Published Paper Details:

Water is the most crucial resource of life and it is necessary for the survival of all living creatures including human beings. The survival of business and agriculture depends on fresh water. An essential step in managing freshwater assets is the evaluation of the quality of the water. Before using water for anything, including drinking, chemical spraying (pesticides, etc.),or animal hydration , it is crucial to assess its purity. The ecosystem and the general public's health are directly impacted by water quality. Therefore, analyzing and predicting water quality is necessary for both environment and human protection. Machine learning can be used to analyze and predict the water quality based on the parameters like PH value, turbidity, hardness, conductivity, dissolved solids in water and others parameters as input to machine learning algorithms and the water is classified as safe or unsafe for the usage of domestic purposes. The Flask applications predicts water quality safety using an XG Boost classifier trained on a dataset (waterQuality1.csv). The dataset undergoes preprocessing where missing values are dropped and object type columns are converted to numeric types. Categorical target variables are encoded for machine learning compatibility. The model is trained on the processed data, evaluated for accuracy, and then used to predict the safest status ("Safe" or "Not Safe")based on user-inputted water quality parameters. Predicted results are displayed ton users on a web page rendered using Flask (predictdailyhousehold.html).The proposed work uses various ML models such as Logistic Regression, Support Vector Machine (SVM), XG Boost(XG) and Random Forest(RF) to classify whether the water is drinkable. The XG boost classifier is selected for the explanation and yields optimum Accuracy and F1-Score of 0.98, with Precision and Re-call of 0.97 and 0.99 respectively. This work is an emerging research at present with a vision of addressing the water quality for the future as well.