Prediction of Drinking Water Quality for Effective Public Health Management to Avoid Water Borne Diseases

The issue of water quality failure is a persistent global concern that leads to sickness, toxicity, the spread of diseases, and loss of life in metropolitan areas. Various physical, functional, and ecological factors may affect drinking water quality. These concerns include the incursion of pollutants into water pipes, leakage, the formation of disinfectant waste products, the penetration of chemicals or microbes, and pollution. Water-borne Diseases (WD) have emerged as a significant global public health issue. It is imperative to forecast the quality of drinkable water by utilizing an automated model that provides a preventive strategy that may be created to enhance public health management (PHM). This study forecasted the Drinking Water Quality (DWQ) to promote Public Health Management (PHM) strategies to prevent WD. Convolutional Neural Network (CNN) with Inverse Distance Loaded (IDL) interpolation has been used to forecast DWQ. One hundred five water specimens from the research region underwent thorough examination via physiochemical and microbiological analyses. The tested characteristics were pH, turbidity, temperature, fluoride concentration levels, and bacterial counts (Faecal Coliforms) to prevent WD. The test findings indicated that the CNN-IDL projected 35% of water specimens from the domestic pipeline network had bacteria levels below what the WHO considers acceptable. Also, about 57% of the samples from the home pipeline network met the fluoride reference values set by the WHO. The sanitary assessment rating clearly showed that the lack of appropriate measures to protect against multiple barriers resulted in declining water quality for users. The findings of this research will be valuable to administrators in implementing essential strategies to avoid WD before it significantly impacts public health.