Environmental degradation, particularly water contamination, has gotten significantly worse in recent years as a consequence of increased economic activity and population growth. Monitoring water quality is a critical part of water pollution prevention and management. As a fundamental human right and an integral part of sound public health policy, everyone should have access to clean drinking water. This is an concern of local importance in terms of health and development. Reductions in adverse health consequences and health care expenses outweigh the interventions' costs in some regions, indicating that water supply and sanitation expenditures might have a positive economic impact. Controlling water contamination necessitates continuous, real-time monitoring of water quality. It needs a lot of time and money to implement biological and lab-based approaches to water pollution reduction. This research introduces a new Sequential Learning Neural Network (SLNN) for the prediction and classification of water quality as a solution to this problem. There are two primary steps in the proposed model: preprocessing of data and classification of water quality. Data pre-processing takes place in a variety of ways, including data transformation, data splitting, and data normalisation, at the beginning of the process. In addition, the SLNN model makes use of several water variables to predict and classify water quality. Data includes pH, Hardness, Solids, Chloramines, Sulfate and Turbidity, is used to test the projected model's performance. The proposed model outperformed the other models in the tests, according to the findings.

Drinking Water; Pre-processing; Sequential Learning Neural Network; Water Pollution; Water Quality.