SMART WATER QUALITY MONITORING SYSTEM

Abstract

The essential importance of water quality necessitates efficient and continuous monitoring to avoid potential health risks and environmental harm. This study introduces a Smart Water Quality Monitoring System (SWQMS), which uses the progressive integration of the Internet of Things (IoT) and machine learning technologies for the real-time monitoring and prediction of water quality. The system is equipped with high-accuracy sensors for measuring pH and Total Dissolved Solids (TDS), fundamental water quality parameters for water health. These sensors were integrated with Arduino UNO R3 micro controller and ESP8266 Wi-Fi module to collect and transfer data to the cloud. The system used the ThingSpeak cloud platform, which visualises the data in real-time and employs end-to-end XGBoost ML domain URL hosted by AWS to predict the EWQI accurately. After comprehensive analysis against other algorithms like Deep Neural Netwroks (DNN) and Random Forest (RF), the model is selected for its better performance. It is optimized and deployed using Flask, Docker and AWS Beanstalk to provide scalable and robust predictive capabilities. This system is a significant advancement in environmental monitoring, providing a cost-effective, efficient and scalable solution for water quality management. Through its real-time data prediction, SWQMS promises to revolutionise water quality monitoring practices, empowering stakeholders including the normal public to make prompt environmental and human health protection decisions.