AI BASED APPROACHES FOR REAL-TIME AIR QUALITY MONITORING IN URBAN ENVIROMENTS (AI BASED FOR AQM)

Urban air pollution poses a significant threat to human health and environmental well-being, necessitating novel monitoring solutions. Traditional approaches frequently fail owing to limits in coverage, resolution, and data dependability. This research presents an innovative AI driven system designed for real-time air quality monitoring in metropolitan environments. The suggested system uses a mix of machine learning and deep learning approaches to dramatically improve prediction accuracy, dependability, and operating efficiency. The integration of AI-based sensor networks and prediction models is important to this approach, since it allows for the quick detection of pollution sources and hotspots. Technical implementation entails the use of a variety of machine learning methods, such as decision trees, random forests, support vector machines, and 279 gradient-boosting machines. Deep learning architectures, most notably the AQNet-CNN model, are used to interpret time-series sensor data by extracting spatial correlations and identifying patterns indicative of air pollution levels. Evaluation criteria such as mean absolute error, coefficient of determination, and root mean square error demonstrate the suggested approach's efficacy. These findings highlight the need of implementing cutting-edge technology to combat urban air pollution and promote sustainable urban development. The information utilized in this study was acquired from air quality sensors positioned across Malta, proving that the suggested framework is relevant and applicable to metropolitan areas.