Scholarlink

<p>This study investigates spatial, seasonal, and zonal variation of water quality parameters in the upper and middle zones of the Ganga River, India, with a focus on the influence by dams and barrages. Trophic status assessment using the trophic state index (TSI), trophic level index (TLI), and the trophic state index for tropical/subtropical water (TSItsr) revealed elevated eutrophication in the middle zone largely associated with nutrient influx and reduced flow. Statistical and machine learning approaches, including Multiple Linear Regression (MLR), Random Forest Model (RFM) and Gaussian Mixture Model (GMM) were employed to identify key drivers of chlorophyll-a (chl-a). Results showed significant spatial and seasonal variability, with both MLR and RF consistently identifying available phosphorus as the primary determinant of chl-a dynamics due to nutrient influx from agricultural runoff and reduced water flow. GMM distinguished two trophic clusters, with significant differences in TSItsr (p &lt; 0.05). These finding underscore the ecological impact of dams and barrages on nutrient dynamics and eutrophication risk, emphasizing the need for targeted nutrient management and sustainable water governance in the Ganga River.</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

Advanced Machine Learning and Statistical Modelling for the Assessment of Water Quality and Trophic Dynamics in the Upper and Middle Ganga River Basin

  • 期刊论文

  • 发表日期：

    2025年12月17日

查看全文
  • Jeetendra Kumar,
  • Basanta Kumar Das,
  • Asha T. Langde,
  • Absar Alam,
  • Ajoy Saha,
  • Shashi Bhusan,
  • Vikas Kumar,
  • Rayees Ahmad Bhatt,
  • Simanku Borah,
  • Nitesh Kumar Sharma

摘要

This study investigates spatial, seasonal, and zonal variation of water quality parameters in the upper and middle zones of the Ganga River, India, with a focus on the influence by dams and barrages. Trophic status assessment using the trophic state index (TSI), trophic level index (TLI), and the trophic state index for tropical/subtropical water (TSItsr) revealed elevated eutrophication in the middle zone largely associated with nutrient influx and reduced flow. Statistical and machine learning approaches, including Multiple Linear Regression (MLR), Random Forest Model (RFM) and Gaussian Mixture Model (GMM) were employed to identify key drivers of chlorophyll-a (chl-a). Results showed significant spatial and seasonal variability, with both MLR and RF consistently identifying available phosphorus as the primary determinant of chl-a dynamics due to nutrient influx from agricultural runoff and reduced water flow. GMM distinguished two trophic clusters, with significant differences in TSItsr (p < 0.05). These finding underscore the ecological impact of dams and barrages on nutrient dynamics and eutrophication risk, emphasizing the need for targeted nutrient management and sustainable water governance in the Ganga River.