Scholarlink

<p>Ensuring sustainable water use and safeguarding public health require continuous monitoring of water quality, particularly in rural and underserved regions. However, real-world water quality classification is significantly challenged by severe multiclass class imbalance, where infrequent but critical contamination events, such as extreme pollutant levels, are vastly underrepresented in the training data. This imbalance biases models toward majority classes, drastically reducing their sensitivity to rare yet hazardous conditions and ultimately compromising early warning capabilities, thereby increasing public health and environmental risks. To effectively address this issue, a deep ensemble framework, DNN-CW-BBAG (Deep Neural Network-Class Weights-Balanced Bagging), is proposed that combines class weighting with balanced bagging, offering both scalability and robustness. The model is developed using sensor data from the rural drinking water system in Heingang, Manipur. This study classifies water quality into five categories based on the Indian Water Quality Index (WQI). The proposed model attained an overall accuracy of 99.1% and achieved a 5.1% improvement in recall for rare classes compared to the average of the baseline algorithms, highlighting its effectiveness in detecting rare contamination events. While previous studies have suggested deep learning (DL) or ensemble methods independently for water quality analysis, this study integrates both to develop a practically viable solution tailored for real-world imbalance scenarios. The model’s generalization ability was validated using a separate dataset from Lalpura, Rajasthan, where it maintained good predictive performance, reinforcing its adaptability across geographically diverse regions. The proposed framework supports informed decision-making for risk management, community-level conservation, and sustainable water usage, directly contributing to Clean Water and Sanitation.</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

Enhancing Rural Water Conservation Through Deep Learning Based Multi-Class Water Quality Classification

  • 期刊论文

  • 发表日期：

    2026年1月10日

查看全文
  • Manjusha Nambiar PV,
  • Arpita Gupta,
  • Giridhar Urkude

摘要

Ensuring sustainable water use and safeguarding public health require continuous monitoring of water quality, particularly in rural and underserved regions. However, real-world water quality classification is significantly challenged by severe multiclass class imbalance, where infrequent but critical contamination events, such as extreme pollutant levels, are vastly underrepresented in the training data. This imbalance biases models toward majority classes, drastically reducing their sensitivity to rare yet hazardous conditions and ultimately compromising early warning capabilities, thereby increasing public health and environmental risks. To effectively address this issue, a deep ensemble framework, DNN-CW-BBAG (Deep Neural Network-Class Weights-Balanced Bagging), is proposed that combines class weighting with balanced bagging, offering both scalability and robustness. The model is developed using sensor data from the rural drinking water system in Heingang, Manipur. This study classifies water quality into five categories based on the Indian Water Quality Index (WQI). The proposed model attained an overall accuracy of 99.1% and achieved a 5.1% improvement in recall for rare classes compared to the average of the baseline algorithms, highlighting its effectiveness in detecting rare contamination events. While previous studies have suggested deep learning (DL) or ensemble methods independently for water quality analysis, this study integrates both to develop a practically viable solution tailored for real-world imbalance scenarios. The model’s generalization ability was validated using a separate dataset from Lalpura, Rajasthan, where it maintained good predictive performance, reinforcing its adaptability across geographically diverse regions. The proposed framework supports informed decision-making for risk management, community-level conservation, and sustainable water usage, directly contributing to Clean Water and Sanitation.