Scholarlink

<p><i>Eichhornia crassipes</i> (water hyacinth) is globally recognized as an invasive species that adversely threatens freshwater ecosystems, ecological health, and economic stability. Its rapid proliferation obstructs waterways, reduces oxygen levels, and disrupts native biodiversity. In response to these challenges, researchers have increasingly adopted advanced computation techniques such as machine learning (ML), deep learning (DL), remote sensing (RS), and hybrid approaches for the detection and monitoring of this species. This systematic review critically examines research published between 2012 and 2025, focusing on three core dimensions: the detection and monitoring techniques employed, the datasets used, and the performance metrics used to evaluate model effectiveness. A total of 74 peer-reviewed articles were analyzed from leading scientific databases. The review identifies key trends, including the increasing use of deep learning models between 2023 and 2025 and the variation in evaluation metrics across primary studies. Additionally, this study highlights the current limitations in dataset availability and the standardization of evaluation metrics. The findings aim to inform future research directions, promote methodological consistency, and support the development of robust, scalable strategies for the environmental monitoring of aquatic invasive species.</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

Advancements in the detection of invasive water hyacinth (Eichhornia crassipes): a critical review of monitoring techniques for aquatic ecosystem management

  • 期刊论文

  • 发表日期：

    2026年1月27日

查看全文
  • Richard Mkechera,
  • Sonika Dahiya

摘要

Eichhornia crassipes (water hyacinth) is globally recognized as an invasive species that adversely threatens freshwater ecosystems, ecological health, and economic stability. Its rapid proliferation obstructs waterways, reduces oxygen levels, and disrupts native biodiversity. In response to these challenges, researchers have increasingly adopted advanced computation techniques such as machine learning (ML), deep learning (DL), remote sensing (RS), and hybrid approaches for the detection and monitoring of this species. This systematic review critically examines research published between 2012 and 2025, focusing on three core dimensions: the detection and monitoring techniques employed, the datasets used, and the performance metrics used to evaluate model effectiveness. A total of 74 peer-reviewed articles were analyzed from leading scientific databases. The review identifies key trends, including the increasing use of deep learning models between 2023 and 2025 and the variation in evaluation metrics across primary studies. Additionally, this study highlights the current limitations in dataset availability and the standardization of evaluation metrics. The findings aim to inform future research directions, promote methodological consistency, and support the development of robust, scalable strategies for the environmental monitoring of aquatic invasive species.