Scholarlink

Maintaining the purity of groundwater is essential to protecting the environment and the safety of people. Nonetheless, there are frequently issues with criterion choosing, geographical coverage, and adaptability with the traditional drinking water quality indexes. Responsive approaches to leadership and high precision are made possible by the prospective methodology change of integrating machine learning and geographical assessment. The areas where groundwater is not supplied a groundwater Quality Index (GQI) is employed to evaluate the potable groundwater quality across Madhya Pradesh utilizing large dataset having 13–15 water quality parameters. In this work total 8536 wells were evaluated and reveled 70%were not a good source of drinking water. The neural network approach gained a significantly high prediction of water quality nearby 95% for GQI. Forecasting precision for irregularly dispersed specimens of groundwater was improved by combining artificial intelligence techniques with geographic assessment. This study demonstrates a scientifically sound, multidisciplinary strategy with important ramifications for a framework for managing the condition of groundwater and susceptibility in future.

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

Groundwater Quality Index Prediction to Assessment for Drinkability Through Machine-Learning Approach with Geospatial Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Onkar Nath Thakur,
  • Santosh Kumar,
  • Nitesh Singh Bhati

摘要

Maintaining the purity of groundwater is essential to protecting the environment and the safety of people. Nonetheless, there are frequently issues with criterion choosing, geographical coverage, and adaptability with the traditional drinking water quality indexes. Responsive approaches to leadership and high precision are made possible by the prospective methodology change of integrating machine learning and geographical assessment. The areas where groundwater is not supplied a groundwater Quality Index (GQI) is employed to evaluate the potable groundwater quality across Madhya Pradesh utilizing large dataset having 13–15 water quality parameters. In this work total 8536 wells were evaluated and reveled 70%were not a good source of drinking water. The neural network approach gained a significantly high prediction of water quality nearby 95% for GQI. Forecasting precision for irregularly dispersed specimens of groundwater was improved by combining artificial intelligence techniques with geographic assessment. This study demonstrates a scientifically sound, multidisciplinary strategy with important ramifications for a framework for managing the condition of groundwater and susceptibility in future.