A systematic review of artificial intelligence applications for indoor air quality monitoring in educational settings

Air pollution in indoor environments poses significant health risks, particularly in sensitive areas like schools, where children are more vulnerable. Traditional air quality monitoring methods are often inadequate, as they lack the capacity to provide real-time, predictive data essential for timely and proactive interventions. This systematic review investigates the role of artificial intelligence (AI), machine learning (ML), and deep learning (DL) in advancing indoor air quality (IAQ) monitoring and management. By analyzing recent studies, this review demonstrates how AI-driven models improve IAQ monitoring by forecasting pollutant concentrations, optimizing ventilation systems, and enhancing the accuracy of low-cost sensors. The review identifies successful implementations of AI in educational settings, highlighting applications such as supervised and unsupervised learning for pollutant prediction, anomaly detection, and reinforcement learning (RL) for heating, ventilation, and air conditioning (HVAC) optimization. However, several challenges remain, such as data scarcity, limited model interpretability, and difficulties in integrating with existing building management systems (BMS), which limit scalability and generalizability. To address these challenges, this review outlines future research directions, such as conducting long-term studies in dynamic, real-world environments and advancing AI and internet of things (IoT) integration. By bridging this gap, the goal is to develop an effective and accessible IAQ solution tailored for schools in hot and arid climates, ensuring healthier environment for students and educators.