Machine Learning-Driven System for Real-Time Air Quality Monitoring and Prediction

This project introduces a machine learning-driven system for real-time air quality monitoring and prediction, utilizing MQ-135, MQ-9, and MQ-6 sensors alongside a DHT sensor. The MQ-13 sensor measures the concentration of carbon dioxide (CO2) and ammonia (NH3), the MQ-9 sensor detects methane (CH4) and liquefied petroleum gas (LPG), while the MQ-6 sensor monitors alcohol and carbon monoxide (CO) levels. The DHT sensor provides concurrent temperature and humidity data. This multi-sensor data is collected and transmitted to a machine learning model to compute the Air Quality Index (AQI), which represents the overall air quality. The system aims to deliver accurate, real-time air quality assessments and predictive insights, enabling timely interventions and better environmental management. By combining diverse sensor data with advanced machine learning techniques, this approach enhances the precision and effectiveness of air quality monitoring and prediction.