Scholarlink

<p>Groundwater over-extraction threatens water sustainability in rain shadow villages in Koregaon taluka, Satara, India. This creates supply-demand gaps and stakeholder conflicts amid erratic monsoons. Traditional methods lack participatory and actionable tools for Village Water Committees (VWSCs) and farmers.​ This paper presents a Digital Twin of Groundwater (DToGW) experiment integrating 27 years of CGWB seasonal depth-to-water (DTW) records, rainfall data, and basaltic aquifer traits into a predictive governance-oriented dashboard, enabling a unified decision-support framework. Unlike a conventional groundwater prediction model, the proposed DToGW is defined here as a dynamic, updateable, and decision-coupled virtual representation of the aquifer system that combines data ingestion, predictive simulation, scenario testing, visualization, and advisory feedback for village institutions. AIML models, Random Forest and LSTM, achieved RMSE 0.26–0.55&#xa0;m and <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\:{R}^{2}\)</EquationSource> </InlineEquation> 0.89–0.91 on test data.​ The approach involves data imputation, lag selection, spatial interpolation uncertainty, deterministic prediction limits, besides governance safeguards for the study-area, socio-hydrological feedbacks, and institutional constraints. The framework enables monthly DTW forecasts supporting scenario simulation, drought-tolerant cropping, and recharge planning to curb over-extraction. DToGW empowers rural stakeholders for a participatory governance through water substitution advisories, resource efficiency through scenario-based demand management, and reduced pumping in stressed zones to optimize the water-energy nexus.​ The study advances AI-enabled water governance not only by improving prediction, but by translating sparse hydro-meteorological records into transparent, participatory, and locally actionable governance intelligence aligned with SDG 6, SDG 12, and climate adaptation goals.</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

A Digital Twin of Groundwater for Village Water Governance

  • 期刊论文

  • 发表日期：

    2026年4月20日

查看全文
  • Dineshkumar Singh,
  • Vishnu Sharma

摘要

Groundwater over-extraction threatens water sustainability in rain shadow villages in Koregaon taluka, Satara, India. This creates supply-demand gaps and stakeholder conflicts amid erratic monsoons. Traditional methods lack participatory and actionable tools for Village Water Committees (VWSCs) and farmers.​ This paper presents a Digital Twin of Groundwater (DToGW) experiment integrating 27 years of CGWB seasonal depth-to-water (DTW) records, rainfall data, and basaltic aquifer traits into a predictive governance-oriented dashboard, enabling a unified decision-support framework. Unlike a conventional groundwater prediction model, the proposed DToGW is defined here as a dynamic, updateable, and decision-coupled virtual representation of the aquifer system that combines data ingestion, predictive simulation, scenario testing, visualization, and advisory feedback for village institutions. AIML models, Random Forest and LSTM, achieved RMSE 0.26–0.55 m and \(\:{R}^{2}\) 0.89–0.91 on test data.​ The approach involves data imputation, lag selection, spatial interpolation uncertainty, deterministic prediction limits, besides governance safeguards for the study-area, socio-hydrological feedbacks, and institutional constraints. The framework enables monthly DTW forecasts supporting scenario simulation, drought-tolerant cropping, and recharge planning to curb over-extraction. DToGW empowers rural stakeholders for a participatory governance through water substitution advisories, resource efficiency through scenario-based demand management, and reduced pumping in stressed zones to optimize the water-energy nexus.​ The study advances AI-enabled water governance not only by improving prediction, but by translating sparse hydro-meteorological records into transparent, participatory, and locally actionable governance intelligence aligned with SDG 6, SDG 12, and climate adaptation goals.