Machine Learning Model to Define Water Potability Considering Distinctive Chemical Contaminants

Ensuring drinking water safety is crucial for maintaining public health and preventing waterborne diseases. To ensure clean and safe drinking water for all, it is vital to continuously monitor, treat, and adhere to quality standards. We specifically designed and developed a hybrid model to predict water drinkability accurately by analyzing diverse chemical contaminants, making a significant contribution to our objective. The hybrid model will help the water supply department to ensure the water quality before supply and this way water safety will be ensured. Substantial advancements have been made across various datasets and enhanced our infrastructure to develop a sophisticated machine learning model for assessing the quality of drinking water. The model is developed based on meta-learning and few-shot learning and then some machine learning models are applied to define the success of our model. The maximum accuracy was found to be 98% using the proposed model.