Scholarlink

<p>Effective porosity and soil moisture are key elements in assessing groundwater recharge, which plays a vital role in the sustainable management of water resources. Precise determination of the hydrodynamic properties of the unsaturated zone is essential for enhancing predictive accuracy. This study introduces an innovative approach that combines ultrasonic waves and machine learning to efficiently and accurately estimate effective porosity and water content in the unsaturated zone, using the Merguellil Basin, located downstream of the El Houareb Dam in the Mediterranean Arid Zone of Central Tunisia, as a case study. Multiple soil samples were gathered from eight transverse sections along the Merguellil Wadi, where ultrasonic wave speeds were also recorded. Subsequently, machine learning was applied to create three predictive models for effective porosity and water content. The findings emphasize the impact of ultrasonic waves on effective porosity and water content in the subsurface, offering valuable insights for forecasting infiltration and groundwater recharge in the Basin. This research provides new perspectives on the application of machine learning to estimate hydrodynamic parameters of unsaturated zones, which is highly relevant for hydrologists and geophysicists working on groundwater recharge in arid regions.</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

Machine learning prediction of effective porosity and water content in unsaturated zones: application to the Merguellil Basin in the arid Mediterranean region of central Tunisia

  • 期刊论文

  • 发表日期：

    2026年1月8日

查看全文
  • Mohamed Abdelhedi,
  • Anis Ammari,
  • Dhouha Ben Othman,
  • Habib Abida,
  • Hakim Gabtni,
  • Chedly Abbes

摘要

Effective porosity and soil moisture are key elements in assessing groundwater recharge, which plays a vital role in the sustainable management of water resources. Precise determination of the hydrodynamic properties of the unsaturated zone is essential for enhancing predictive accuracy. This study introduces an innovative approach that combines ultrasonic waves and machine learning to efficiently and accurately estimate effective porosity and water content in the unsaturated zone, using the Merguellil Basin, located downstream of the El Houareb Dam in the Mediterranean Arid Zone of Central Tunisia, as a case study. Multiple soil samples were gathered from eight transverse sections along the Merguellil Wadi, where ultrasonic wave speeds were also recorded. Subsequently, machine learning was applied to create three predictive models for effective porosity and water content. The findings emphasize the impact of ultrasonic waves on effective porosity and water content in the subsurface, offering valuable insights for forecasting infiltration and groundwater recharge in the Basin. This research provides new perspectives on the application of machine learning to estimate hydrodynamic parameters of unsaturated zones, which is highly relevant for hydrologists and geophysicists working on groundwater recharge in arid regions.