Scholarlink

<p>This study employs morphometric analysis integrated with machine learning (Random Forest) to delineate groundwater potential zones (GWPZs) in the Neyyar Basin. A total of 60 morphometric parameters, categorized under linear, areal, relief, and drainage texture aspects, were extracted using SRTM DEM (30&#xa0;m resolution) and analyzed to assess their influence on groundwater occurrence. Thematic layers such as geology, geomorphology, drainage density, lineament density, land use/land cover, soil type, slope, curvature, and rainfall were integrated with CGWB well yield and static water level data to train the Random Forest model. The results classified the basin into high (43.27%), moderate (21.78%), and low (34.96%) groundwater potential zones. High potential zones were observed in valleys, lower slopes, and fractured rock regions, where favorable infiltration and storage conditions enhance groundwater availability. Low potential zones were concentrated in steep terrains with high drainage density and low permeability, restricting recharge. The study confirms that morphometric parameters such as drainage density, bifurcation ratio, and relief characteristics are key indicators of groundwater occurrence, influencing infiltration, runoff, and storage capacity. By integrating detailed morphometric analysis with machine learning, this study enhances the accuracy of groundwater potential mapping, offering a robust approach for sustainable water resource management.</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

Spatial modelling of groundwater potential zones in the Neyyar Basin using machine learning and morphometric analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月16日

查看全文
  • R. J. Jerin Joe,
  • V. Stephen Pitchaimani,
  • S. Kaliraj,
  • S. Richard Abishek,
  • A. Antony Alosanai Promilton,
  • Shankar Karuppannan

摘要

This study employs morphometric analysis integrated with machine learning (Random Forest) to delineate groundwater potential zones (GWPZs) in the Neyyar Basin. A total of 60 morphometric parameters, categorized under linear, areal, relief, and drainage texture aspects, were extracted using SRTM DEM (30 m resolution) and analyzed to assess their influence on groundwater occurrence. Thematic layers such as geology, geomorphology, drainage density, lineament density, land use/land cover, soil type, slope, curvature, and rainfall were integrated with CGWB well yield and static water level data to train the Random Forest model. The results classified the basin into high (43.27%), moderate (21.78%), and low (34.96%) groundwater potential zones. High potential zones were observed in valleys, lower slopes, and fractured rock regions, where favorable infiltration and storage conditions enhance groundwater availability. Low potential zones were concentrated in steep terrains with high drainage density and low permeability, restricting recharge. The study confirms that morphometric parameters such as drainage density, bifurcation ratio, and relief characteristics are key indicators of groundwater occurrence, influencing infiltration, runoff, and storage capacity. By integrating detailed morphometric analysis with machine learning, this study enhances the accuracy of groundwater potential mapping, offering a robust approach for sustainable water resource management.