Scholarlink

The goal of sustainable development (SD) is clean water management and sanitation. SD intends to improve the quality of life of people all over the world. The sanitation services depend on various factors such as groundwater level, hydraulics, and degree of contamination. Poor sanitation will affect health with various diseases such as diarrhea, typhoid etc.; in this chapter, machine learning (ML) algorithms are used to evaluate the water portability with various parameters, namely, hardness, solids, chloramines, sulfate, organic carbon, trihalomethanes, and turbidity. Various machine learning algorithms which include both classification and regression are used for analysis such as decision tree with Gini impurity, random forest KNN, K-means, and logistic regression. The performance is analyzed by making a comparative study with various ML algorithms. Experimental results show a random forest with the highest accuracy.

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

Water Quality Analysis for Better Sustainability Using Machine Learning Approach

  • 工具书词条

  • 发表日期：

    2026年

查看全文
  • A. K. Meeradevi,
  • B. J. Sowmya,
  • Anita Kanavalli,
  • Jagadish Kallimani

摘要

The goal of sustainable development (SD) is clean water management and sanitation. SD intends to improve the quality of life of people all over the world. The sanitation services depend on various factors such as groundwater level, hydraulics, and degree of contamination. Poor sanitation will affect health with various diseases such as diarrhea, typhoid etc.; in this chapter, machine learning (ML) algorithms are used to evaluate the water portability with various parameters, namely, hardness, solids, chloramines, sulfate, organic carbon, trihalomethanes, and turbidity. Various machine learning algorithms which include both classification and regression are used for analysis such as decision tree with Gini impurity, random forest KNN, K-means, and logistic regression. The performance is analyzed by making a comparative study with various ML algorithms. Experimental results show a random forest with the highest accuracy.