Scholarlink

<p>This systematic review examines the application of artificial intelligence (AI) in irrigation water quality (IWQ) assessment to meet the rising demand for efficient and sustainable agricultural water management. Previous reviews on this topic often lacked methodological rigor and comprehensive synthesis of AI techniques. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, an extensive search of major databases retrieved 281 articles, of which 43 met stringent quality criteria. Analysis of these studies reveals key trends, including the increasing use of hybrid and ensemble models, growing emphasis on model interpretability, integration with supporting technologies such as Geographic Information Systems (GIS) and the Internet of Things (IoT), and novel approaches for addressing data scarcity and class imbalance. Nevertheless, significant challenges remain, particularly the limited generalizability of models due to localized datasets, the absence of standardized irrigation water quality indices, and the lack of real-time monitoring and prediction systems. This review highlights critical research gaps and outlines future directions, offering a comprehensive synthesis of current knowledge on AI applications in IWQ assessment and their potential to advance sustainable agricultural practices.</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

Towards efficient artificial intelligence techniques for the assessment of irrigation water quality: a systematic literature review

  • 期刊论文

  • 发表日期：

    2025年10月1日

查看全文
  • Musa Mustapha,
  • Mhamed Zineddine,
  • Oluwadamilare Harazeem Abdulganiyu,
  • Yakub Kayode Saheed,
  • Ahmed El Hilali Alaoui

摘要

This systematic review examines the application of artificial intelligence (AI) in irrigation water quality (IWQ) assessment to meet the rising demand for efficient and sustainable agricultural water management. Previous reviews on this topic often lacked methodological rigor and comprehensive synthesis of AI techniques. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, an extensive search of major databases retrieved 281 articles, of which 43 met stringent quality criteria. Analysis of these studies reveals key trends, including the increasing use of hybrid and ensemble models, growing emphasis on model interpretability, integration with supporting technologies such as Geographic Information Systems (GIS) and the Internet of Things (IoT), and novel approaches for addressing data scarcity and class imbalance. Nevertheless, significant challenges remain, particularly the limited generalizability of models due to localized datasets, the absence of standardized irrigation water quality indices, and the lack of real-time monitoring and prediction systems. This review highlights critical research gaps and outlines future directions, offering a comprehensive synthesis of current knowledge on AI applications in IWQ assessment and their potential to advance sustainable agricultural practices.