Scholarlink

<p>This review examines the application of boosting algorithms in surface water quality modeling across five domains: (1) rivers and streamflow, (2) agricultural applications and irrigation, (3) coastal waters, (4) reservoirs and lakes, and (5) wastewater. Of the 592 explored studies throughout this review from January 1, 2010, to September 1, 2025, 156 studies were scrutinized and analyzed after screening, exclusion, and retrieval. By the aid of a systematic PRISMA-guided search of Scopus, Web of Science, and Google Scholar, the applications of several commonly used and recent boosting algorithms like AdaBoost, CatBoost, LightGBM, SGBoost, gradient boosting, XGBoost, and NGBoost were examined for predicting physical, chemical, heavy metal, and biological water quality parameters. The primary outcome of this review demonstrates that XGBoost is the prominent, widely used, and most accurate algorithm, outperforming in 58% of comparative studies due to its scalability and regularization.</p><p><?noindent??><b>Clinical trial number</b> Not applicable.</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

Ensemble Boosting Methods for Surface Water Quality Modeling: A Review

  • 期刊论文

  • 发表日期：

    2025年10月3日

查看全文
  • Mohammad Zounemat-Kermani,
  • Marwan Kheimi

摘要

This review examines the application of boosting algorithms in surface water quality modeling across five domains: (1) rivers and streamflow, (2) agricultural applications and irrigation, (3) coastal waters, (4) reservoirs and lakes, and (5) wastewater. Of the 592 explored studies throughout this review from January 1, 2010, to September 1, 2025, 156 studies were scrutinized and analyzed after screening, exclusion, and retrieval. By the aid of a systematic PRISMA-guided search of Scopus, Web of Science, and Google Scholar, the applications of several commonly used and recent boosting algorithms like AdaBoost, CatBoost, LightGBM, SGBoost, gradient boosting, XGBoost, and NGBoost were examined for predicting physical, chemical, heavy metal, and biological water quality parameters. The primary outcome of this review demonstrates that XGBoost is the prominent, widely used, and most accurate algorithm, outperforming in 58% of comparative studies due to its scalability and regularization.

Clinical trial number Not applicable.