Scholarlink

The water, it is the second most important necessity for mankind after air, whole world is searching water in different planets. This research study explores the application of artificial neural networks (ANN) with the AdaBoost algorithm to predict groundwater quality in Kanpur, a city located in the Uttar Pradesh region of India. A total of twelve (12) groundwater samples were collected and analyzed to assess key physicochemical factors, such as pH, Total Dissolved Solids (TDS), Electrical Conductivity (EC), Chlorides (Cl), Calcium (Ca), Sodium (Na), Potassium (K), Magnesium (Mg), Sulfates (SO4), Phosphates (PO4), and Nitrates (NO3), both before and after the monsoon season. The water quality index (WQI) was calculated based on these parameters. The findings indicated that most factors fell within acceptable ranges, but EC, TDS, Total Hardness (TH), Ca, and Mg exceeded the standard limits as per WHO guidelines, potentially impacting the suitability of groundwater for drinking. To enhance the accuracy of groundwater quality predictions using the water quality index, a multi-layer backpropagation algorithm within an artificial neural network (ANN) was employed, with additional refinement from the AdaBoost algorithm. The results affirmed the ANN’s reliability in predicting the water quality, consistently delivering satisfactory results in all evaluated terms.

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

An Advanced Model to Predict Water Quality Index of Groundwater Using ANN and AdaBoost Algorithm

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mehtab Mehdi,
  • Bharti Sharma,
  • Usman Ali Khan,
  • Mohd. Sayeed Khan,
  • Ali Sirageldeen Ahmed

摘要

The water, it is the second most important necessity for mankind after air, whole world is searching water in different planets. This research study explores the application of artificial neural networks (ANN) with the AdaBoost algorithm to predict groundwater quality in Kanpur, a city located in the Uttar Pradesh region of India. A total of twelve (12) groundwater samples were collected and analyzed to assess key physicochemical factors, such as pH, Total Dissolved Solids (TDS), Electrical Conductivity (EC), Chlorides (Cl), Calcium (Ca), Sodium (Na), Potassium (K), Magnesium (Mg), Sulfates (SO4), Phosphates (PO4), and Nitrates (NO3), both before and after the monsoon season. The water quality index (WQI) was calculated based on these parameters. The findings indicated that most factors fell within acceptable ranges, but EC, TDS, Total Hardness (TH), Ca, and Mg exceeded the standard limits as per WHO guidelines, potentially impacting the suitability of groundwater for drinking. To enhance the accuracy of groundwater quality predictions using the water quality index, a multi-layer backpropagation algorithm within an artificial neural network (ANN) was employed, with additional refinement from the AdaBoost algorithm. The results affirmed the ANN’s reliability in predicting the water quality, consistently delivering satisfactory results in all evaluated terms.