Scholarlink

<p>Groundwater is eventually undermined by human activities, such as rapid industrialization, urbanization, over-extraction, and contamination from agricultural and urban sources. Among the different contaminants, the presence of minerals such as calcium (Ca), magnesium (Mg), sodium (Na), potassium (K), fluoride (F), and chloride (Cl) proves to have serious health risks when present in excess concentrations. This study addresses this gap by developing a predictive machine learning model to evaluate the groundwater quality index (GWQI) and to identify the critical contaminants affecting water safety. A total of 1989 groundwater samples were collected from Jajpur district, where the Sukinda Valley is located, and analyzed for multiple physicochemical parameters, as this region is known for extensive chromite mining activities and has been identified as one of the most critically polluted areas in India, posing significant groundwater contamination risks. This study introduces the novel hybrid machine learning model, LCBoost fusion, which distinguishes this work from previous studies by combining the strengths of CatBoost and LightGBM to enhance predictive accuracy. It has been achieved with the help of a hybrid machine learning model i.e. LCBoost fusion. The model outperforms individual models (CatBoost and LightGBM), by achieving low RMSE (0.6826), MSE (0.5100), MAE (0.3148) and a high <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\textrm{R}^2\)</EquationSource> </InlineEquation> score of 0.9810. Feature importance analysis highlights potassium (K), fluoride (F) and total hardness (TH) as the most influential indicators of groundwater contamination. This research successfully demonstrates the application of machine learning in assessing groundwater quality risks in Odisha, with practical implications for real-time groundwater monitoring and risk mitigation. LCBoost Fusion model offers a reliable and efficient approach for real-time groundwater monitoring and risk mitigation. These findings will help environmental organizations and policy makers to map out targeted places for sustainable groundwater 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

Prediction of groundwater quality assessment by integrating boosted learning with DE optimizer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月1日

查看全文
  • Sonalika Subudhi,
  • Alok Kumar Pati,
  • Sephali Bose,
  • Subhasmita Sahoo,
  • Avipsa Pattanaik,
  • Biswa Mohan Acharya,
  • Rakesh Ranjan Thakur

摘要

Groundwater is eventually undermined by human activities, such as rapid industrialization, urbanization, over-extraction, and contamination from agricultural and urban sources. Among the different contaminants, the presence of minerals such as calcium (Ca), magnesium (Mg), sodium (Na), potassium (K), fluoride (F), and chloride (Cl) proves to have serious health risks when present in excess concentrations. This study addresses this gap by developing a predictive machine learning model to evaluate the groundwater quality index (GWQI) and to identify the critical contaminants affecting water safety. A total of 1989 groundwater samples were collected from Jajpur district, where the Sukinda Valley is located, and analyzed for multiple physicochemical parameters, as this region is known for extensive chromite mining activities and has been identified as one of the most critically polluted areas in India, posing significant groundwater contamination risks. This study introduces the novel hybrid machine learning model, LCBoost fusion, which distinguishes this work from previous studies by combining the strengths of CatBoost and LightGBM to enhance predictive accuracy. It has been achieved with the help of a hybrid machine learning model i.e. LCBoost fusion. The model outperforms individual models (CatBoost and LightGBM), by achieving low RMSE (0.6826), MSE (0.5100), MAE (0.3148) and a high \(\textrm{R}^2\) score of 0.9810. Feature importance analysis highlights potassium (K), fluoride (F) and total hardness (TH) as the most influential indicators of groundwater contamination. This research successfully demonstrates the application of machine learning in assessing groundwater quality risks in Odisha, with practical implications for real-time groundwater monitoring and risk mitigation. LCBoost Fusion model offers a reliable and efficient approach for real-time groundwater monitoring and risk mitigation. These findings will help environmental organizations and policy makers to map out targeted places for sustainable groundwater management.