Scholarlink

<p>Harmful algal blooms (HABs) pose escalating ecological, economic, and public health threats across global aquatic ecosystems. This study presents a comprehensive bibliometric analysis of the research landscape at the intersection of sensor technologies and artificial intelligence for HAB monitoring. Using 1278 peer-reviewed publications (2005–2024) retrieved from the Web of Science Core Collection and analyzed via CiteSpace, we explored publication trends, collaboration networks, keyword evolution, and citation bursts. The results reveal exponential growth in research output since 2019, with the USA and China leading in productivity and international collaboration. Thematic evolution has shifted from marine-focused remote sensing to AI-driven freshwater monitoring, emphasizing real-time sensing, multi-source data fusion, and early warning systems. Despite technical progress, key challenges persist, including data heterogeneity, limited model interpretability, and poor cross-regional transferability. This study outlines strategic directions—such as digital twin construction, physics-informed AI, and transfer learning—to guide the development of scalable, explainable, and climate-aware monitoring systems. By mapping the intellectual structure and emerging frontiers of this field, our findings provide a foundation for interdisciplinary innovation and evidence-based environmental governance.</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

Application of sensors and artificial intelligence in algal bloom monitoring: a knowledge map, research hotspots, and future trends based on CiteSpace

  • 期刊论文

  • 发表日期：

    2026年1月2日

查看全文
  • Xiangfa Wang

摘要

Harmful algal blooms (HABs) pose escalating ecological, economic, and public health threats across global aquatic ecosystems. This study presents a comprehensive bibliometric analysis of the research landscape at the intersection of sensor technologies and artificial intelligence for HAB monitoring. Using 1278 peer-reviewed publications (2005–2024) retrieved from the Web of Science Core Collection and analyzed via CiteSpace, we explored publication trends, collaboration networks, keyword evolution, and citation bursts. The results reveal exponential growth in research output since 2019, with the USA and China leading in productivity and international collaboration. Thematic evolution has shifted from marine-focused remote sensing to AI-driven freshwater monitoring, emphasizing real-time sensing, multi-source data fusion, and early warning systems. Despite technical progress, key challenges persist, including data heterogeneity, limited model interpretability, and poor cross-regional transferability. This study outlines strategic directions—such as digital twin construction, physics-informed AI, and transfer learning—to guide the development of scalable, explainable, and climate-aware monitoring systems. By mapping the intellectual structure and emerging frontiers of this field, our findings provide a foundation for interdisciplinary innovation and evidence-based environmental governance.