Air pollution is a substantial detriment to industrial safety, environmental sustainability, an‎d human health. Urbanization, industrial activities, an‎d vehicle emissions raise the concentrations of dangerous pollutants such as particulate matter (PM2.5, PM10), CO₂, NOx, VOCs, an‎d other gases. Air quality monitoring an‎d forecasting systems are essential to making guided decisions, responding to regulatory requirements, an‎d undertaking preventive action. The existing monitored air quality systems are limited by high cost, large size, an‎d long investment time, reducing their effectiveness in creating actionable insights while indicating a need for low-cost, smart, an‎d scalable systems. A review of recent literature shows that substantial developments have taken place using Internet of Things (IoT) technologies an‎d machine learning (ML) methods such as long short-term memory (LSTM), gated recurrent unit (GRU), an‎d Conv1D-LSTM. Earlier efforts have established low-cost sensor networks, microcontroller-based platforms, an‎d machine learning solutions for monitoring air quality indoors an‎d outdoors, an‎d predicting pollutants. Although these platforms an‎d methods can be informative, they often suffer from gaps in the pollutant an‎d geographic scope, reliability in sensor data retrieva‎l, short-term forecast constantly, lack of real-time capabilities, an‎d scalability across multiple settings. Addressing these shortcomings could enable a more reliable, responsive, an‎d intelligent air quality management system. Therefore, the research presents a novel architecture for monitoring an‎d forecasting air quality using IoT. The purpose of the proposed solutions, which feature low-cost hardware, heavy connectivity an‎d predictive intelligence, is to overcome the limitations of current architectures, an‎d provide a full-fledged tool for addressing air quality in urban, industrial, an‎d indoor settings, while laying the groundwork for automation an‎d other forms of proactive environmental control in future work.

10/29/2025 12:00:00 AM

88164

1404/08/12

A Comprehensive Review of AI-Driven IoT Approaches for Real-Time Air Quality Monitoring an‎d Anomaly Detection

Air Quality Monitoring , Internet of Things (IoT) , Artificial Intelligence (AI) , Low-Cost Sensors , Predictive Analytics , Environmental Management , Urban Pollution