The project focuses on the prediction and classification of water quality using machine learning algorithms. By leveraging a dataset containing key water parameters, the system applies Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), and ensemble techniques such as Stacking and Voting classifiers to predict the water quality index and classify water quality levels into categories. This automated solution aims to replace traditional water quality testing methods, offering an efficient and scalable approach to water monitoring. The system is implemented with a user-friendly web interface that allows users to input water parameters and receive classification results instantly. The models are evaluated using accuracy, precision, recall, and F1-score, ensuring high performance in classification tasks. The integration of ensemble methods helps improve the overall prediction quality, enhancing model robustness and reliability. The project contributes to advancing the understanding of water quality classification using machine learning methods.

Keywords: water quality, prediction, classification, machine learning, Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), ensemble methods, Stacking, Voting classifiers, web interface.