AI-Driven Adaptive Ventilation Systems For Real-Time Pollution Control In Industrial And Urban Settings: A Systematic Review

Abstract

The escalating urbanization and industrial activities in cities have significantly impacted air quality, posing health risks and environmental challenges that demand innovative solutions. This review systematically explores the integration of artificial intelligence (AI) and Internet of Things (IoT) sensors within smart cities, focusing on their role in real-time air quality monitoring and dynamic response mechanisms. By adhering to PRISMA guidelines, we analyze recent advancements in AI-driven automated control systems, which utilize IoT sensors to continuously monitor pollutants, including nitrogen dioxide (NO₂), sulfur dioxide (SO₂), carbon monoxide (CO), and particulate matter (PM). The data gathered by these sensors feed into AI algorithms that facilitate immediate, adaptive responses, such as modifying traffic light sequences to alleviate congestion and notifying nearby facilities to adjust emissions during high pollution periods. This review synthesizes findings on the effectiveness, limitations, and scalability of these systems, highlighting key challenges like sensor data accuracy, privacy considerations, and the infrastructure required for city-wide deployment. The paper concludes by emphasizing the transformative potential of AI and IoT in fostering sustainable urban environments and presents recommendations for future research and policy improvements to optimize smart city air quality management.