Scholarlink

<p>Water insecurity is a growing sustainability challenge in arid regions, where climate variability and groundwater overexploitation threaten ecological stability and socio-economic development. In Eastern Saudi Arabia, groundwater is the primary freshwater source, yet integrated frameworks linking surface hydroclimatic stress with groundwater availability under future climate scenarios remain limited. This study aims to develop a climate-adaptive GeoAI framework to assess seasonal water risk and resilience by jointly evaluating surface drought indicators and groundwater potential. The framework integrates satellite-based Earth observation data, physically based hydrological variables, and a hybrid artificial neural network and long short-term memory model to predict reference evapotranspiration, actual evapotranspiration, and land surface temperature, and to analyze their relationship with groundwater potential zones. Applied across the Eastern Province using historical data and CMIP6 climate projections under SSP1-2.6, SSP2-4.5, and SSP5-8.5, the model demonstrates strong predictive performance with R² exceeding 0.95. Results indicate higher seasonal water risk during winter and spring, with resilience patterns more closely associated with groundwater potential than surface drought indicators. These findings highlight the critical role of groundwater resilience in sustainable water and land management under climate change.</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

Assessing water security, climate risk, and groundwater resilience for sustainable development in the Eastern Province of Saudi Arabia

  • 期刊论文

  • 发表日期：

    2026年4月30日

查看全文
  • Mahfuzur Rahman,
  • Md Anuwer Hossain,
  • Mohammed Benaafi,
  • Mahmudur Rahman,
  • Md Ahadul Islam Patwary,
  • Golden Odey,
  • Isam H. Aljundi

摘要

Water insecurity is a growing sustainability challenge in arid regions, where climate variability and groundwater overexploitation threaten ecological stability and socio-economic development. In Eastern Saudi Arabia, groundwater is the primary freshwater source, yet integrated frameworks linking surface hydroclimatic stress with groundwater availability under future climate scenarios remain limited. This study aims to develop a climate-adaptive GeoAI framework to assess seasonal water risk and resilience by jointly evaluating surface drought indicators and groundwater potential. The framework integrates satellite-based Earth observation data, physically based hydrological variables, and a hybrid artificial neural network and long short-term memory model to predict reference evapotranspiration, actual evapotranspiration, and land surface temperature, and to analyze their relationship with groundwater potential zones. Applied across the Eastern Province using historical data and CMIP6 climate projections under SSP1-2.6, SSP2-4.5, and SSP5-8.5, the model demonstrates strong predictive performance with R² exceeding 0.95. Results indicate higher seasonal water risk during winter and spring, with resilience patterns more closely associated with groundwater potential than surface drought indicators. These findings highlight the critical role of groundwater resilience in sustainable water and land management under climate change.