Real-Time Air Quality Intelligence: Low-Cost Smart Urban Monitoring Using Deep Time-Series Models

Air quality affects large urban areas, where rapid urban development and human activities place constant pressure on ecosystems and public health. In this context, large-scale air quality assessment, supported by short-term forecasts, can provide useful information for environmental management and decision-making in urban areas, thus supporting evidence-based urban environmental management. The aim of this work is to design an affordable, smart real-time air pollution monitoring and prediction system for urban planning in overpopulated locations, which is deeply related to community health. The system focuses on real-time monitoring and forecasting of air quality. Prediction tasks were limited to gaseous pollutants CO and CO2. Measurements were obtained over four months from a low-cost sensor platform installed in a highly populated neighborhood district in Baghdad, Iraq. Air quality prediction of gas concentrations was done using three types of time-series algorithms: Long Short-Term Memory, or LSTM; Gated Recurrent Unit, or GRU; and Temporal Convolutional Network, or TCN, models. Among these, the LSTM architecture showed more stable behavior and a higher predictive R2, ranging from 98.2% to 98.9%. Generally, the findings suggest that combining low-cost sensing technologies with artificial intelligence can offer a feasible and scalable solution for urban air quality monitoring. This approach may support cost-effective strategies for monitoring air quality in resource-constrained urban environments.