tracking of sparse invasive populations and their biomass even under shifting climate scenarios. They further enable predictive forecasting and the optimization of management strategies. When AI-driven diagnostics are integrated with autonomous robotics, they form a robust framework for epidemic mitigation. Here, we provide a systematic macro-perspective review, bridging foundational AI mechanisms with actionable IPM intelligence. We analyze the evolution of agricultural AI from cross-modal architectures to multi-scale diagnostics and full-lifecycle interventions. Finally, we propose a framework for the global agroecological network, offering a sustainable path toward maximizing productivity while ensuring ecological resilience.</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

From detection to action: artificial intelligence in integrated pest and invasive plant management

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月8日

查看全文
  • Yaoxing Li,
  • Lianming Zha,
  • Weitong Liu,
  • Feng Luo,
  • Chenyang Xu

摘要

Global agriculture faces growing threats from pests, pathogens, and invasive species, intensified by climate change and biodiversity losses. Conventional approaches are limited in both precision and scale, and artificial intelligence (AI) is now reshaping integrated pest management (IPM). Modern agricultural monitoring leverages high-resolution observations, hyperspectral sensors, and the Internet of Things (IoT) to facilitate early detection for diseases. Hybrid AI systems can integrate multi-source data to enhance the accuracy of real-time monitoring of pest and disease dynamics, including the detection and tracking of sparse invasive populations and their biomass even under shifting climate scenarios. They further enable predictive forecasting and the optimization of management strategies. When AI-driven diagnostics are integrated with autonomous robotics, they form a robust framework for epidemic mitigation. Here, we provide a systematic macro-perspective review, bridging foundational AI mechanisms with actionable IPM intelligence. We analyze the evolution of agricultural AI from cross-modal architectures to multi-scale diagnostics and full-lifecycle interventions. Finally, we propose a framework for the global agroecological network, offering a sustainable path toward maximizing productivity while ensuring ecological resilience.