Abstract
The air quality within urban public transport is a critical determinant of passenger health. In the crowded and poorly ventilated cabins of Almaty's metro, buses, and trolleybuses, concentrations of CO(2) and PM(2.5) often accumulate, elevating the risk of respiratory and cardiovascular diseases. This study investigates the air quality along three of the city's busiest transport corridors, analyzing how the concentrations of CO(2), PM(2.5), and PM(10), as well as the temperature and relative humidity, fluctuate with the passenger density and time of day. Continuous measurements were collected using the Tynys mobile IoT device, which was bench-calibrated against a commercial reference sensor. Several machine learning models (logistic regression, decision tree, XGBoost, and random forest) were trained on synchronized environmental and occupancy data, with the XGBoost model achieving the highest predictive accuracy at 91.25%. Our analysis confirms that passenger occupancy is the primary driver of in-cabin pollution and that these machine learning models effectively capture the nonlinear relationships among environmental variables. Since the surveyed routes serve Almaty's most densely populated districts, improving the ventilation on these lines is of immediate importance to public health. Furthermore, the high-temporal-resolution data revealed short-term pollution spikes that correspond with peak ridership, advancing the current understanding of exposure risks in transit. These findings highlight the urgent need to combine real-time monitoring with ventilation upgrades. They also demonstrate the practical value of using low-cost IoT technologies and data-driven analytics to safeguard public health in urban mobility systems.